@article{mayakonda2016maftools,
title={Maftools: Efficient analysis, visualization and summarization of MAF files from large-scale cohort based cancer studies.},
author={Mayakonda, Anand and Koeffler, H Phillip},
journal={bioRxiv},
pages={052662},
year={2016},
publisher={Cold Spring Harbor Labs Journals}
}
@article {ChedraouiSilva148726,
author = {Chedraoui Silva, Tiago and Coetzee, Simon G. and Yao, Lijing and Hazelett, Dennis J. and Noushmehr, Houtan and Berman, Benjamin P.},
title = {Enhancer Linking by Methylation/Expression Relationships with the R package ELMER version 2},
year = {2017},
doi = {10.1101/148726},
publisher = {Cold Spring Harbor Laboratory},
abstract = {Recent studies indicate that DNA methylation can be used to identify changes at transcriptional enhancers and other cis-regulatory elements in primary human samples. A systematic approach to inferring gene regulatory networks has been provided by the R/Bioconductor package ELMER (Enhancer Linking by Methylation/Expression Relationships), which first identifies DNA methylation changes in distal regulatory elements and correlates these with the expression of nearby genes to identify direct transcriptional targets. Next, ELMER performs a transcription factor binding motif analysis and integrates with expression profiling of all human transcription factors, to identify master regulatory TFs and place each differentially methylated regulatory element into the context of an altered gene regulatory network (GRN). Here we present a completely updated version of the package (ELMER v. 2.0), which uses the latest Bioconductor data structures including the popular MultiAsssayExperiment, supports multiple reference genome assemblies as well as the DNA methylation platforms Infinium MethylationEPIC and Infinium HumanMethylation450, and provides a {\textquoteright}Supervised{\textquoteright} analysis mode for paired sample study designs (such as treated vs. untreated replicate samples). It also supports data import from the new NCI Genomic Data Commons (GDC) database. The new version is substantially re-written, improving stability, performance, and extensibility. It also uses improved databases for transcription factor binding domain families and binding motif specificities, and has newly designed output plots for publication-quality figures. Below, we describe the methods and new features of ELMER v. 2.0 and present two use case demonstrating how the tool can be used to analyze TCGA data in either Unsupervised or Supervised mode. ELMER (v2.0.0) is available as an R/Bioconductor package at https://github.com/tiagochst/ELMER. Also, ELMER.data (v2.0.0), which provides auxiliary data required to perform the analysis, is available at https://github.com/tiagochst/ELMER.data.},
URL = {https://www.biorxiv.org/content/early/2017/10/10/148726},
eprint = {https://www.biorxiv.org/content/early/2017/10/10/148726.full.pdf},
journal = {bioRxiv}
}
@article{zhou2016comprehensive,
title={Comprehensive characterization, annotation and innovative use of Infinium DNA methylation BeadChip probes},
author={Zhou, Wanding and Laird, Peter W and Shen, Hui},
journal={Nucleic Acids Research},
pages={gkw967},
year={2016},
publisher={Oxford Univ Press}
}
@article{doi:10.1093/nar/gkw967,
author = {Zhou, Wanding and Laird, Peter W. and Shen, Hui},
title = {Comprehensive characterization, annotation and innovative use of Infinium DNA methylation BeadChip probes},
journal = {Nucleic Acids Research},
volume = {45},
number = {4},
pages = {e22},
year = {2017},
doi = {10.1093/nar/gkw967},
URL = { + http://dx.doi.org/10.1093/nar/gkw967},
eprint = {/oup/backfile/Content_public/Journal/nar/45/4/10.1093_nar_gkw967/2/gkw967.pdf}
}
@article{durinck2009mapping,
title={Mapping identifiers for the integration of genomic datasets with the R/Bioconductor package biomaRt},
author={Durinck, Steffen and Spellman, Paul T and Birney, Ewan and Huber, Wolfgang},
journal={Nature protocols},
volume={4},
number={8},
pages={1184--1191},
year={2009},
publisher={Nature Publishing Group}
}
@article{yates2015ensembl,
title={Ensembl 2016},
author={Yates, Andrew and Akanni, Wasiu and Amode, M Ridwan and Barrell, Daniel and Billis, Konstantinos and Carvalho-Silva, Denise and Cummins, Carla and Clapham, Peter and Fitzgerald, Stephen and Gil, Laurent and others},
journal={Nucleic acids research},
pages={gkv1157},
year={2015},
publisher={Oxford Univ Press}
}
@article{durinck2005biomart,
title={BioMart and Bioconductor: a powerful link between biological databases and microarray data analysis},
author={Durinck, Steffen and Moreau, Yves and Kasprzyk, Arek and Davis, Sean and De Moor, Bart and Brazma, Alvis and Huber, Wolfgang},
journal={Bioinformatics},
volume={21},
number={16},
pages={3439--3440},
year={2005},
publisher={Oxford Univ Press}
}
@article{benjamini1995controlling,
title={Controlling the false discovery rate: a practical and powerful approach to multiple testing},
author={Benjamini, Yoav and Hochberg, Yosef},
journal={Journal of the royal statistical society. Series B (Methodological)},
pages={289--300},
year={1995},
publisher={JSTOR}
}
@article{heinz2010simple,
title={Simple combinations of lineage-determining transcription factors prime cis-regulatory elements required for macrophage and B cell identities},
author={Heinz, Sven and Benner, Christopher and Spann, Nathanael and Bertolino, Eric and Lin, Yin C and Laslo, Peter and Cheng, Jason X and Murre, Cornelis and Singh, Harinder and Glass, Christopher K},
journal={Molecular cell},
volume={38},
number={4},
pages={576--589},
year={2010},
publisher={Elsevier}
}
@article{kulakovskiy2016hocomoco,
title={HOCOMOCO: expansion and enhancement of the collection of transcription factor binding sites models},
author={Kulakovskiy, Ivan V and Vorontsov, Ilya E and Yevshin, Ivan S and Soboleva, Anastasiia V and Kasianov, Artem S and Ashoor, Haitham and Ba-Alawi, Wail and Bajic, Vladimir B and Medvedeva, Yulia A and Kolpakov, Fedor A and others},
journal={Nucleic acids research},
volume={44},
number={D1},
pages={D116--D125},
year={2016},
publisher={Oxford Univ Press}
}
@article{wingender2013tfclass,
title={TFClass: an expandable hierarchical classification of human transcription factors},
author={Wingender, Edgar and Schoeps, Torsten and D{\"o}nitz, J{\"u}rgen},
journal={Nucleic acids research},
volume={41},
number={D1},
pages={D165--D170},
year={2013},
publisher={Oxford Univ Press}
}
@article{gu2016complex,
title={Complex heatmaps reveal patterns and correlations in multidimensional genomic data},
author={Gu, Zuguang and Eils, Roland and Schlesner, Matthias},
journal={Bioinformatics},
volume={32},
number={18},
pages={2847--2849},
year={2016},
publisher={Oxford University Press}
}
@article{Stark01012006,
author = {Stark, Chris and Breitkreutz, Bobby-Joe and Reguly, Teresa and Boucher, Lorrie and Breitkreutz, Ashton and Tyers, Mike},
title = {BioGRID: a general repository for interaction datasets},
volume = {34},
number = {suppl 1},
pages = {D535-D539},
year = {2006},
doi = {10.1093/nar/gkj109},
abstract ={Access to unified datasets of protein and genetic interactions is critical for interrogation of gene/protein function and analysis of global network properties. BioGRID is a freely accessible database of physical and genetic interactions available at http://www.thebiogrid.org. BioGRID release version 2.0 includes >116 000 interactions from Saccharomyces cerevisiae, Caenorhabditis elegans, Drosophila melanogaster and Homo sapiens. Over 30 000 interactions have recently been added from 5778 sources through exhaustive curation of the Saccharomyces cerevisiae primary literature. An internally hyper-linked web interface allows for rapid search and retrieval of interaction data. Full or user-defined datasets are freely downloadable as tab-delimited text files and PSI-MI XML. Pre-computed graphical layouts of interactions are available in a variety of file formats. User-customized graphs with embedded protein, gene and interaction attributes can be constructed with a visualization system called Osprey that is dynamically linked to the BioGRID.},
URL = {http://nar.oxfordjournals.org/content/34/suppl_1/D535.abstract},
eprint = {http://nar.oxfordjournals.org/content/34/suppl_1/D535.full.pdf+html},
journal = {Nucleic Acids Research}
}
@article{mayakonda2016maftools,
title={Maftools: Efficient analysis, visualization and summarization of MAF files from large-scale cohort based cancer studies.},
author={Mayakonda, Anand and Koeffler, H Phillip},
journal={bioRxiv},
pages={052662},
year={2016},
publisher={Cold Spring Harbor Labs Journals}
}
@Article{10.12688/f1000research.8923.2,
AUTHOR = { Silva, TC and Colaprico, A and Olsen, C and D'Angelo, F and Bontempi, G and Ceccarelli, M and Noushmehr, H},
TITLE = {TCGA Workflow: Analyze cancer genomics and epigenomics data using Bioconductor packages [version 2; referees: 1 approved, 1 approved with reservations] },
JOURNAL = {F1000Research},
VOLUME = {5},
YEAR = {2016},
NUMBER = {1542},
DOI = {10.12688/f1000research.8923.2}
}
@article{cancer2014integrated_thca,
title={Integrated genomic characterization of papillary thyroid carcinoma},
author={Cancer Genome Atlas Research Network and others},
journal={Cell},
volume={159},
number={3},
pages={676--690},
year={2014},
publisher={Elsevier}
}
@article{cancer2015genomic_skcm,
title={Genomic classification of cutaneous melanoma},
author={Cancer Genome Atlas Network and others},
journal={Cell},
volume={161},
number={7},
pages={1681--1696},
year={2015},
publisher={Elsevier}
}
@article{cancer2014comprehensive_stad,
title={Comprehensive molecular characterization of gastric adenocarcinoma},
author={Cancer Genome Atlas Research Network and others},
journal={Nature},
volume={513},
number={7517},
pages={202--209},
year={2014},
publisher={Nature Publishing Group}
}
@article{cancer2012comprehensive_lusc,
title={Comprehensive genomic characterization of squamous cell lung cancers},
author={Cancer Genome Atlas Research Network and others},
journal={Nature},
volume={489},
number={7417},
pages={519--525},
year={2012},
publisher={Nature Publishing Group}
}
@article{cancer2015molecular_prad,
title={The molecular taxonomy of primary prostate cancer},
author={Cancer Genome Atlas Research Network and others},
journal={Cell},
volume={163},
number={4},
pages={1011--1025},
year={2015},
publisher={Elsevier}
}
@article{cancer2016comprehensive,
title={Comprehensive molecular characterization of papillary renal-cell carcinoma},
author={Cancer Genome Atlas Research Network and others},
journal={N Engl J Med},
volume={2016},
number={374},
pages={135--145},
year={2016},
publisher={Mass Medical Soc}
}
@article{davis2014somatic,
title={The somatic genomic landscape of chromophobe renal cell carcinoma},
author={Davis, Caleb F and Ricketts, Christopher J and Wang, Min and Yang, Lixing and Cherniack, Andrew D and Shen, Hui and Buhay, Christian and Kang, Hyojin and Kim, Sang Cheol and Fahey, Catherine C and others},
journal={Cancer cell},
volume={26},
number={3},
pages={319--330},
year={2014},
publisher={Elsevier}
}
@article{cancer2013comprehensive,
title={Comprehensive molecular characterization of clear cell renal cell carcinoma},
author={Cancer Genome Atlas Research Network and others},
journal={Nature},
volume={499},
number={7456},
pages={43--49},
year={2013},
publisher={Nature Publishing Group}
}
@article{cancer2015comprehensive,
title={Comprehensive genomic characterization of head and neck squamous cell carcinomas},
author={Cancer Genome Atlas Network and others},
journal={Nature},
volume={517},
number={7536},
pages={576--582},
year={2015},
publisher={Nature Publishing Group}
}
@article{zheng2016comprehensive,
title={Comprehensive Pan-Genomic Characterization of Adrenocortical Carcinoma},
author={Zheng, Siyuan and Cherniack, Andrew D and Dewal, Ninad and Moffitt, Richard A and Danilova, Ludmila and Murray, Bradley A and Lerario, Antonio M and Else, Tobias and Knijnenburg, Theo A and Ciriello, Giovanni and others},
journal={Cancer cell},
volume={29},
number={5},
pages={723--736},
year={2016},
publisher={Elsevier}
}
@article{Gu20052016,
author = {Gu, Zuguang and Eils, Roland and Schlesner, Matthias},
title = {Complex heatmaps reveal patterns and correlations in multidimensional genomic data},
year = {2016},
doi = {10.1093/bioinformatics/btw313},
abstract ={Summary: Parallel heatmaps with carefully designed annotation graphics are powerful for efficient visualization of patterns and relationships among high dimensional genomic data. Here we present the ComplexHeatmap package that provides rich functionalities for customizing heatmaps, arranging multiple parallel heatmaps and including user-defined annotation graphics. We demonstrate the power of ComplexHeatmap to easily reveal patterns and correlations among multiple sources of information with four real-world datasets.Availability: The ComplexHeatmap package and documentation are freely available from the Bioconductor project: http://www.bioconductor.org/packages/devel/bioc/html/ComplexHeatmap.html.Contact: m.schlesner@dkfz.deSupplementary information: Supplementary data are available at Bioinformatics online.},
URL = {http://bioinformatics.oxfordjournals.org/content/early/2016/05/20/bioinformatics.btw313.abstract},
eprint = {http://bioinformatics.oxfordjournals.org/content/early/2016/05/20/bioinformatics.btw313.full.pdf+html},
journal = {Bioinformatics}
}
@article{montojo2010genemania,
author = {Montojo, J and Zuberi, K and Rodriguez, H and Kazi, F and Wright, G and Donaldson, S L and Morris, Q and Bader, G D},
title = {{GeneMANIA Cytoscape plugin: fast gene function predictions on the desktop}},
journal = {Bioinformatics},
year = {2010},
volume = {26},
number = {22},
pages = {2927--2928},
month = nov
}
@article{samur2014rtcgatoolbox,
title={RTCGAToolbox: A New Tool for Exporting TCGA Firehose Data},
author={Samur, Mehmet Kemal},
year={2014}
}
@article{nishida2006histone,
title={Histone H3 acetylated at lysine 9 in promoter is associated with low nucleosome density in the vicinity of transcription start site in human cell},
author={Nishida, Hiromi and Suzuki, Takahiro and Kondo, Shinji and Miura, Hisashi and Fujimura, Yu-ichi and Hayashizaki, Yoshihide},
journal={Chromosome Research},
volume={14},
number={2},
pages={203--211},
year={2006},
publisher={Springer}
}
@ARTICLE{Tarjan72depthfirst,
author = {Robert Tarjan},
title = {Depth first search and linear graph algorithms},
journal = {SIAM Journal on Computing},
year = {1972}
}
@article{mercier2011integrated,
title={An integrated pipeline for the genome-wide analysis of transcription factor binding sites from ChIP-Seq},
author={Mercier, Eloi and Droit, Arnaud and Li, Leping and Robertson, Gordon and Zhang, Xuekui and Gottardo, Raphael},
journal={PLoS One},
volume={6},
number={2},
pages={e16432},
year={2011},
publisher={Public Library of Science}
}
@article{mahony2007stamp,
title={STAMP: a web tool for exploring DNA-binding motif similarities},
author={Mahony, Shaun and Benos, Panayiotis V},
journal={Nucleic acids research},
volume={35},
number={suppl 2},
pages={W253--W258},
year={2007},
publisher={Oxford Univ Press}
}
@article{mahony2007dna,
title={DNA familial binding profiles made easy: comparison of various motif alignment and clustering strategies},
author={Mahony, Shaun and Auron, Philip E and Benos, Panayiotis V},
journal={PLoS Comput Biol},
volume={3},
number={3},
pages={e61},
year={2007},
publisher={Public Library of Science}
}
@article{li2009gadem,
title={GADEM: a genetic algorithm guided formation of spaced dyads coupled with an EM algorithm for motif discovery},
author={Li, Leping},
journal={Journal of Computational Biology},
volume={16},
number={2},
pages={317--329},
year={2009},
publisher={Mary Ann Liebert, Inc. 2 Madison Avenue Larchmont, NY 10538 USA}
}
@misc{mercier2014motiv,
title={Motiv: Motif identification and validation},
author={Mercier, Eloi and Gottardo, Raphael},
year={2014}
}
@misc{ou2013motifstack,
title={motifStack: Plot stacked logos for single or multiple DNA, RNA and amino acid sequence},
author={Ou, J and Brodsky, M and Wolfe, S and Zhu, LJ},
year={2013}
}
@misc{droit2015rgadem,
title={rGADEM: De novo motif discovery},
author={Droit, A and Gottardo, R and Roberston, G and Li, L},
year={2015}
}
@article{phillips2008role,
title={The role of methylation in gene expression},
author={Phillips, Theresa},
journal={Nature Education},
volume={1},
number={1},
pages={116},
year={2008}
}
@article{yao2015demystifying,
title={Demystifying the secret mission of enhancers: linking distal regulatory elements to target genes},
author={Yao, Lijing and Berman, Benjamin P and Farnham, Peggy J},
journal={Critical reviews in biochemistry and molecular biology},
volume={50},
number={6},
pages={550--573},
year={2015},
publisher={Taylor \& Francis}
}
@article{sur2012mice,
title={Mice lacking a Myc enhancer that includes human SNP rs6983267 are resistant to intestinal tumors},
author={Sur, Inderpreet Kaur and Hallikas, Outi and V{\"a}h{\"a}rautio, Anna and Yan, Jian and Turunen, Mikko and Enge, Martin and Taipale, Minna and Karhu, Auli and Aaltonen, Lauri A and Taipale, Jussi},
journal={Science},
volume={338},
number={6112},
pages={1360--1363},
year={2012},
publisher={American Association for the Advancement of Science}
}
@article{groschel2014single,
title={A single oncogenic enhancer rearrangement causes concomitant EVI1 and GATA2 deregulation in leukemia},
author={Gr{\"o}schel, Stefan and Sanders, Mathijs A and Hoogenboezem, Remco and de Wit, Elzo and Bouwman, Britta AM and Erpelinck, Claudia and van der Velden, Vincent HJ and Havermans, Marije and Avellino, Roberto and van Lom, Kirsten and others},
journal={Cell},
volume={157},
number={2},
pages={369--381},
year={2014},
publisher={Elsevier}
}
@article{cancer2014comprehensive_lung,
title={Comprehensive molecular profiling of lung adenocarcinoma},
author={Cancer Genome Atlas Research Network and others},
journal={Nature},
volume={511},
number={7511},
pages={543--550},
year={2014},
publisher={Nature Publishing Group}
}
@article{giorgio2015large,
title={A large genomic deletion leads to enhancer adoption by the lamin B1 gene: a second path to autosomal dominant leukodystrophy (ADLD)},
author={Giorgio, Elisa and Robyr, Daniel and Spielmann, Malte and Ferrero, Enza and Di Gregorio, Eleonora and Imperiale, Daniele and Vaula, Giovanna and Stamoulis, Georgios and Santoni, Federico and Atzori, Cristiana and others},
journal={Human molecular genetics},
pages={ddv065},
year={2015},
publisher={Oxford Univ Press}
}
@article{cancer2014comprehensive_gastric,
title={Comprehensive molecular characterization of gastric adenocarcinoma},
author={Cancer Genome Atlas Research Network and others},
journal={Nature},
volume={513},
number={7517},
pages={202--209},
year={2014},
publisher={Nature Publishing Group}
}
@article{cancer2012comprehensive_colon,
title={Comprehensive molecular characterization of human colon and rectal cancer},
author={Cancer Genome Atlas Network and others},
journal={Nature},
volume={487},
number={7407},
pages={330--337},
year={2012},
publisher={Nature Publishing Group}
}
@article{shi2014integrative,
title={Integrative Analysis of High-throughput Cancer Studies With Contrasted Penalization},
author={Shi, Xingjie and Liu, Jin and Huang, Jian and Zhou, Yong and Shia, BenChang and Ma, Shuangge},
journal={Genetic epidemiology},
volume={38},
number={2},
pages={144--151},
year={2014},
publisher={Wiley Online Library}
}
@article{cancer2012comprehensive_brca,
title={Comprehensive molecular portraits of human breast tumours},
author={Cancer Genome Atlas Network and others},
journal={Nature},
volume={490},
number={7418},
pages={61--70},
year={2012},
publisher={Nature Publishing Group}
}
@article{rhodes2005integrative,
title={Integrative analysis of the cancer transcriptome},
author={Rhodes, Daniel R and Chinnaiyan, Arul M},
journal={Nature genetics},
volume={37},
pages={S31--S37},
year={2005},
publisher={Nature Publishing Group}
}
@article{marabita2013evaluation,
title={An evaluation of analysis pipelines for DNA methylation profiling using the Illumina HumanMethylation450 BeadChip platform},
author={Marabita, Francesco and Almgren, Malin and Lindholm, Mal{\'e}ne E and Ruhrmann, Sabrina and Fagerstr{\"o}m-Billai, Fredrik and Jagodic, Maja and Sundberg, Carl J and Ekstr{\"o}m, Tomas J and Teschendorff, Andrew E and Tegn{\'e}r, Jesper and others},
journal={Epigenetics},
volume={8},
number={3},
pages={333--346},
year={2013},
publisher={Taylor \& Francis}
}
@article{deaton2011cpg,
title={CpG islands and the regulation of transcription},
author={Deaton, Aim{\'e}e M and Bird, Adrian},
journal={Genes \& development},
volume={25},
number={10},
pages={1010--1022},
year={2011},
publisher={Cold Spring Harbor Lab}
}
@article{TCGAbiolinks,
author = {Colaprico, Antonio and Silva, Tiago C. and Olsen, Catharina and Garofano, Luciano and Cava, Claudia and Garolini, Davide and Sabedot, Thais S. and Malta, Tathiane M. and Pagnotta, Stefano M. and Castiglioni, Isabella and Ceccarelli, Michele and Bontempi, Gianluca and Noushmehr, Houtan},
title = {TCGAbiolinks: an R/Bioconductor package for integrative analysis of TCGA data},
volume = {44},
number = {8},
pages = {e71},
year = {2016},
doi = {10.1093/nar/gkv1507},
abstract ={The Cancer Genome Atlas (TCGA) research network has made public a large collection of clinical and molecular phenotypes of more than 10 000 tumor patients across 33 different tumor types. Using this cohort, TCGA has published over 20 marker papers detailing the genomic and epigenomic alterations associated with these tumor types. Although many important discoveries have been made by TCGA's research network, opportunities still exist to implement novel methods, thereby elucidating new biological pathways and diagnostic markers. However, mining the TCGA data presents several bioinformatics challenges, such as data retrieval and integration with clinical data and other molecular data types (e.g. RNA and DNA methylation). We developed an R/Bioconductor package called TCGAbiolinks to address these challenges and offer bioinformatics solutions by using a guided workflow to allow users to query, download and perform integrative analyses of TCGA data. We combined methods from computer science and statistics into the pipeline and incorporated methodologies developed in previous TCGA marker studies and in our own group. Using four different TCGA tumor types (Kidney, Brain, Breast and Colon) as examples, we provide case studies to illustrate examples of reproducibility, integrative analysis and utilization of different Bioconductor packages to advance and accelerate novel discoveries.},
URL = {http://nar.oxfordjournals.org/content/44/8/e71.abstract},
eprint = {http://nar.oxfordjournals.org/content/44/8/e71.full.pdf+html},
journal = {Nucleic Acids Research}
}
@article{Cell,
title = "Molecular Profiling Reveals Biologically Discrete Subsets and Pathways of Progression in Diffuse Glioma ",
journal = "Cell ",
volume = "164",
number = "3",
pages = "550 - 563",
year = "2016",
note = "",
issn = "0092-8674",
doi = "http://dx.doi.org/10.1016/j.cell.2015.12.028",
url = "http://www.sciencedirect.com/science/article/pii/S009286741501692X",
author = "Michele Ceccarelli and FlorisP. Barthel and TathianeM. Malta and ThaisS. Sabedot and SofieR. Salama and BradleyA. Murray and Olena Morozova and Yulia Newton and Amie Radenbaugh and StefanoM. Pagnotta and Samreen Anjum and Jiguang Wang and Ganiraju Manyam and Pietro Zoppoli and Shiyun Ling and ArjunA. Rao and Mia Grifford and AndrewD. Cherniack and Hailei Zhang and Laila Poisson and CarlosGilberto Carlotti Jr. and DanielaPrettidaCunha Tirapelli and Arvind Rao and Tom Mikkelsen and ChingC. Lau and W.K.Alfred Yung and Raul Rabadan and Jason Huse and DanielJ. Brat and NormanL. Lehman and JillS. Barnholtz-Sloan and Siyuan Zheng and Kenneth Hess and Ganesh Rao and Matthew Meyerson and Rameen Beroukhim and Lee Cooper and Rehan Akbani and Margaret Wrensch and David Haussler and KennethD. Aldape and PeterW. Laird and DavidH. Gutmann and Samreen Anjum and Harindra Arachchi and J.Todd Auman and Miruna Balasundaram and Saianand Balu and Gene Barnett and Stephen Baylin and Sue Bell and Christopher Benz and Natalie Bir and KeithL. Black and Tom Bodenheimer and Lori Boice and MoizS. Bootwalla and Jay Bowen and ChristopherA. Bristow and YaronS.N. Butterfield and Qing-Rong Chen and Lynda Chin and Juok Cho and Eric Chuah and Sudha Chudamani and SimonG. Coetzee and MarkL. Cohen and Howard Colman and Marta Couce and Fulvio D’Angelo and Tanja Davidsen and Amy Davis and JohnA. Demchok and Karen Devine and Li Ding and Rebecca Duell and J.Bradley Elder and JenniferM. Eschbacher and Ashley Fehrenbach and Martin Ferguson and Scott Frazer and Gregory Fuller and Jordonna Fulop and StaceyB. Gabriel and Luciano Garofano and JulieM. Gastier-Foster and Nils Gehlenborg and Mark Gerken and Gad Getz and Caterina Giannini and WilliamJ. Gibson and Angela Hadjipanayis and D.Neil Hayes and DavidI. Heiman and Beth Hermes and Joe Hilty and KatherineA. Hoadley and AlanP. Hoyle and Mei Huang and StuartR. Jefferys and CorbinD. Jones and StevenJ.M. Jones and Zhenlin Ju and Alison Kastl and Ady Kendler and Jaegil Kim and Raju Kucherlapati and PhillipH. Lai and MichaelS. Lawrence and Semin Lee and KristenM. Leraas and TaraM. Lichtenberg and Pei Lin and Yuexin Liu and Jia Liu and JuliaY. Ljubimova and Yiling Lu and Yussanne Ma and DennisT. Maglinte and HarshadS. Mahadeshwar and MarcoA. Marra and Mary McGraw and Christopher McPherson and Shaowu Meng and PiotrA. Mieczkowski and C.Ryan Miller and GordonB. Mills and RichardA. Moore and LisleE. Mose and AndrewJ. Mungall and Rashi Naresh and Theresa Naska and Luciano Neder and MichaelS. Noble and Ardene Noss and BrianPatrick O’Neill and QuinnT. Ostrom and Cheryl Palmer and Angeliki Pantazi and Michael Parfenov and PeterJ. Park and JoelS. Parker and CharlesM. Perou and ChristopherR. Pierson and Todd Pihl and Alexei Protopopov and Amie Radenbaugh and NilsaC. Ramirez and W.Kimryn Rathmell and Xiaojia Ren and Jeffrey Roach and A.Gordon Robertson and Gordon Saksena and JacquelineE. Schein and StevenE. Schumacher and Jonathan Seidman and Kelly Senecal and Sahil Seth and Hui Shen and Yan Shi and Juliann Shih and Kristen Shimmel and Hugues Sicotte and Suzanne Sifri and Tiago Silva and JanaeV. Simons and Rosy Singh and Tara Skelly and AndrewE. Sloan and HeidiJ. Sofia and MatthewG. Soloway and Xingzhi Song and Carrie Sougnez and Camila Souza and SusanM. Staugaitis and Huandong Sun and Charlie Sun and Donghui Tan and Jiabin Tang and Yufang Tang and Leigh Thorne and FelipeAmstalden Trevisan and Timothy Triche and DavidJ. VanDenBerg and Umadevi Veluvolu and Doug Voet and Yunhu Wan and Zhining Wang and Ronald Warnick and JohnN. Weinstein and DanielJ. Weisenberger and MatthewD. Wilkerson and Felicia Williams and Lisa Wise and Yingli Wolinsky and Junyuan Wu and AndrewW. Xu and Lixing Yang and Liming Yang and TravisI. Zack and JeanC. Zenklusen and Jianhua Zhang and Wei Zhang and Jiashan Zhang and Erik Zmuda and Houtan Noushmehr and Antonio Iavarone and Roel G.W. Verhaak",
abstract = "Summary Therapy development for adult diffuse glioma is hindered by incomplete knowledge of somatic glioma driving alterations and suboptimal disease classification. We defined the complete set of genes associated with 1,122 diffuse grade II-III-IV gliomas from The Cancer Genome Atlas and used molecular profiles to improve disease classification, identify molecular correlations, and provide insights into the progression from low- to high-grade disease. Whole-genome sequencing data analysis determined that \{ATRX\} but not \{TERT\} promoter mutations are associated with increased telomere length. Recent advances in glioma classification based on \{IDH\} mutation and 1p/19q co-deletion status were recapitulated through analysis of \{DNA\} methylation profiles, which identified clinically relevant molecular subsets. A subtype of \{IDH\} mutant glioma was associated with \{DNA\} demethylation and poor outcome; a group of IDH-wild-type diffuse glioma showed molecular similarity to pilocytic astrocytoma and relatively favorable survival. Understanding of cohesive disease groups may aid improved clinical outcomes. "
}
@Article{Cote,
Author="Cote, R. and Reisinger, F. and Martens, L. and Barsnes, H. and Vizcaino, J. A. and Hermjakob, H. ",
Title="{{T}he {O}ntology {L}ookup {S}ervice: bigger and better}",
Journal="Nucleic Acids Res.",
Year="2010",
Volume="38",
Number="Web Server issue",
Pages="W155--160",
Month="Jul"
}
% 21075792
@Article{Fingerman,
Author="Fingerman, I. M. and McDaniel, L. and Zhang, X. and Ratzat, W. and Hassan, T. and Jiang, Z. and Cohen, R. F. and Schuler, G. D. ",
Title="{{N}{C}{B}{I} {E}pigenomics: a new public resource for exploring epigenomic data sets}",
Journal="Nucleic Acids Res.",
Year="2011",
Volume="39",
Number="Database issue",
Pages="D908--912",
Month="Jan"
}
@misc{hahne2015gviz,
title={Gviz: Plotting data and annotation information along genomic coordinates. Bioconductor. 2015},
author={Hahne, F and Durinck, S and Ivanek, R and Mueller, A and Lianoglou, S and Tan, G},
year={2015}
}
@article{yu2015chipseeker,
title={ChIPseeker: an R/Bioconductor package for ChIP peak annotation, comparison and visualization},
author={Yu, Guangchuang and Wang, Li-Gen and He, Qing-Yu},
journal={Bioinformatics},
pages={btv145},
year={2015},
publisher={Oxford Univ Press}
}
% 22120008
@Article{Berman,
Author="Berman, B. P. and Weisenberger and others ",
Title="{{R}egions of focal {D}{N}{A} hypermethylation and long-range hypomethylation in colorectal cancer coincide with nuclear lamina-associated domains}",
Journal="Nat. Genet.",
Year="2012",
Volume="44",
Number="1",
Pages="40--46",
Month="Jan"
}
% 24120142
@Article{Brennan,
Author="Brennan, C. W. and Verhaak and others ",
Title="{{T}he somatic genomic landscape of glioblastoma}",
Journal="Cell",
Year="2013",
Volume="155",
Number="2",
Pages="462--477",
Month="Oct"
}
% 24885402
@Article{Rhie,
Author="Rhie, S. K. and Hazelett, D. J. and Coetzee, S. G. and Yan, C. and Noushmehr, H. and Coetzee, G. A. ",
Title="{{N}ucleosome positioning and histone modifications define relationships between regulatory elements and nearby gene expression in breast epithelial cells}",
Journal="BMC Genomics",
Year="2014",
Volume="15",
Pages="331"
}
% 20399149
@Article{Noushmehr,
Author="Noushmehr, H. and Weisenberger, D. J. and others",
Title="{{I}dentification of a {C}p{G} island methylator phenotype that defines a distinct subgroup of glioma}",
Journal="Cancer Cell",
Year="2010",
Volume="17",
Number="5",
Pages="510--522",
Month="May"
}
% 20531367
@Article{Hawkins,
Author="Hawkins, R. D. and Hon, G. C. and Ren, B. ",
Title="{{N}ext-generation genomics: an integrative approach}",
Journal="Nat. Rev. Genet.",
Year="2010",
Volume="11",
Number="7",
Pages="476--486",
Month="Jul"
}
% 25311424
@Article{Rodriguez,
Author="Rodriguez, R. and Miller, K. M. ",
Title="{{U}nravelling the genomic targets of small molecules using high-throughput sequencing}",
Journal="Nat. Rev. Genet.",
Year="2014",
Volume="15",
Number="12",
Pages="783--796",
Month="Dec"
}
% 22770212
@Article{Dawson,
Author="Dawson, M. A. and Kouzarides, T. ",
Title="{{C}ancer epigenetics: from mechanism to therapy}",
Journal="Cell",
Year="2012",
Volume="150",
Number="1",
Pages="12--27",
Month="Jul"
}
@article{morganellagaia,
title={GAIA: Genomic Analysis of Important Aberrations},
author={Morganella, Sandro and Pagnotta, Stefano Maria and Ceccarelli, Michele}
}
% 25263941
@Article{Yang,
Author="Yang, X. and Han, H. and De Carvalho, D. D. and Lay, F. D. and Jones, P. A. and Liang, G. ",
Title="{{G}ene body methylation can alter gene expression and is a therapeutic target in cancer}",
Journal="Cancer Cell",
Year="2014",
Volume="26",
Number="4",
Pages="577--590",
Month="Oct"
}
@Article{Meyer2008,
author="Meyer, Patrick E.
and Lafitte, Fr{\'e}d{\'e}ric
and Bontempi, Gianluca",
title="minet: A R/Bioconductor Package for Inferring Large Transcriptional Networks Using Mutual Information",
journal="BMC Bioinformatics",
year="2008",
volume="9",
number="1",
pages="1--10",
abstract="This paper presents the R/Bioconductor package minet (version 1.1.6) which provides a set of functions to infer mutual information networks from a dataset. Once fed with a microarray dataset, the package returns a network where nodes denote genes, edges model statistical dependencies between genes and the weight of an edge quantifies the statistical evidence of a specific (e.g transcriptional) gene-to-gene interaction. Four different entropy estimators are made available in the package minet (empirical, Miller-Madow, Schurmann-Grassberger and shrink) as well as four different inference methods, namely relevance networks, ARACNE, CLR and MRNET. Also, the package integrates accuracy assessment tools, like F-scores, PR-curves and ROC-curves in order to compare the inferred network with a reference one.",
issn="1471-2105",
doi="10.1186/1471-2105-9-461",
url="http://dx.doi.org/10.1186/1471-2105-9-461"
}
@Article{Altay2011,
author="Altay, G{\"o}kmen
and Emmert-Streib, Frank",
title="Structural influence of gene networks on their inference: analysis of C3NET",
journal="Biology Direct",
year="2011",
volume="6",
number="1",
pages="1--16",
abstract="The availability of large-scale high-throughput data possesses considerable challenges toward their functional analysis. For this reason gene network inference methods gained considerable interest. However, our current knowledge, especially about the influence of the structure of a gene network on its inference, is limited.",
issn="1745-6150",
doi="10.1186/1745-6150-6-31",
url="http://dx.doi.org/10.1186/1745-6150-6-31"
}
@article{castro2012reder,
title={RedeR: R/Bioconductor package for representing modular structures, nested networks and multiple levels of hierarchical associations},
author={Castro, MA and Wang, Xin and Fletcher, MN and Meyer, Kerstin B and Markowetz, Florian},
journal={Genome Biol},
volume={13},
number={4},
pages={R29},
year={2012}
}
% 15526163
@Article{Hermann,
Author="Hermann, A. and Gowher, H. and Jeltsch, A. ",
Title="{{B}iochemistry and biology of mammalian {D}{N}{A} methyltransferases}",
Journal="Cell. Mol. Life Sci.",
Year="2004",
Volume="61",
Number="19-20",
Pages="2571--2587",
Month="Oct"
}
@article{luo2013pathview,
title={Pathview: an R/Bioconductor package for pathway-based data integration and visualization},
author={Luo, Weijun and Brouwer, Cory},
journal={Bioinformatics},
volume={29},
number={14},
pages={1830--1831},
year={2013},
publisher={Oxford Univ Press}
}
% 25394363
@Article{Wong,
Author="Wong, E. S. and Thybert, D. and Schmitt, B. M. and Stefflova, K. and Odom, D. T. and Flicek, P. ",
Title="{{D}ecoupling of evolutionary changes in transcription factor binding and gene expression in mammals}",
Journal="Genome Res.",
Year="2015",
Volume="25",
Number="2",
Pages="167--178",
Month="Feb"
}
@article{creyghton2010histone,
title={Histone H3K27ac separates active from poised enhancers and predicts developmental state},
author={Creyghton, Menno P and Cheng, Albert W and Welstead, G Grant and Kooistra, Tristan and Carey, Bryce W and Steine, Eveline J and Hanna, Jacob and Lodato, Michael A and Frampton, Garrett M and Sharp, Phillip A and others},
journal={Proceedings of the National Academy of Sciences},
volume={107},
number={50},
pages={21931--21936},
year={2010},
publisher={National Acad Sciences}
}
% 19752007
@Article{Sharma,
Author="Sharma, S. and Kelly, T. K. and Jones, P. A. ",
Title="{{E}pigenetics in cancer}",
Journal="Carcinogenesis",
Year="2010",
Volume="31",
Number="1",
Pages="27--36",
Month="Jan"
}
@article{rada2011unique,
title={A unique chromatin signature uncovers early developmental enhancers in humans},
author={Rada-Iglesias, Alvaro and Bajpai, Ruchi and Swigut, Tomek and Brugmann, Samantha A and Flynn, Ryan A and Wysocka, Joanna},
journal={Nature},
volume={470},
number={7333},
pages={279--283},
year={2011},
publisher={Nature Publishing Group}
}
% 21376230
@Article{Hanahan,
Author="Hanahan, D. and Weinberg, R. A. ",
Title="{{H}allmarks of cancer: the next generation}",
Journal="Cell",
Year="2011",
Volume="144",
Number="5",
Pages="646--674",
Month="Mar"
}
@article{heintzman2009histone,
title={Histone modifications at human enhancers reflect global cell-type-specific gene expression},
author={Heintzman, Nathaniel D and Hon, Gary C and Hawkins, R David and Kheradpour, Pouya and Stark, Alexander and Harp, Lindsey F and Ye, Zhen and Lee, Leonard K and Stuart, Rhona K and Ching, Christina W and others},
journal={Nature},
volume={459},
number={7243},
pages={108--112},
year={2009},
publisher={Nature Publishing Group}
}
@article{peters2003partitioning,
title={Partitioning and plasticity of repressive histone methylation states in mammalian chromatin},
author={Peters, Antoine HFM and Kubicek, Stefan and Mechtler, Karl and O'Sullivan, Roderick J and Derijck, Alwin AHA and Perez-Burgos, Laura and Kohlmaier, Alexander and Opravil, Susanne and Tachibana, Makoto and Shinkai, Yoichi and others},
journal={Molecular cell},
volume={12},
number={6},
pages={1577--1589},
year={2003},
publisher={Elsevier}
}
@article{bonasio2010molecular,
title={Molecular signals of epigenetic states},
author={Bonasio, Roberto and Tu, Shengjiang and Reinberg, Danny},
journal={science},
volume={330},
number={6004},
pages={612--616},
year={2010},
publisher={American Association for the Advancement of Science}
}
@article{bernstein2005genomic,
title={Genomic maps and comparative analysis of histone modifications in human and mouse},
author={Bernstein, Bradley E and Kamal, Michael and Lindblad-Toh, Kerstin and Bekiranov, Stefan and Bailey, Dione K and Huebert, Dana J and McMahon, Scott and Karlsson, Elinor K and Kulbokas, Edward J and Gingeras, Thomas R and others},
journal={Cell},
volume={120},
number={2},
pages={169--181},
year={2005},
publisher={Elsevier}
}
@article{heintzman2007distinct,
title={Distinct and predictive chromatin signatures of transcriptional promoters and enhancers in the human genome},
author={Heintzman, Nathaniel D and Stuart, Rhona K and Hon, Gary and Fu, Yutao and Ching, Christina W and Hawkins, R David and Barrera, Leah O and Van Calcar, Sara and Qu, Chunxu and Ching, Keith A and others},
journal={Nature genetics},
volume={39},
number={3},
pages={311--318},
year={2007},
publisher={Nature Publishing Group}
}
@article{safran2010genecards,
title={GeneCards Version 3: the human gene integrator},
author={Safran, Marilyn and Dalah, Irina and Alexander, Justin and Rosen, Naomi and Stein, Tsippi Iny and Shmoish, Michael and Nativ, Noam and Bahir, Iris and Doniger, Tirza and Krug, Hagit and others},
journal={Database},
volume={2010},
pages={baq020},
year={2010},
publisher={Oxford University Press}
}
% 21941284
@Article{Baylin,
Author="Baylin, S. B. and Jones, P. A. ",
Title="{{A} decade of exploring the cancer epigenome - biological and translational implications}",
Journal="Nat. Rev. Cancer",
Year="2011",
Volume="11",
Number="10",
Pages="726--734",
Month="Oct"
}
@article{siegmund2011statistical,
title={Statistical approaches for the analysis of DNA methylation microarray data},
author={Siegmund, Kimberly D},
journal={Human genetics},
volume={129},
number={6},
pages={585--595},
year={2011},
publisher={Springer}
}
@article{noushmehr2010identification,
title={Identification of a CpG island methylator phenotype that defines a distinct subgroup of glioma},
author={Noushmehr, Houtan and Weisenberger, Daniel J and Diefes, Kristin and Phillips, Heidi S and Pujara, Kanan and Berman, Benjamin P and Pan, Fei and Pelloski, Christopher E and Sulman, Erik P and Bhat, Krishna P and others},
journal={Cancer cell},
volume={17},
number={5},
pages={510--522},
year={2010},
publisher={Elsevier}
}
@article{robertson2005dna,
title={DNA methylation and human disease},
author={Robertson, Keith D},
journal={Nature Reviews Genetics},
volume={6},
number={8},
pages={597--610},
year={2005},
publisher={Nature Publishing Group}
}
@Article{Bernstein,
Author="Bernstein, B. E. and Stamatoyannopoulos, J. A. and Costello, J. F. and Ren, B. and Milosavljevic, A. and Meissner, A. and Kellis, M. and Marra, M. A. and Beaudet, A. L. and Ecker, J. R. and Farnham, P. J. and Hirst, M. and Lander, E. S. and Mikkelsen, T. S. and Thomson, J. A. ",
Title="{{T}he {N}{I}{H} {R}oadmap {E}pigenomics {M}apping {C}onsortium}",
Journal="Nat. Biotechnol.",
Year="2010",
Volume="28",
Number="10",
Pages="1045--1048",
Month="Oct"
}
@Article{methylKit,
AUTHOR = {Akalin, Altuna and Kormaksson, Matthias and Li, Sheng and Garrett-Bakelman, Francine and Figueroa, Maria and Melnick, Ari and Mason, Christopher},
TITLE = {methylKit: a comprehensive R package for the analysis of genome-wide DNA methylation profiles},
JOURNAL = {Genome Biology},
VOLUME = {13},
YEAR = {2012},
NUMBER = {10},
PAGES = {R87},
URL = {http://genomebiology.com/2012/13/10/R87},
DOI = {10.1186/gb-2012-13-10-r87},
PubMedID = {23034086},
ISSN = {1465-6906},
ABSTRACT = {DNA methylation is a chemical modification of cytosine bases that is pivotal for gene regulation,
cellular specification and cancer development. Here, we describe an R package, methylKit, that
rapidly analyzes genome-wide cytosine epigenetic profiles from high-throughput methylation and
hydroxymethylation sequencing experiments. methylKit includes functions for clustering, sample
quality visualization, differential methylation analysis and annotation features, thus automating
and simplifying many of the steps for discerning statistically significant bases or regions of DNA
methylation. Finally, we demonstrate methylKit on breast cancer data, in which we find statistically
significant regions of differential methylation and stratify tumor subtypes. methylKit is available
at http://code.google.com/p/methylkit webcite.},
}
@inproceedings{Rob13,
author = {Robbins, David E. and Gr\"{u}neberg, Alexander and Deus, Helena F. and Tanik, Murat M. and Almeida, Jonas},
title = {TCGA Toolbox: An Open Web App Framework for Distributing Big Data Analysis Pipelines for Cancer Genomics},
booktitle = {Proceedings of the International Conference on Bioinformatics, Computational Biology and Biomedical Informatics},
series = {BCB'13},
year = {2013},
isbn = {978-1-4503-2434-2},
location = {Wshington DC, USA},
pages = {62:62--62:67},
articleno = {62},
numpages = {6},
url = {http://doi.acm.org/10.1145/2506583.2506595},
doi = {10.1145/2506583.2506595},
acmid = {2506595},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {Big Data, Genomics, The Cancer Genome Atlas},
}
@article{Zhu14,
author = {Zhu, Yitan and Qiu, Peng and Ji, Yuan},
citeulike-article-id = {13204408},
citeulike-linkout-0 = {http://dx.doi.org/10.1038/nmeth.2956},
citeulike-linkout-1 = {http://dx.doi.org/10.1038/nmeth.2956},
day = {29},
doi = {10.1038/nmeth.2956},
issn = {1548-7091},
journal = {Nat Meth},
month = jun,
number = {6},
pages = {599--600},
posted-at = {2014-05-30 09:26:54},
priority = {5},
publisher = {Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.},
title = {{TCGA}-Assembler: open-source software for retrieving and processing {TCGA} data},
url = {http://dx.doi.org/10.1038/nmeth.2956},
volume = {11},
year = {2014}
}
@book{Jam13,
author = {James, Gareth and Witten, Daniela and Hastie, Trevor and Tibshirani, Robert},
citeulike-article-id = {12889876},
citeulike-linkout-0 = {http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20\&path=ASIN/1461471370},
citeulike-linkout-1 = {http://www.amazon.de/exec/obidos/redirect?tag=citeulike01-21\&path=ASIN/1461471370},
citeulike-linkout-2 = {http://www.amazon.fr/exec/obidos/redirect?tag=citeulike06-21\&path=ASIN/1461471370},
citeulike-linkout-3 = {http://www.amazon.jp/exec/obidos/ASIN/1461471370},
citeulike-linkout-4 = {http://www.amazon.co.uk/exec/obidos/ASIN/1461471370/citeulike00-21},
citeulike-linkout-5 = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20\&path=ASIN/1461471370},
citeulike-linkout-6 = {http://www.worldcat.org/isbn/1461471370},
citeulike-linkout-7 = {http://books.google.com/books?vid=ISBN1461471370},
citeulike-linkout-8 = {http://www.amazon.com/gp/search?keywords=1461471370\&index=books\&linkCode=qs},
citeulike-linkout-9 = {http://www.librarything.com/isbn/1461471370},
day = {12},
edition = {1st ed. 2013. Corr. 4th printing 2014},
howpublished = {Hardcover},
isbn = {1461471370},
keywords = {data\_analysis, multivariate, regression, statistics},
month = aug,
posted-at = {2014-10-24 13:57:01},
priority = {4},
publisher = {Springer},
title = {An Introduction to Statistical Learning: with Applications in R (Springer Texts in Statistics)},
url = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20\&path=ASIN/1461471370},
year = {2013}
}
@misc{gwas1,
author = {},
title = {Survival Analysis in {R}, \url{http://bioinformatics.ca/files/Statistics/Statistics_Day2-Module6.pdf
}},
year = {}
}
@misc{survival3,
author = {Diez},
title = {Survival Analysis in {R}, \url{https://www.openintro.org/download.php?file=survival_analysis_in_R\&referrer=/stat/surv.php}},
year = 2013
}
@misc{survival2,
author = {Hetzel},
title = {Statistics with {R} Survival analysis, \url{http://anson.ucdavis.edu/~hiwang/teaching/11fall/R_tutorial\%204.pdf}},
year = 2008
}
@misc{survival1,
author = {Sarkar},
title = {Statistics with {R} Survival analysis, \url{http://anson.ucdavis.edu/~hiwang/teaching/11fall/R_tutorial\%203.pdf}},
year = 2005
}
@misc{expression11,
author = {Plaisier},
title = {Gene Expression Analysis a Tutorial in {R}, \url{http://baliga.sy stemsbiology.net/introSysBio2 011/}},
year = 2011
}
@article{Ols14,
title = "Inference and validation of predictive gene networks from biomedical literature and gene expression data ",
journal = "Genomics ",
volume = "",
number = "0",
pages = " - ",
year = "2014",
note = "",
issn = "0888-7543",
doi = "http://dx.doi.org/10.1016/j.ygeno.2014.03.004",
url = "http://www.sciencedirect.com/science/article/pii/S0888754314000330",
author = "Catharina Olsen and Kathleen Fleming and Niall Prendergast and Renee Rubio and Frank Emmert-Streib and Gianluca Bontempi and Benjamin Haibe-Kains and John Quackenbush",
keywords = "Network inference",
keywords = "Quantitative validation",
keywords = "Gene expression",
keywords = "Targeted perturbations "
}
@Article{Hau12,
AUTHOR = {Haury, Anne-Claire and Mordelet, Fantine and Vera-Licona, Paola and Vert, Jean-Philippe},
TITLE = {TIGRESS: Trustful Inference of Gene REgulation using Stability Selection},
JOURNAL = {BMC Systems Biology},
VOLUME = {6},
YEAR = {2012},
NUMBER = {1},
PAGES = {145},
URL = {http://www.biomedcentral.com/1752-0509/6/145},
DOI = {10.1186/1752-0509-6-145},
PubMedID = {23173819},
ISSN = {1752-0509},
ABSTRACT = {BACKGROUND:Inferring the structure of gene regulatory networks (GRN) from a collection of gene expression data has many potential applications, from the elucidation of complex biological processes to the identification of potential drug targets. It is however a notoriously difficult problem, for which the many existing methods reach limited accuracy.RESULTS:In this paper, we formulate GRN inference as a sparse regression problem and investigate the performance of a popular feature selection method, least angle regression (LARS) combined with stability selection, for that purpose. We introduce a novel, robust and accurate scoring technique for stability selection, which improves the performance of feature selection with LARS. The resulting method, which we call TIGRESS (for Trustful Inference of Gene REgulation with Stability Selection), was ranked among the top GRN inference methods in the DREAM5 gene network inference challenge. In particular, TIGRESS was evaluated to be the best linear regression-based method in the challenge. We investigate in depth the influence of the various parameters of the method, and show that a fine parameter tuning can lead to significant improvements and state-of-the-art performance for GRN inference, in both directed and undirected settings.CONCLUSIONS:TIGRESS reaches state-of-the-art performance on benchmark data, including both in silico and in vivo (E. coli and S. cerevisiae) networks. This study confirms the potential of feature selection techniques for GRN inference. Code and data are available on http://cbio.ensmp.fr/tigress webcite. Moreover, TIGRESS can be run online through the GenePattern platform (GP-DREAM, http://dream.broadinstitute.org webcite).},
}
@inproceedings{And11,
added-at = {2011-08-09T00:00:00.000+0200},
author = {Andrews, Emad A. M. and Bonner, Anthony J.},
biburl = {http://www.bibsonomy.org/bibtex/2d4aa0aad3abb013ef34c3bc28613be13/dblp},
booktitle = {IJCAI},
editor = {Walsh, Toby},
interhash = {f582b5c920416e30a45443edcd431e03},
intrahash = {d4aa0aad3abb013ef34c3bc28613be13},
isbn = {978-1-57735-516-8},
keywords = {dblp},
pages = {1635-1640},
publisher = {IJCAI/AAAI},
timestamp = {2011-08-09T00:00:00.000+0200},
title = {Explaining Genetic Knock-Out Effects Using Cost-Based Abduction.},
url = {http://dblp.uni-trier.de/db/conf/ijcai/ijcai2011.html#AndrewsB11},
year = 2011
}
@article{Jor10,
title={Metastasis-Associated Gene Expression Changes Predict Poor Outcomes in Patients with Dukes Stage B and C Colorectal Cancer},
author={Robert N Jorissen and Peter Gibbs and Michael Christie and Saurabh Prakash and Lara Lipton and Jayesh Desai and David Kerr and Lauri A Aaltonen and Diego Arango and Mogens Kruh?ffer and Torben F Orntoft and Claus Lindbjerg Andersen and Mike Gruidl and Vidya P Kamath and Steven Eschrich and Timothy J Yeatman and Oliver M Sieber},
year={2010},
journal={Clin Cancer Res}
}
@article{Oni10,
abstract = {The transcription factor {POU5f1}/{OCT4} controls pluripotency in mammalian {ES} cells, but little is known about its functions in the early embryo. We used time-resolved transcriptome analysis of zebrafish pou5f1 {MZspg} mutant embryos to identify genes regulated by Pou5f1. Comparison to mammalian systems defines evolutionary conserved Pou5f1 targets. Time-series data reveal many Pou5f1 targets with delayed or advanced onset of expression. We identify two Pou5f1-dependent mechanisms controlling developmental timing. First, several Pou5f1 targets are transcriptional repressors, mediating repression of differentiation genes in distinct embryonic compartments. We analyze her3 gene regulation as example for a repressor in the neural anlagen. Second, the dynamics of {SoxB1} group gene expression and Pou5f1-dependent regulation of her3 and {foxD3} uncovers differential requirements for {SoxB1} activity to control temporal dynamics of activation, and spatial distribution of targets in the embryo. We establish a mathematical model of the early Pou5f1 and {SoxB1} gene network to demonstrate regulatory characteristics important for developmental timing. The temporospatial structure of the zebrafish Pou5f1 target networks may explain aspects of the evolution of the mammalian stem cell networks.},
author = {Onichtchouk, D. and Geier, F. and Polok, B. and Messerschmidt, D.M. and Mossner, R. and Wendik, B. and Song, S. and Taylor, V. and Timmer, J. and Driever, W.},
citeulike-article-id = {6780699},
citeulike-linkout-0 = {http://dx.doi.org/10.1038/msb.2010.9},
citeulike-linkout-1 = {http://dx.doi.org/10.1038/msb20109},
day = {09},
doi = {10.1038/msb.2010.9},
journal = {Molecular Systems Biology},
keywords = {dataset-time-series, transcriptiona-regulatory-networks, zebrafish},
month = mar,
posted-at = {2010-03-22 16:03:06},
priority = {2},
publisher = {Nature Publishing Group},
title = {Zebrafish Pou5f1-dependent transcriptional networks in temporal control of early development},
url = {http://dx.doi.org/10.1038/msb.2010.9},
volume = {6},
year = {2010}
}
@article{Fuj07,
author = {Fujita, A. and Sato, J.R. and Garay-Malpartida, H.M. and Yamaguchi, R. and Miyano, S. and Sogayar, M.C. and Ferreira, C.E.},
citeulike-article-id = {7432603},
citeulike-linkout-0 = {http://dx.doi.org/10.1186/1752-0509-1-39},
day = {xx},
doi = {10.1186/1752-0509-1-39},
journal = {BMC systems biology},
keywords = {connotea, import, interaction},
month = {xx},
pages = {39},
posted-at = {2010-07-09 15:00:19},
priority = {2},
title = {Modeling gene expression regulatory networks with the sparse vector autoregressive model},
url = {http://dx.doi.org/10.1186/1752-0509-1-39},
volume = {1},
year = {2007}
}
@article{Muk07,
author = {N.D. Mukhopadhyay and
S. Chatterjee},
title = {Causality and pathway search in microarray time series experiment},
journal = {Bioinformatics},
volume = {23},
number = {4},
year = {2007},
pages = {442-449},
ee = {http://dx.doi.org/10.1093/bioinformatics/btl598},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@inproceedings{She09,
author = {Shermin, A. and Orgun, M.A.},
title = {Using dynamic bayesian networks to infer gene regulatory networks from expression profiles},
booktitle = {Proceedings of the 2009 ACM symposium on Applied Computing},
series = {SAC '09},
year = {2009},
isbn = {978-1-60558-166-8},
location = {Honolulu, Hawaii},
pages = {799--803},
numpages = {5},
url = {http://doi.acm.org/10.1145/1529282.1529449},
doi = {10.1145/1529282.1529449},
acmid = {1529449},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {cell cycle, dynamic bayesian network, gene expression, gene regulatory network},
}
@article{Per03,
author = {Perrin, B.E. and Ralaivola, L. and Mazurie, A. and Bottani, S. and Mallet, J. and Buc, D'alche F.},
citeulike-article-id = {3225500},
citeulike-linkout-0 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/19/suppl\_2/ii138},
journal = {Bioinformatics},
keywords = {bayesian-networks, grn-inference, rnn},
number = {Suppl. 2},
posted-at = {2008-09-11 14:01:05},
priority = {2},
title = {Gene network inference using dynamic bayesian-networks},
url = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/19/suppl\_2/ii138},
volume = {19},
year = {2003}
}
@article{Gra69,
abstract = {There occurs on some occasions a difficulty in deciding the direction of causality between two related variables and also whether or not feedback is occurring. Testable definitions of causality and feedback are proposed and illustrated by use of simple two-variable models. The important problem of apparent instantaneous causality is discussed and it is suggested that the problem often arises due to slowness in recording information or because a sufficiently wide class of possible causal variables has not been used. It can be shown that the cross spectrum between two variables can be decomposed into two parts, each relating to a single causal arm of a feedback situation. Measures of causal lag and causal strength can then be constructed. A generalisation of this result with the partial cross spectrum is suggested.},
author = {Granger, C.W.J.},
citeulike-article-id = {1303897},
citeulike-linkout-0 = {http://dx.doi.org/10.2307/1912791},
citeulike-linkout-1 = {http://www.jstor.org/stable/1912791},
doi = {10.2307/1912791},
issn = {00129682},
journal = {Econometrica},
month = aug,
number = {3},
pages = {424--438},
posted-at = {2008-04-18 18:11:50},
priority = {2},
publisher = {The Econometric Society},
title = {Investigating Causal Relations by Econometric Models and Cross-spectral Methods},
url = {http://dx.doi.org/10.2307/1912791},
volume = {37},
year = {1969}
}
@article{kundaje2015integrative,
title={Integrative analysis of 111 reference human epigenomes},
author={Kundaje, Anshul and Meuleman, Wouter and Ernst, Jason and Bilenky, Misha and Yen, Angela and Heravi-Moussavi, Alireza and Kheradpour, Pouya and Zhang, Zhizhuo and Wang, Jianrong and Ziller, Michael J and others},
journal={Nature},
volume={518},
number={7539},
pages={317--330},
year={2015},
publisher={Nature Publishing Group}
}
@article{altay2010inferring,
title={Inferring the conservative causal core of gene regulatory networks},
author={Altay, G{\"o}kmen and Emmert-Streib, Frank},
journal={BMC Systems Biology},
volume={4},
number={1},
pages={132},
year={2010},
publisher={BioMed Central Ltd}
}
@article{faith2007large,
title={Large-scale mapping and validation of Escherichia coli transcriptional regulation from a compendium of expression profiles},
author={Faith, Jeremiah J and Hayete, Boris and Thaden, Joshua T and Mogno, Ilaria and Wierzbowski, Jamey and Cottarel, Guillaume and Kasif, Simon and Collins, James J and Gardner, Timothy S},
journal={PLoS Biol},
volume={5},
number={1},
pages={e8},
year={2007}
}
@article{huynh2010inferring,
title={Inferring regulatory networks from expression data using tree-based methods},
author={Huynh-Thu, V{\^a}n Anh and Irrthum, Alexandre and Wehenkel, Louis and Geurts, Pierre},
journal={PloS one},
volume={5},
number={9},
pages={e12776},
year={2010},
publisher={Public Library of Science}
}
@article{Zha13,
title = "Using gene expression programming to infer gene regulatory networks from time-series data ",
journal = "Computational Biology and Chemistry ",
volume = "",
number = "0",
pages = " - ",
year = "2013",
note = "",
issn = "1476-9271",
doi = "http://dx.doi.org/10.1016/j.compbiolchem.2013.09.004",
url = "http://www.sciencedirect.com/science/article/pii/S1476927113000881",
author = "Y. Zhang and Y. Pu and H. Zhang and Y. Su and L. Zhang and J. Zhou"
}
@article{meyer2007information,
title={Information-theoretic inference of large transcriptional regulatory networks},
author={Meyer, Patrick E and Kontos, Kevin and Lafitte, Frederic and Bontempi, Gianluca},
journal={EURASIP journal on bioinformatics and systems biology},
volume={2007},
pages={8--8},
year={2007},
publisher={Hindawi Publishing Corp.}
}
@article{Gio13,
abstract = {Motivation: Coexpression networks are data-derived representations of genes behaving in a similar way across tissues and experimental conditions. They have been used for hypothesis generation and guilt-by-association approaches for inferring functions of previously unknown genes. So far, the main platform for expression data has been {DNA} microarrays; however, the recent development of {RNA}-seq allows for higher accuracy and coverage of transcript populations. It is therefore important to assess the potential for biological investigation of coexpression networks derived from this novel technique in a condition-independent dataset.},
author = {Giorgi, F.M. and Del~Fabbro, C. and Licausi, F.},
citeulike-article-id = {12059704},
citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btt053},
citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/content/29/6/717.abstract},
citeulike-linkout-2 = {http://bioinformatics.oxfordjournals.org/content/29/6/717.full.pdf},
citeulike-linkout-3 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/29/6/717},
citeulike-linkout-4 = {http://view.ncbi.nlm.nih.gov/pubmed/23376351},
citeulike-linkout-5 = {http://www.hubmed.org/display.cgi?uids=23376351},
day = {15},
doi = {10.1093/bioinformatics/btt053},
issn = {1460-2059},
journal = {Bioinformatics},
keywords = {arabidopsis, coexpression, microarray, network, rna-seq},
month = mar,
number = {6},
pages = {717--724},
pmid = {23376351},
posted-at = {2013-02-23 05:35:56},
priority = {2},
publisher = {Oxford University Press},
title = {Comparative study of {RNA}-seq- and Microarray-derived coexpression networks in Arabidopsis thaliana},
url = {http://dx.doi.org/10.1093/bioinformatics/btt053},
volume = {29},
year = {2013}
}
@article{Mar06b,
author = {Marbach, Daniel and Prill, Robert J. and Schaffter, Thomas and Mattiussi, Claudio and Floreano, Dario and Stolovitzky, Gustavo},
title = {Revealing strengths and weaknesses of methods for gene network inference},
volume = {107},
number = {14},
pages = {6286-6291},
year = {2010},
doi = {10.1073/pnas.0913357107},
abstract ={Numerous methods have been developed for inferring gene regulatory networks from expression data, however, both their absolute and comparative performance remain poorly understood. In this paper, we introduce a framework for critical performance assessment of methods for gene network inference. We present an in silico benchmark suite that we provided as a blinded, community-wide challenge within the context of the DREAM (Dialogue on Reverse Engineering Assessment and Methods) project. We assess the performance of 29 gene-network-inference methods, which have been applied independently by participating teams. Performance profiling reveals that current inference methods are affected, to various degrees, by different types of systematic prediction errors. In particular, all but the best-performing method failed to accurately infer multiple regulatory inputs (combinatorial regulation) of genes. The results of this community-wide experiment show that reliable network inference from gene expression data remains an unsolved problem, and they indicate potential ways of network reconstruction improvements.},
URL = {http://www.pnas.org/content/107/14/6286.abstract},
eprint = {http://www.pnas.org/content/107/14/6286.full.pdf+html},
journal = {Proceedings of the National Academy of Sciences}
}
@article{Mil02,
author = {Milo, R. and Shen-Orr, S. and Itzkovitz, S. and Kashtan, N. and Chklovskii, D. and Alon, U.},
title = {Network Motifs: Simple Building Blocks of Complex Networks},
volume = {298},
number = {5594},
pages = {824-827},
year = {2002},
doi = {10.1126/science.298.5594.824},
abstract ={Complex networks are studied across many fields of science. To uncover their structural design principles, we defined ?network motifs,? patterns of interconnections occurring in complex networks at numbers that are significantly higher than those in randomized networks. We found such motifs in networks from biochemistry, neurobiology, ecology, and engineering. The motifs shared by ecological food webs were distinct from the motifs shared by the genetic networks of Escherichia coli and Saccharomyces cerevisiae or from those found in the World Wide Web. Similar motifs were found in networks that perform information processing, even though they describe elements as different as biomolecules within a cell and synaptic connections between neurons in Caenorhabditis elegans. Motifs may thus define universal classes of networks. This approach may uncover the basic building blocks of most networks.},
URL = {http://www.sciencemag.org/content/298/5594/824.abstract},
eprint = {http://www.sciencemag.org/content/298/5594/824.full.pdf},
journal = {Science}
}
@article{Kha05,
author = {Khatri, P. and Draghici, S.},
title = {Ontological analysis of gene expression data: current tools, limitations, and open problems},
volume = {21},
number = {18},
pages = {3587-3595},
year = {2005},
doi = {10.1093/bioinformatics/bti565},
abstract ={Summary: Independent of the platform and the analysis methods used, the result of a microarray experiment is, in most cases, a list of differentially expressed genes. An automatic ontological analysis approach has been recently proposed to help with the biological interpretation of such results. Currently, this approach is the de facto standard for the secondary analysis of high throughput experiments and a large number of tools have been developed for this purpose. We present a detailed comparison of 14 such tools using the following criteria: scope of the analysis, visualization capabilities, statistical model(s) used, correction for multiple comparisons, reference microarrays available, installation issues and sources of annotation data. This detailed analysis of the capabilities of these tools will help researchers choose the most appropriate tool for a given type of analysis. More importantly, in spite of the fact that this type of analysis has been generally adopted, this approach has several important intrinsic drawbacks. These drawbacks are associated with all tools discussed and represent conceptual limitations of the current state-of-the-art in ontological analysis. We propose these as challenges for the next generation of secondary data analysis tools.Contact: sod@cs.wayne.edu},
URL = {http://bioinformatics.oxfordjournals.org/content/21/18/3587.abstract},
eprint = {http://bioinformatics.oxfordjournals.org/content/21/18/3587.full.pdf+html},
journal = {Bioinformatics}
}
@article{Ahn09,
author = {Ahn, S. AND Wang, R.T. AND Park, C.C. AND Lin, A. AND Leahy, R.M. AND Lange, K. AND Smith, D.J.},
journal = {PLoS Comput Biol},
publisher = {Public Library of Science},
title = {Directed Mammalian Gene Regulatory Networks Using Expression and Comparative Genomic Hybridization Microarray Data from Radiation Hybrids},
year = {2009},
month = {06},
volume = {5},
url = {http://dx.doi.org/10.1371%2Fjournal.pcbi.1000407},
pages = {e1000407},
abstract = {Author Summary
An important problem in systems biology is to map gene networks, which help identify gene functions and discover critical disease pathways. Current methods for constructing gene networks have identified a number of biologically significant functional modules. However, these networks do not reveal directionality, that is, which gene regulates which, an important aspect of gene regulation. Radiation hybrid panels are a venerable method for high resolution genetic mapping. Recently we have used radiation hybrids to map loci based on their effects on gene expression. Because these regulatory loci are finely mapped, we can identify which gene turns on another gene, that is, directionality. In this paper, we constructed directed networks from radiation hybrid expression data. We found the radiation hybrid networks concordant with available datasets but also demonstrate that they can reveal information inaccessible to existing approaches. Importantly, directionality can help dissect cause and effect in genetic networks, aiding in understanding and ultimately rational intervention.
},
number = {6},
doi = {10.1371/journal.pcbi.1000407}
}
@article{Ben95,
abstract = {The common approach to the multiplicity problem calls for controlling the familywise error rate ({FWER}). This approach, though, has faults, and we point out a few. A different approach to problems of multiple significance testing is presented. It calls for controlling the expected proportion of falsely rejected hypotheses-the false discovery rate. This error rate is equivalent to the {FWER} when all hypotheses are true but is smaller otherwise. Therefore, in problems where the control of the false discovery rate rather than that of the {FWER} is desired, there is potential for a gain in power. A simple sequential Bonferroni-type procedure is proved to control the false discovery rate for independent test statistics, and a simulation study shows that the gain in power is substantial. The use of the new procedure and the appropriateness of the criterion are illustrated with examples.},
author = {Benjamini, Y. and Hochberg, Y.},
citeulike-article-id = {1042553},
citeulike-linkout-0 = {http://dx.doi.org/10.2307/2346101},
citeulike-linkout-1 = {http://www.jstor.org/stable/2346101},
doi = {10.2307/2346101},
issn = {00359246},
journal = {Journal of the Royal Statistical Society. Series B (Methodological)},
keywords = {multiple-testing, significance},
number = {1},
pages = {289--300},
posted-at = {2007-02-12 20:49:34},
priority = {2},
publisher = {Blackwell Publishing for the Royal Statistical Society},
title = {Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing},
url = {http://dx.doi.org/10.2307/2346101},
volume = {57},
year = {1995}
}
@article{He10,
title = "Stable feature selection for biomarker discovery ",
journal = "Computational Biology and Chemistry ",
volume = "34",
number = "4",
pages = "215 - 225",
year = "2010",
note = "",
issn = "1476-9271",
author = "Z. He and W. Yu",
keywords = "Feature selection",
keywords = "Biomarker discovery",
keywords = "Stability",
keywords = "Machine learning "
}
@incollection{Geu10,
author = {P. Geurts},
title = {Bias vs Variance Decomposition for Regression and Classification},
booktitle = {Data Mining and Knowledge Discovery Handbook},
year = {2010},
pages = {733-746},
publisher = {springer},
}
@inproceedings{Ste56,
author = {Stein, James},
booktitle = {Proceedings of the Third Berkeley Symposium on Mathematical Statistics and Probability},
citeulike-article-id = {3212241},
citeulike-linkout-0 = {http://projecteuclid.org/DPubS?service=UI\&\#38;version=1.0\&\#38;verb=Display\&\#38;page=toc\&\#38;handle=euclid.bsmsp/1200501640},
citeulike-linkout-1 = {http://projecteuclid.org/euclid.bsmsp/1200501656},
editor = {Neyman, Jerzy},
keywords = {ebayes, paradox, rms, shrinkage, statistics},
location = {Statistical Laboratory of the University of California, Berkeley},
pages = {197--206},
posted-at = {2008-09-10 14:10:58},
priority = {0},
publisher = {University of California Press},
title = {Inadmissibility of the Usual Estimator for the Mean of a Multivariate Normal Distribution},
url = {http://projecteuclid.org/DPubS?service=UI\&\#38;version=1.0\&\#38;verb=Display\&\#38;page=toc\&\#38;handle=euclid.bsmsp/1200501640},
year = {1956}
}
@INPROCEEDINGS{Mei95,
author = {Ronny Meir},
title = {Bias, variance and the combination of estimators; The case of linear least squares},
booktitle = {In Advances in Neural Information Processing Systems 7},
year = {1995},
publisher = {Morgan Kaufmann}
}
@article{Nic11,
author = {Nicolau, M. and Levine, A.J. and Carlsson, G.},
title = {Topology based data analysis identifies a subgroup of breast cancers with a unique mutational profile and excellent survival},
volume = {108},
number = {17},
pages = {7265-7270},
year = {2011},
doi = {10.1073/pnas.1102826108},
abstract ={High-throughput biological data, whether generated as sequencing, transcriptional microarrays, proteomic, or other means, continues to require analytic methods that address its high dimensional aspects. Because the computational part of data analysis ultimately identifies shape characteristics in the organization of data sets, the mathematics of shape recognition in high dimensions continues to be a crucial part of data analysis. This article introduces a method that extracts information from high-throughput microarray data and, by using topology, provides greater depth of information than current analytic techniques. The method, termed Progression Analysis of Disease (PAD), first identifies robust aspects of cluster analysis, then goes deeper to find a multitude of biologically meaningful shape characteristics in these data. Additionally, because PAD incorporates a visualization tool, it provides a simple picture or graph that can be used to further explore these data. Although PAD can be applied to a wide range of high-throughput data types, it is used here as an example to analyze breast cancer transcriptional data. This identified a unique subgroup of Estrogen Receptor-positive (ER+) breast cancers that express high levels of c-MYB and low levels of innate inflammatory genes. These patients exhibit 100% survival and no metastasis. No supervised step beyond distinction between tumor and healthy patients was used to identify this subtype. The group has a clear and distinct, statistically significant molecular signature, it highlights coherent biology but is invisible to cluster methods, and does not fit into the accepted classification of Luminal A/B, Normal-like subtypes of ER+ breast cancers. We denote the group as c-MYB+ breast cancer.},
URL = {http://www.pnas.org/content/108/17/7265.abstract},
eprint = {http://www.pnas.org/content/108/17/7265.full.pdf+html},
journal = {Proceedings of the National Academy of Sciences}
}
@article{Sta11,
added-at = {2012-09-13T00:00:00.000+0200},
author = {Staiger, C. and Cadot, Sidney and Kooter, R. and Dittrich, Marcus T. and M?ller, Tobias and Klau, Gunnar W. and Wessels, Lodewyk F. A.},
biburl = {http://www.bibsonomy.org/bibtex/256db8dfc33174e54e1877e7aef3ffc69/dblp},
ee = {http://arxiv.org/abs/1110.3717},
interhash = {bd99e4862e0770d177ef9a95eb9e5380},
intrahash = {56db8dfc33174e54e1877e7aef3ffc69},
journal = {CoRR},
keywords = {dblp},
timestamp = {2012-09-13T00:00:00.000+0200},
title = {A critical evaluation of network and pathway based classifiers for outcome prediction in breast cancer},
url = {http://dblp.uni-trier.de/db/journals/corr/corr1110.html#abs-1110-3717},
volume = {abs/1110.3717},
year = 2011
}
@article{Chu07,
author={H.-Y. Chuang and E. Lee and Y.-T. Liu and D. Lee and T. Ideke},
journal={Molecular Systems Biology},
title={Network-based classification of breast cancer metastasis},
year={2007}
}
@book{Fel68,
added-at = {2007-04-10T16:00:38.000+0200},
author = {Feller, W.},
biburl = {http://www.bibsonomy.org/bibtex/2ffca3cfe18c41b3cf8b28a6604a59e58/andreab},
citeulike-article-id = {167212},
description = {An Introduction to Probability Theory and Its Applications},
howpublished = {Hardcover},
interhash = {5913bc93a52c1fad7ce8b0993debf407},
intrahash = {ffca3cfe18c41b3cf8b28a6604a59e58},
isbn = {0471257087},
keywords = {book combinatorics d4.1 discrete feller probability tagora},
month = {January},
priority = {2},
publisher = {Wiley},
timestamp = {2007-04-10T16:00:38.000+0200},
title = {An Introduction to Probability Theory and Its Applications},
url = {http://www.amazon.ca/exec/obidos/redirect?tag=citeulike04-20{\&}path=ASIN/0471257087},
volume = 1,
year = 1968
}
@article{Sir12,
author = {S\^irbu, , A. AND Kerr, , G. AND Crane, , M. AND Ruskin, , H.J.},
journal = {PLoS ONE},
publisher = {Public Library of Science},
title = {RNA-Seq vs Dual- and Single-Channel Microarray Data: Sensitivity Analysis for Differential Expression and Clustering},
year = {2012},
month = {12},
volume = {7},
url = {http://dx.doi.org/10.1371%2Fjournal.pone.0050986},
pages = {e50986},
abstract = {With the fast development of high-throughput sequencing technologies, a new generation of genome-wide gene expression measurements is under way. This is based on mRNA sequencing (RNA-seq), which complements the already mature technology of microarrays, and is expected to overcome some of the latter?s disadvantages. These RNA-seq data pose new challenges, however, as strengths and weaknesses have yet to be fully identified. Ideally, Next (or Second) Generation Sequencing measures can be integrated for more comprehensive gene expression investigation to facilitate analysis of whole regulatory networks. At present, however, the nature of these data is not very well understood. In this paper we study three alternative gene expression time series datasets for the Drosophila melanogaster embryo development, in order to compare three measurement techniques: RNA-seq, single-channel and dual-channel microarrays. The aim is to study the state of the art for the three technologies, with a view of assessing overlapping features, data compatibility and integration potential, in the context of time series measurements. This involves using established tools for each of the three different technologies, and technical and biological replicates (for RNA-seq and microarrays, respectively), due to the limited availability of biological RNA-seq replicates for time series data. The approach consists of a sensitivity analysis for differential expression and clustering. In general, the RNA-seq dataset displayed highest sensitivity to differential expression. The single-channel data performed similarly for the differentially expressed genes common to gene sets considered. Cluster analysis was used to identify different features of the gene space for the three datasets, with higher similarities found for the RNA-seq and single-channel microarray dataset.
},
number = {12},
doi = {10.1371/journal.pone.0050986}
}
@article{Chu02,
title={Assessment of the relationship between signal intensities and transcript concentration for Affymetrix GeneChip arrays.},
author={Chudin, E. and Walker, R. and Kosaka, A. and Wu, S.X. and Rabert, D. and Chang, T.K. and Kreder, D.E.},
journal={Genome Biol},
volume={3},
number={1},
pages={RESEARCH0005},
year={2002},
abstract={BACKGROUND Affymetrix microarrays have become increasingly popular in gene-expression studies; however, limitations of the technology have not been well established for commercially available arrays. The hybridization signal has been shown to be proportional to actual transcript concentration for specialized arrays containing hundreds of distinct probe pairs per gene. Additionally, the technology has been described as capable of distinguishing concentration levels within a factor of 2, and of detecting transcript frequencies as low as 1 in 2,000,000. Using commercially available arrays, we assessed these representations directly through a series of 'spike-in' hybridizations involving four prokaryotic transcripts in the absence and presence of fixed eukaryotic background. The contribution of probe-target interactions to the mismatch signal was quantified under various analyte concentrations. RESULTS A linear relationship between transcript abundance and signal was consistently observed between 1 pM and 10 pM transcripts. The signal ceased to be linear above the 10 pM level and commenced saturating around the 100 pM level. The 0.1 pM transcripts were virtually undetectable in the presence of eukaryotic background. Our measurements show that preponderance of the signal for mismatch probes derives from interactions with the target transcripts. CONCLUSIONS Landmark studies outlining an observed linear relationship between signal and transcript concentration were carried out under highly specialized conditions and may not extend to commercially available arrays under routine operating conditions. Additionally, alternative metrics that are not based on the difference in the signal of members of a probe pair may further improve the quantitative utility of the Affymetrix GeneChip array. }
}
@article{Bar11,
abstract = {Given the functional interdependencies between the molecular components in a human cell, a disease is rarely a consequence of an abnormality in a single gene, but reflects the perturbations of the complex intracellular and intercellular network that links tissue and organ systems. The emerging tools of network medicine offer a platform to explore systematically not only the molecular complexity of a particular disease, leading to the identification of disease modules and pathways, but also the molecular relationships among apparently distinct (patho)phenotypes. Advances in this direction are essential for identifying new disease genes, for uncovering the biological significance of disease-associated mutations identified by genome-wide association studies and full-genome sequencing, and for identifying drug targets and biomarkers for complex diseases.},
author = {Barabasi, A.-L. and Gulbahce, N. and Loscalzo, J.},
citeulike-article-id = {8443527},
citeulike-linkout-0 = {http://dx.doi.org/10.1038/nrg2918},
citeulike-linkout-1 = {http://dx.doi.org/10.1038/nrg2918},
citeulike-linkout-2 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3140052/},
citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/21164525},
citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=21164525},
day = {01},
doi = {10.1038/nrg2918},
issn = {1471-0056},
journal = {Nat Rev Genet},
keywords = {human-disease, network-medicine, networks},
month = jan,
number = {1},
pages = {56--68},
pmcid = {PMC3140052},
pmid = {21164525},
posted-at = {2012-02-21 14:06:01},
priority = {5},
publisher = {Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.},
title = {Network medicine: a network-based approach to human disease},
url = {http://dx.doi.org/10.1038/nrg2918},
volume = {12},
year = {2011}
}
@article{Kae05,
abstract = {Genetically identical cells exposed to the same environmental conditions can show significant variation in molecular content and marked differences in phenotypic characteristics. This variability is linked to stochasticity in gene expression, which is generally viewed as having detrimental effects on cellular function with potential implications for disease. However, stochasticity in gene expression can also be advantageous. It can provide the flexibility needed by cells to adapt to fluctuating environments or respond to sudden stresses, and a mechanism by which population heterogeneity can be established during cellular differentiation and development.},
author = {Kaern, M. and Elston, T. C. and Blake, W. J. and Collins, J. J.},
citeulike-article-id = {518658},
journal = {Nat Rev Genet},
keywords = {all, microarrays, motivation},
number = {6},
pages = {451--64},
posted-at = {2006-02-23 18:37:38},
priority = {2},
title = {Stochasticity in gene expression: from theories to phenotypes},
volume = {6},
year = {2005}
}
@misc{Mat05,
title={RNAi-mediated pathways in the nucleus}, url={http://www.nature.com/nrg/journal/v6/n1/full/nrg1500.html}, DOI={10.1038/nrg1500}, number={1}, journal={Nature Reviews Genetics}, author={M.A. Matzke, J.A. Birchler}, year={2005}, pages={24?35}}
@book{Dra03,
author = {Draghici, S.},
citeulike-article-id = {212394},
citeulike-linkout-0 = {http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20\&path=ASIN/1584883154},
citeulike-linkout-1 = {http://www.amazon.de/exec/obidos/redirect?tag=citeulike01-21\&path=ASIN/1584883154},
citeulike-linkout-2 = {http://www.amazon.fr/exec/obidos/redirect?tag=citeulike06-21\&path=ASIN/1584883154},
citeulike-linkout-3 = {http://www.amazon.jp/exec/obidos/ASIN/1584883154},
citeulike-linkout-4 = {http://www.amazon.co.uk/exec/obidos/ASIN/1584883154/citeulike00-21},
citeulike-linkout-5 = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20\&path=ASIN/1584883154},
citeulike-linkout-6 = {http://www.worldcat.org/isbn/1584883154},
citeulike-linkout-7 = {http://books.google.com/books?vid=ISBN1584883154},
citeulike-linkout-8 = {http://www.amazon.com/gp/search?keywords=1584883154\&index=books\&linkCode=qs},
citeulike-linkout-9 = {http://www.librarything.com/isbn/1584883154},
day = {04},
howpublished = {Paperback},
isbn = {1584883154},
keywords = {bioinformatics, book, microarray, statistics},
month = jun,
posted-at = {2009-03-02 07:42:41},
priority = {5},
publisher = {{Chapman \& Hall/CRC}},
title = {Data Analysis Tools for {DNA} Microarrays},
url = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20\&path=ASIN/1584883154},
year = {2003}
}
@article{Vee02,
abstract = {Breast cancer patients with the same stage of disease can have markedly different treatment responses and overall outcome. The strongest predictors for metastases (for example, lymph node status and histological grade) fail to classify accurately breast tumours according to their clinical behaviour1, 2, 3. Chemotherapy or hormonal therapy reduces the risk of distant metastases by approximately one-third; however, 70?80\% of patients receiving this treatment would have survived without it4, 5. None of the signatures of breast cancer gene expression reported to date6, 7, 8, 9, 10, 11, 12 allow for patient-tailored therapy strategies. Here we used {DNA} microarray analysis on primary breast tumours of 117 young patients, and applied supervised classification to identify a gene expression signature strongly predictive of a short interval to distant metastases ('poor prognosis' signature) in patients without tumour cells in local lymph nodes at diagnosis (lymph node negative). In addition, we established a signature that identifies tumours of {BRCA1} carriers. The poor prognosis signature consists of genes regulating cell cycle, invasion, metastasis and angiogenesis. This gene expression profile will outperform all currently used clinical parameters in predicting disease outcome. Our findings provide a strategy to select patients who would benefit from adjuvant therapy.},
address = {Division of Diagnostic Oncology, The Netherlands Cancer Institute, 121 Plesmanlaan, 1066 CX Amsterdam, The Netherlands.},
author = {Van t Veer, L.J. and Dai, H. and Van de Vijver, M.J. and He, Y.D. and Hart, A.A.M. and Mao, M. and Peterse, H.L. and van der Kooy, K. and Marton, M.J. and Witteveen, A.T. and Schreiber, G.J. and Kerkhoven, R.M. and Roberts, C. and Linsley, P.S. and Bernards, R. and Friend, S.H.},
citeulike-article-id = {504894},
citeulike-linkout-0 = {http://dx.doi.org/10.1038/415530a},
citeulike-linkout-1 = {http://dx.doi.org/10.1038/415530a},
citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/11823860},
citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=11823860},
day = {31},
doi = {10.1038/415530a},
issn = {0028-0836},
journal = {Nature},
keywords = {breast, cancer, classification, microarray, survival},
month = jan,
number = {6871},
pages = {530--536},
pmid = {11823860},
posted-at = {2006-05-03 05:39:02},
priority = {0},
publisher = {Nature Publishing Group},
title = {Gene expression profiling predicts clinical outcome of breast cancer},
url = {http://dx.doi.org/10.1038/415530a},
volume = {415},
year = {2002}
}
@book{Mai05,
editor = {O. Maimon and
L. Rokach},
title = {The Data Mining and Knowledge Discovery Handbook},
publisher = {Springer},
year = {2005},
isbn = {0-387-24435-2},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@article{Bra02,
abstract = {An increasingly popular model of regulation is to represent networks of genes as if they directly affect each other. Although such gene networks are phenomenological because they do not explicitly represent the proteins and metabolites that mediate cell interactions, they are a logical way of describing phenomena observed with transcription profiling, such as those that occur with popular microarray technology. The ability to create gene networks from experimental data and use them to reason about their dynamics and design principles will increase our understanding of cellular function. We propose that gene networks are also a good way to describe function unequivocally, and that they could be used for genome functional annotation. Here, we review some of the concepts and methods associated with gene networks, with emphasis on their construction based on experimental data.},
address = {Virginia Bioinformatics Institute, Virginia Polytechnic Institute and State University, Blacksburg, VA 24061, USA.},
author = {Brazhnik, P. and de la Fuente, A. and Mendes, P.},
citeulike-article-id = {2448264},
citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/12413821},
citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=12413821},
issn = {0167-7799},
journal = {Trends in biotechnology},
keywords = {cell\_interactions, cellular\_function, design\_principles, functional\_annotation, gene\_networks, microarray\_technology, phenomena, transcription},
month = nov,
number = {11},
pages = {467--472},
pmid = {12413821},
posted-at = {2010-03-30 18:00:33},
priority = {2},
title = {Gene networks: how to put the function in genomics.},
url = {http://view.ncbi.nlm.nih.gov/pubmed/12413821},
volume = {20},
year = {2002}
}
@article{Bos89,
abstract = {
Mutations in codon 12, 13, or 61 of one of the three ras genes, H-ras, K-ras, and N-ras, convert these genes into active oncogenes. Rapid assays for the detection of these point mutations have been developed recently and used to investigate the role mutated ras genes play in the pathogenesis of human tumors. It appeared that ras gene mutations can be found in a variety of tumor types, although the incidence varies greatly. The highest incidences are found in adenocarcinomas of the pancreas (90\%), the colon (50\%), and the lung (30\%); in thyroid tumors (50\%); and in myeloid leukemia (30\%). For some tumor types a relationship may exist between the presence of a ras mutation and clinical or histopathological features of the tumor. There is some evidence that environmental agents may be involved in the induction of the mutations.
},
author = {Bos, J.L.},
citeulike-article-id = {689123},
citeulike-linkout-0 = {http://cancerres.aacrjournals.org/content/49/17/4682.abstract},
citeulike-linkout-1 = {http://cancerres.aacrjournals.org/content/49/17/4682.full.pdf},
citeulike-linkout-2 = {http://cancerres.aacrjournals.org/cgi/content/abstract/49/17/4682},
citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/2547513},
citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=2547513},
day = {1},
issn = {0008-5472},
journal = {Cancer research},
month = sep,
number = {17},
pages = {4682--4689},
pmid = {2547513},
posted-at = {2013-02-05 00:15:08},
priority = {2},
title = {ras oncogenes in human cancer: a review.},
url = {http://cancerres.aacrjournals.org/content/49/17/4682.abstract},
volume = {49},
year = {1989}
}
@article{CGAN12,
title={Comprehensive molecular characterization of human colon and rectal cancer},
url={http://www.nature.com/nature/journal/v487/n7407/full/nature11252.html}, DOI={10.1038/nature11252}, number={7407}, journal={Nature}, author={The Cancer Genome Atlas Network}, year={2012},
volume = {487},
pages={330?337}}
@book{Ken51,
author = {Kenney, J. F. and Keeping, E. S.},
citeulike-article-id = {10064874},
citeulike-linkout-0 = {http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20\&path=ASIN/B000JCWX9U},
citeulike-linkout-1 = {http://www.amazon.de/exec/obidos/redirect?tag=citeulike01-21\&path=ASIN/B000JCWX9U},
citeulike-linkout-2 = {http://www.amazon.fr/exec/obidos/redirect?tag=citeulike06-21\&path=ASIN/B000JCWX9U},
citeulike-linkout-3 = {http://www.amazon.jp/exec/obidos/ASIN/B000JCWX9U},
citeulike-linkout-4 = {http://www.amazon.co.uk/exec/obidos/ASIN/B000JCWX9U/citeulike00-21},
citeulike-linkout-5 = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20\&path=ASIN/B000JCWX9U},
edition = {2nd},
howpublished = {Hardcover},
keywords = {dinv},
posted-at = {2011-11-24 15:12:38},
priority = {1},
publisher = {D. Van Nostrand Company Inc},
title = {Mathematics of Statistics Part Two},
url = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20\&path=ASIN/B000JCWX9U},
year = {1951}
}
@article{Guy03,
abstract = {Variable and feature selection have become the focus of much research in areas of application for which datasets with tens or hundreds of thousands of variables are available. These areas include text processing of internet documents, gene expression array analysis, and combinatorial chemistry. The objective of variable selection is three-fold: improving the prediction performance of the predictors, providing faster and more cost-effective predictors, and providing a better understanding of the underlying process that generated the data. The contributions of this special issue cover a wide range of aspects of such problems: providing a better definition of the objective function, feature construction, feature ranking, multivariate feature selection, efficient search methods, and feature validity assessment methods.},
address = {Cambridge, MA, USA},
author = {Guyon, I. and Elisseeff, A.},
citeulike-article-id = {167555},
citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=944968},
issn = {1532-4435},
journal = {J. Mach. Learn. Res.},
month = mar,
pages = {1157--1182},
posted-at = {2005-09-30 13:49:05},
priority = {0},
publisher = {JMLR.org},
title = {An introduction to variable and feature selection},
url = {http://portal.acm.org/citation.cfm?id=944968},
volume = {3},
year = {2003}
}
@article{Cer11,
abstract = {Pathway Commons (http://www.pathwaycommons.org) is a collection of publicly available pathway data from multiple organisms. Pathway Commons provides a web-based interface that enables biologists to browse and search a comprehensive collection of pathways from multiple sources represented in a common language, a download site that provides integrated bulk sets of pathway information in standard or convenient formats and a web service that software developers can use to conveniently query and access all data. Database providers can share their pathway data via a common repository. Pathways include biochemical reactions, complex assembly, transport and catalysis events and physical interactions involving proteins, {DNA}, {RNA}, small molecules and complexes. Pathway Commons aims to collect and integrate all public pathway data available in standard formats. Pathway Commons currently contains data from nine databases with over 1400 pathways and 687?000 interactions and will be continually expanded and updated.},
author = {Cerami, E.G. and Gross, B.E. and Demir, E. and Rodchenkov, I. and Babur, \"{O}. and Anwar, N. and Schultz, N. and Bader, G.D. and Sander, C.},
citeulike-article-id = {8244969},
citeulike-linkout-0 = {http://dx.doi.org/10.1093/nar/gkq1039},
citeulike-linkout-1 = {http://nar.oxfordjournals.org/content/early/2010/11/10/nar.gkq1039.abstract},
citeulike-linkout-2 = {http://nar.oxfordjournals.org/content/early/2010/11/10/nar.gkq1039.full.pdf},
citeulike-linkout-3 = {http://nar.oxfordjournals.org/cgi/content/abstract/39/suppl\_1/D685},
citeulike-linkout-4 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3013659/},
citeulike-linkout-5 = {http://view.ncbi.nlm.nih.gov/pubmed/21071392},
citeulike-linkout-6 = {http://www.hubmed.org/display.cgi?uids=21071392},
day = {01},
doi = {10.1093/nar/gkq1039},
issn = {1362-4962},
journal = {Nucleic Acids Research},
keywords = {benjamin-gross, bioinformatics, chris-sander, emek-demir, ethan-cerami, gary-bader, igor-rodchenkov, nadia-anwar, nikolaus-schultz, ozgun-babur},
month = jan,
number = {suppl 1},
pages = {D685--D690},
pmcid = {PMC3013659},
pmid = {21071392},
posted-at = {2010-11-14 18:04:36},
priority = {2},
publisher = {Oxford University Press},
title = {Pathway Commons, a web resource for biological pathway data},
url = {http://dx.doi.org/10.1093/nar/gkq1039},
volume = {39},
year = {2011}
}
@article {Sni12,
title = { "Big Data": Big Gaps of Knowledge in the Field of Internet Science},
journal = {International Journal of Internet Science},
volume = {7},
year = {2012},
pages = {1-5},
abstract = {\ Research on so-called \‘Big Data\’ has received a considerable momentum and is expected to grow in the future. One very interesting stream of research on Big Data analyzes online networks. Many online networks are known to have some typical macro-characteristics, such as \‘small world\’ properties. Much less is known about underlying micro-processes leading to these properties. The models used by Big Data researchers usually are inspired by mathematical ease of exposition. We propose to follow in addition a different strategy that leads to knowledge about micro-processes that match with actual online behavior. This knowledge can then be used for the selection of mathematically-tractable models of online network formation and evolution. Insight from social and behavioral research is needed for pursuing this strategy of knowledge generation about micro-processes. Accordingly, our proposal points to a unique role that social scientists could play in Big Data research
},
issn = {1662-5544},
author = {Snijders,C.C.P. and Matzat,U. and Reips,U.D.}
}
@book{McD09,
address = {Baltimore, Maryland, USA},
author = {McDonald, J.H.},
citeulike-article-id = {7370024},
citeulike-linkout-0 = {http://www.lulu.com/product/5507346},
citeulike-linkout-1 = {http://udel.edu/\~{}mcdonald/statintro.html},
day = {28},
edition = {Second},
keywords = {statistics},
month = sep,
posted-at = {2010-06-30 17:12:24},
priority = {0},
publisher = {Sparky House Publishing},
title = {Handbook of Biological Statistics},
url = {http://www.lulu.com/product/5507346},
year = {2009}
}
@inproceedings{Kon09a,
author = {Kontos, K. and Bontempi, G.},
title = {An improved shrinkage estimator to infer regulatory networks with Gaussian graphical models},
booktitle = {Proceedings of the 2009 ACM symposium on Applied Computing},
series = {SAC '09},
year = {2009},
isbn = {978-1-60558-166-8},
location = {Honolulu, Hawaii},
pages = {793--798},
numpages = {6},
url = {http://doi.acm.org/10.1145/1529282.1529448},
doi = {10.1145/1529282.1529448},
acmid = {1529448},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {Gaussian graphical model, genetic regulatory network, shrinkage},
}
@article{Pel08,
author = {J.-P. Pellet and
A. Elisseeff},
title = {Using Markov Blankets for Causal Structure Learning},
journal = {Journal of Machine Learning Research},
volume = {9},
year = {2008},
pages = {1295-1342},
ee = {http://doi.acm.org/10.1145/1390681.1442776},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@article{Dyk70,
author={R. Dykstra},
title={Establishing the Positive Definiteness of the Sample Covariance Matrix},
year={1970},
journal={The Annals of Mathematical Statistics}
}
@inproceedings{Bou93,
author = {Bouckaert, R.R.},
title = {Probalistic Network Construction Using the Minimum Description Length Principle},
booktitle = {Proceedings of the European Conference on Symbolic and Quantitative Approaches to Reasoning and Uncertainty},
series = {ECSQARU '93},
year = {1993},
isbn = {3-540-57395-X},
pages = {41--48},
numpages = {8},
url = {http://dl.acm.org/citation.cfm?id=646560.695256},
acmid = {695256},
publisher = {Springer-Verlag},
address = {London, UK, UK},
}
@article{Ris86,
added-at = {2008-02-26T11:58:58.000+0100},
author = {Rissanen, J.},
biburl = {http://www.bibsonomy.org/bibtex/2dd8314c2592057009f02d5d57d276196/schaul},
citeulike-article-id = {2381468},
description = {idsia},
interhash = {898efd867e95db57deab54fb111cbae3},
intrahash = {dd8314c2592057009f02d5d57d276196},
journal = {The Annals of Statistics},
keywords = {juergen},
number = 3,
pages = {1080--1100},
priority = {2},
timestamp = {2008-02-26T11:58:58.000+0100},
title = {Stochastic Complexity and Modeling},
volume = 14,
year = 1986
}
@misc{Scu11,
abstract = {The aim of this chapter is twofold. In the first part we will provide a brief
overview of the mathematical and statistical foundations of graphical models,
along with their fundamental properties, estimation and basic inference
procedures. In particular we will develop Markov networks (also known as Markov
random fields) and Bayesian networks, which comprise most past and current
literature on graphical models. In the second part we will review some
applications of graphical models in systems biology.},
archivePrefix = {arXiv},
author = {Scutari, M. and Strimmer, K.},
citeulike-article-id = {7144980},
citeulike-linkout-0 = {http://arxiv.org/abs/1005.1036},
citeulike-linkout-1 = {http://arxiv.org/pdf/1005.1036},
day = {28},
eprint = {1005.1036},
keywords = {graphical\_models, review},
month = jun,
posted-at = {2011-06-29 13:07:39},
priority = {2},
title = {Introduction to Graphical Modelling},
url = {http://arxiv.org/abs/1005.1036},
year = {2011}
}
@inproceedings{Cla12,
added-at = {2012-10-22T00:00:00.000+0200},
author = {Claassen, T. and Heskes, T.},
biburl = {http://www.bibsonomy.org/bibtex/23d879a4e0febabd661d0a8a86a88fea6/dblp},
booktitle = {UAI},
editor = {de~Freitas, N. and Murphy, K.P.},
ee = {http://uai.sis.pitt.edu/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=2283&proceeding_id=28},
interhash = {1769b163aade515fa385959f81573b64},
intrahash = {3d879a4e0febabd661d0a8a86a88fea6},
keywords = {dblp},
pages = {207-216},
publisher = {AUAI Press},
timestamp = {2012-10-22T00:00:00.000+0200},
title = {A Bayesian Approach to Constraint Based Causal Inference.},
url = {http://dblp.uni-trier.de/db/conf/uai/uai2012.html#ClaassenH12},
year = 2012
}
@inproceedings{Bor12,
added-at = {2013-01-25T00:00:00.000+0100},
author = {Borboudakis, G. and Tsamardinos, I.},
biburl = {http://www.bibsonomy.org/bibtex/2d81e08351eb45546277e004f9b0b9713/dblp},
booktitle = {ICML},
ee = {http://icml.cc/discuss/2012/875.html},
interhash = {33e06f0a90109e7d3dea3523a245cdf2},
intrahash = {d81e08351eb45546277e004f9b0b9713},
keywords = {dblp},
publisher = {icml.cc / Omnipress},
timestamp = {2013-01-25T00:00:00.000+0100},
title = {Incorporating Causal Prior Knowledge as Path-Constraints in Bayesian Networks and Maximal Ancestral Graphs.},
url = {http://dblp.uni-trier.de/db/conf/icml/icml2012.html#BorboudakisT12},
year = 2012
}
@book{Her13,
title={Causal Inference},
author={Hernan, M.A. and Robins, J.M.},
isbn={9781420076165},
series={Monographs on Statistics and Applied Probability},
url={http://books.google.be/books?id=\_KnHIAAACAAJ},
year={2013},
publisher={Taylor \& Francis Group}
}
@ARTICLE{Pea03,
title = {Statistics and causal inference: A review},
author = {Pearl, J.},
year = {2003},
journal = {TEST: An Official Journal of the Spanish Society of Statistics and Operations Research},
volume = {12},
number = {2},
pages = {281-345},
keywords = {Structural equation models; confounding; noncompliance; graphical methods; counterfactuals; 68T30},
url = {http://EconPapers.repec.org/RePEc:spr:testjl:v:12:y:2003:i:2:p:281-345}
}
@article{Wan10,
author = {Wang, L. and Li, P. and Brutnell, T.P.},
title = {Exploring plant transcriptomes using ultra high-throughput sequencing},
volume = {9},
number = {2},
pages = {118-128},
year = {2010},
doi = {10.1093/bfgp/elp057},
abstract ={Ultra high-throughput sequencing (UHTS) technologies offer the potential to interrogate transcriptomes in detail that has traditionally been restricted to single gene surveys. For instance, it is now possible to globally define transcription start sites, polyadenylation signals, alternative splice sites and generate quantitative data on gene transcript accumulation in single tissues or cell types. These technologies are thus paving the way for whole genome transcriptomics and will undoubtedly lead to novel insights into plant development and biotic and abiotic stress responses. However, several challenges exist to making this technology broadly accessible to the plant research community. These include the current need for a computationally intensive analysis of data sets, a lack of standardized alignment and formatting procedures and a relatively small number of analytical software packages to interpret UHTS outputs. In this review we summarize recent findings from UHTS and discuss potential opportunities and challenges for broad adoption of these technologies in the plant science community.},
URL = {http://bfg.oxfordjournals.org/content/9/2/118.abstract},
eprint = {http://bfg.oxfordjournals.org/content/9/2/118.full.pdf+html},
journal = {Briefings in Functional Genomics}
}
@article{Mar12,
abstract = {Reconstructing gene regulatory networks from high-throughput data is a long-standing challenge. Through the Dialogue on Reverse Engineering Assessment and Methods (DREAM) project, we performed a comprehensive blind assessment of over 30 network inference methods on Escherichia coli, Staphylococcus aureus, Saccharomyces cerevisiae and in silico microarray data. We characterize the performance, data requirements and inherent biases of different inference approaches, and we provide guidelines for algorithm application and development. We observed that no single inference method performs optimally across all data sets. In contrast, integration of predictions from multiple inference methods shows robust and high performance across diverse data sets. We thereby constructed high-confidence networks for E. coli and S. aureus, each comprising similar to 1,700 transcriptional interactions at a precision of similar to 50\%. We experimentally tested 53 previously unobserved regulatory interactions in E. coli, of which 23 (43\%) were supported. Our results establish community-based methods as a powerful and robust tool for the inference of transcriptional gene regulatory networks.},
author = {Marbach, D. and Costello, J.C. and K\"u ffner, R. and Vega, N.M. and Prill, R.J. and Camacho, D.M. and Allison, K.R. and Kellis, M. and Collins, J.J. and Stolovitzky, G. and DREAM5 Consortium, the and Saeys, Y.},
issn = {1548-7091},
journal = {NATURE METHODS},
keyword = {INTEGRATION,CHALLENGES,MODELS,REGRESSION,RECONSTRUCTION,SELECTION,EXPRESSION DATA,TRANSCRIPTIONAL REGULATORY NETWORK,ESCHERICHIA-COLI,ALGORITHM},
language = {eng},
number = {8},
pages = {796--804},
title = {Wisdom of crowds for robust gene network inference},
url = {http://dx.doi.org/10.1038/NMETH.2016},
volume = {9},
year = {2012},
}
@article{Mar06a,
abstract = {We describe a computational protocol for the {ARACNE} algorithm, an information-theoretic method for identifying transcriptional interactions between gene products using microarray expression profile data. Similar to other algorithms, {ARACNE} predicts potential functional associations among genes, or novel functions for uncharacterized genes, by identifying statistical dependencies between gene products. However, based on biochemical validation, literature searches and {DNA} binding site enrichment analysis, {ARACNE} has also proven effective in identifying bona fide transcriptional targets, even in complex mammalian networks. Thus we envision that predictions made by {ARACNE}, especially when supplemented with prior knowledge or additional data sources, can provide appropriate hypotheses for the further investigation of cellular networks. While the examples in this protocol use only gene expression profile data, the algorithm's theoretical basis readily extends to a variety of other high-throughput measurements, such as pathway-specific or genome-wide proteomics, {microRNA} and metabolomics data. As these data become readily available, we expect that {ARACNE} might prove increasingly useful in elucidating the underlying interaction models. For a microarray data set containing approximately 10,000 probes, reconstructing the network around a single probe completes in several minutes using a desktop computer with a Pentium 4 processor. Reconstructing a genome-wide network generally requires a computational cluster, especially if the recommended bootstrapping procedure is used.},
address = {Department of Biomedical Informatics, Columbia University, New York, New York 10032, USA.},
author = {Margolin, A.A. and Wang, K. and Lim, W.K. and Kustagi, M. and Nemenman, I. and Califano, A.},
citeulike-article-id = {1377984},
citeulike-linkout-0 = {http://dx.doi.org/10.1038/nprot.2006.106},
doi = {10.1038/nprot.2006.106},
journal = {Nat Protoc},
keywords = {animal, bibtex-import, bioinformatics, networks, regulation},
number = {2},
pages = {662--671},
posted-at = {2007-06-11 04:15:43},
priority = {2},
title = {Reverse engineering cellular networks.},
url = {http://dx.doi.org/10.1038/nprot.2006.106},
volume = {1},
year = {2006}
}
@article{DeM12,
author = {de Matos Simoes, , R. AND Emmert-Streib, F.},
journal = {PLoS ONE},
publisher = {Public Library of Science},
title = {Bagging Statistical Network Inference from Large-Scale Gene Expression Data},
year = {2012},
month = {03},
volume = {7},
url = {http://dx.doi.org/10.1371%2Fjournal.pone.0033624},
pages = {e33624},
abstract = {Modern biology and medicine aim at hunting molecular and cellular causes of biological functions and diseases. Gene regulatory networks (GRN) inferred from gene expression data are considered an important aid for this research by providing a map of molecular interactions. Hence, GRNs have the potential enabling and enhancing basic as well as applied research in the life sciences. In this paper, we introduce a new method called BC3NET for inferring causal gene regulatory networks from large-scale gene expression data. BC3NET is an ensemble method that is based on bagging the C3NET algorithm, which means it corresponds to a Bayesian approach with noninformative priors. In this study we demonstrate for a variety of simulated and biological gene expression data from S. cerevisiae that BC3NET is an important enhancement over other inference methods that is capable of capturing biochemical interactions from transcription regulation and protein-protein interaction sensibly. An implementation of BC3NET is freely available as an R package from the CRAN repository.
},
number = {3},
doi = {10.1371/journal.pone.0033624}
}
@article{Ris78,
author = {Rissanen, J.},
citeulike-article-id = {3787343},
journal = {Automatica},
keywords = {compression, description, length, minimum},
pages = {465--471},
posted-at = {2008-12-14 08:20:57},
priority = {0},
title = {Modeling By Shortest Data Description},
volume = {14},
year = {1978}
}
@MISC{Bou94,
author = {R.R. Bouckaert},
title = {Probabilistic Network Construction Using the Minimum Description Length Principle},
year = {1994}
}
@incollection{Ols13d,
author={C. Olsen and B. Haibe-Kains and J. Quackenbush and G. Bontempi},
title={On the Integration of Prior Knowledge in the Inference of Regulatory Networks},
publisher={World Science},
booktitle = {On the Integration of Prior Knowledge in the Inference of Regulatory Networks},
year={2013}
}
@article{Pow11,
author = {D.M.W.~Powers },
title = {EVALUATION: FROM PRECISION, RECALL AND F-MEASURE TO ROC, INFORMEDNESS, MARKEDNESS \& CORRELATION},
journal = {Journal of Machine Learning Technologies},
volume = {2},
number = {1},
year = {2011},
pages = {37--63},
}
@article{Tsu05,
author = {Tsuda, K. and Shin, H. and Sch\"{o}lkopf, B.},
title = {Fast protein classification with multiple networks},
journal = {Bioinformatics},
issue_date = {January 2005},
volume = {21},
number = {2},
month = jan,
year = {2005},
issn = {1367-4803},
pages = {59--65},
numpages = {7},
url = {http://dx.doi.org/10.1093/bioinformatics/bti1110},
doi = {10.1093/bioinformatics/bti1110},
acmid = {1181531},
publisher = {Oxford University Press},
address = {Oxford, UK},
}
@article{Lan04,
abstract = {Kernel methods provide a principled framework in which to represent many types of data, including vectors, strings, trees and graphs. As such, these methods are useful for drawing inferences about biological phenomena. We describe a method for combining multiple kernel representations in an optimal fashion, by formulating the problem as a convex optimization problem that can be solved using semidefinite programming techniques. The method is applied to the problem of predicting yeast protein functional classifications using a support vector machine ({SVM}) trained on five types of data. For this problem, the new method performs better than a previously-described Markov random field method, and better than the {SVM} trained on any single type of data.},
address = {Division of Electrical Engineering, University of California, Berkeley, USA.},
author = {Lanckriet, G.R. and Deng, M. and Cristianini, N. and Jordan, M.I. and Noble, W.S.},
citeulike-article-id = {638220},
citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/14992512},
citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=14992512},
issn = {1793-5091},
journal = {Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing},
keywords = {function\_prediction, kernel},
pages = {300--311},
pmid = {14992512},
posted-at = {2009-03-11 17:31:13},
priority = {2},
title = {Kernel-based data fusion and its application to protein function prediction in yeast.},
url = {http://view.ncbi.nlm.nih.gov/pubmed/14992512},
year = {2004}
}
@article{Lar07,
added-at = {2011-02-04T00:00:00.000+0100},
author = {Larsen, P.E. and Almasri, E. and Chen, G. and Dai, Y.},
biburl = {http://www.bibsonomy.org/bibtex/20d4ed94dd8a920f4e9e44d85be438e52/dblp},
ee = {http://dx.doi.org/10.1186/1471-2105-8-317},
interhash = {248e3886b5bbda47b4d2f6b0c58a0955},
intrahash = {0d4ed94dd8a920f4e9e44d85be438e52},
journal = {BMC Bioinformatics},
keywords = {dblp},
timestamp = {2011-02-04T00:00:00.000+0100},
title = {A statistical method to incorporate biological knowledge for generating testable novel gene regulatory interactions from microarray experiments.},
url = {http://dblp.uni-trier.de/db/journals/bmcbi/bmcbi8.html#LarsenACD07},
volume = 8,
year = 2007
}
@inproceedings{Alm08,
author = {Almasri, E. and Larsen, P. and Chen, G. and Dai, Y.},
title = {Incorporating literature knowledge in Bayesian network for inferring gene networks with gene expression data},
booktitle = {Proceedings of the 4th international conference on Bioinformatics research and applications},
series = {ISBRA'08},
year = {2008},
isbn = {3-540-79449-2, 978-3-540-79449-3},
location = {Atlanta, GA, USA},
pages = {184--195},
numpages = {12},
url = {http://dl.acm.org/citation.cfm?id=1791494.1791512},
acmid = {1791512},
publisher = {Springer-Verlag},
address = {Berlin, Heidelberg},
keywords = {Bayesian network, likelihood score, prior probability},
}
@article{Nar04,
added-at = {2009-06-03T16:52:25.000+0200},
author = {Nariai, N. and Kim, S. and Imoto, S. and Miyano, S.},
biburl = {http://www.bibsonomy.org/bibtex/24f51a82f585bd3dd28f7ba5a64fdd7f6/dalbem},
groups = {public},
interhash = {93d724290ad781ed6cb7367b8d3ff952},
intrahash = {4f51a82f585bd3dd28f7ba5a64fdd7f6},
journal = {Proc. of Symposium on Biocomputation},
keywords = {jabref:noKeywordAssigned},
pages = {336-347},
timestamp = {2009-06-03T16:52:25.000+0200},
title = {``{U}sing protein-protein interactions for refining gene networks estimated from microarray data by {B}ayesian networks''},
username = {dalbem},
volume = 9,
year = 2004
}
@MISC{Tam05,
author = {Y. Tamada and H. Bannai and M. Kanehisa and S. Miyano},
title = {Utilizing evolutionary information and gene expression data for estimating gene networks with Bayesian network models},
year = {2005}
}
@article{Pap13,
author={S. Papillon-Cavanagh and N. De~Jay and N. Hachem and C. Olsen and G. Bontempi and H. Aerts and J. Quackenbush and B. Haibe-Kains},
title={Comparative Study and Validation of Genomic Predictors for Anticancer Drug Sensitivity},
journal={Journal of the American Medical Informatics Association},
year=2013
}
@article{DeJ13a,
author = {De Jay$^*$, N. and Papillon-Cavanagh$^*$, S. and Olsen, C. and El-Hachem, N. and Bontempi, G. and Haibe-Kains, B.},
title = {{mRMRe}: an {R} package for parallelized mRMR ensemble feature selection},
year = {2013},
doi = {10.1093/bioinformatics/btt383},
abstract ={Motivation: Feature selection is one of the main challenges in analyzing high-throughput genomic data. Minimum redundancy maximum relevance (mRMR) is a particularly fast feature selection method for finding a set of both relevant and complementary features. Here we describe the mRMRe R package, in which the mRMR technique is extended by using an ensemble approach in order to better explore the feature space and build more robust predictors. To deal with the computational complexity of the ensemble approach the main functions of the package are implemented and parallelized in C using the openMP API.Results: Our ensemble mRMR implementations outperform the classical mRMR approach in terms of prediction accuracy. They identify genes more relevant to the biological context and may lead to richer biological interpretations. The parallelized functions included in the package show significant gains in terms of run-time speed when compared to previously released packages.Availability: The R package mRMRe is available on CRAN and is provided open source under the Artistic-2.0 License. The code used to generate all the results reported in this application note is available from Supplementary File 1.Contact: bhaibeka@ircm.qc.caSupplementary Information: Supplementary information is available at Bioinformatics online.},
URL = {http://bioinformatics.oxfordjournals.org/content/early/2013/07/03/bioinformatics.btt383.abstract},
eprint = {http://bioinformatics.oxfordjournals.org/content/early/2013/07/03/bioinformatics.btt383.full.pdf+html},
journal = {Bioinformatics}
}
@article{Ols13a,
author={C. Olsen and G. Bontempi and J. Quackenbush and B. Haibe-Kains},
title={predictionet: an R/Bioconductor package for biological network inference integrating prior knowledge},
journal={preprint},
year=2013
}
@Manual{DeJ12a,
title = {mRMRe: R package for parallelized mRMR ensemble feature selection},
author = {N. De~Jay and S. Papillon-Cavanagh and C. Olsen and G. Bontempi and B.Haibe-Kains},
year = {2012},
note = {R package version 1.0.2}
}
@Manual{Hai12a,
title = {predictionet: Inference for predictive networks designed for (but not limited to) genomic data},
author = {B. Haibe-Kains and C. Olsen and G. Bontempi and J. Quackenbush},
year = {2012},
note = {R package version 1.1.5},
url = {http://compbio.dfci.harvard.edu, http://www.ulb.ac.be/di/mlg},
}
@article{Ols13b,
author={C. Olsen and A. Djebbari and K. Fleming and N. Prendergast and R. Rubio and F. Emmert-Streib and G. Bontempi and B. Haibe-Kains and J. Quackenbush},
title={Inference of predictive gene networks from biomedical literature and gene expression data},
journal={Submitted to Genomics},
year=2013
}
@article{Ols13c,
author={C. Olsen and P.E. Meyer and G. Bontempi},
title={A scalable heuristic to orient arcs in undirected networks},
journal={preprint},
year=2013
}
@article{Mir11,
title = "Fourier spectral factor model for prediction of multidimensional signals",
journal = "Signal Processing",
volume = "91",
number = "9",
pages = "2172 - 2177",
year = "2011",
note = "",
issn = "0165-1684",
doi = "10.1016/j.sigpro.2011.03.014",
url = "http://www.sciencedirect.com/science/article/pii/S0165168411000892",
author = "A.A. Miranda and C. Olsen and G. Bontempi",
keywords = "Spectral density function",
keywords = "Eigenvalue decomposition"
}
@incollection{Mey11,
author={P.E. Meyer and C. Olsen and G. Bontempi},
title={Transcriptional Network Inference based on Information Theory},
booktitle={Applied Statistics for Network Biology: Methods in Systems Biology},
publisher={Wiley} ,
year={2011}
}
@book {Gly99,
title = {Computation, Causation, and Discovery},
year = {1999},
publisher = {AAAI Press},
organization = {AAAI Press},
keywords = {FUNDAMENTALS computer science},
editor = {C. Glymour and G.F. Cooper}
}
@InCollection{Hit12,
author = {Hitchcock, C.},
title = {Probabilistic Causation},
booktitle = {The Stanford Encyclopedia of Philosophy},
editor = {Edward N. Zalta},
howpublished = {\url{http://plato.stanford.edu/archives/win2012/entries/causation-probabilistic/}},
year = {2012},
publisher = {None},
edition = {Winter 2012},
}
@book{Whi90,
abstract = {Graphical models--a subset of log-linear models--reveal the interrelationships between multiple variables and features of the underlying conditional independence. Following the theorem-proof-remarks format, this introduction to the use of graphical models in the description and modeling of multivariate systems covers conditional independence, several types of independence graphs, Gaussian models, issues in model selection, regression and decomposition. Many numerical examples and exercises with solutions are included.},
author = {Whittaker, J.},
citeulike-article-id = {487586},
citeulike-linkout-0 = {http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20\&path=ASIN/0471917508},
citeulike-linkout-1 = {http://www.amazon.de/exec/obidos/redirect?tag=citeulike01-21\&path=ASIN/0471917508},
citeulike-linkout-2 = {http://www.amazon.fr/exec/obidos/redirect?tag=citeulike06-21\&path=ASIN/0471917508},
citeulike-linkout-3 = {http://www.amazon.co.uk/exec/obidos/ASIN/0471917508/citeulike00-21},
citeulike-linkout-4 = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20\&path=ASIN/0471917508},
citeulike-linkout-5 = {http://www.worldcat.org/isbn/0471917508},
citeulike-linkout-6 = {http://books.google.com/books?vid=ISBN0471917508},
citeulike-linkout-7 = {http://www.amazon.com/gp/search?keywords=0471917508\&index=books\&linkCode=qs},
citeulike-linkout-8 = {http://www.librarything.com/isbn/0471917508},
day = {28},
howpublished = {Hardcover},
isbn = {0471917508},
keywords = {graphical\_models},
month = mar,
posted-at = {2008-06-03 16:14:07},
priority = {2},
publisher = {John Wiley \& Sons},
title = {Graphical Models in Applied Multivariate Statistics (Wiley Series in Probability \& Statistics)},
url = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20\&path=ASIN/0471917508},
year = {1990}
}
@article{Wer90,
jstor_articletype = {research-article},
title = {On Substantive Research Hypotheses, Conditional Independence Graphs and Graphical Chain Models},
author = {Wermuth, N. and Lauritzen, S.L.},
journal = {Journal of the Royal Statistical Society. Series B (Methodological)},
jstor_issuetitle = {},
volume = {52},
number = {1},
jstor_formatteddate = {1990},
pages = {pp. 21-50},
url = {http://www.jstor.org/stable/2345650},
ISSN = {00359246},
abstract = {Graphs consisting of points, and lines or arrows as connections between selected pairs of points, are used to formulate hypotheses about relations between variables. Points stand for variables, connections represent associations. When a missing connection is interpreted as a conditional independence, the graph characterizes a conditional independence structure as well. Statistical models, called graphical chain models, correspond to special types of graphs which are interpreted in this fashion. Examples are used to illustrate how conditional independences are reflected in summary statistics derived from the models and how the graphs help to identify analogies and equivalences between different models. Graphical chain models are shown to provide a unifying concept for many statistical techniques that in the past have proven to be useful in analyses of data. They also provide tools for new types of analysis.},
language = {English},
year = {1990},
publisher = {Wiley-Blackwell for the Royal Statistical Society},
copyright = {Copyright ? 1990 Royal Statistical Society},
}
@ARTICLE{Pen05,
author = {H. Peng and F. Long and C. Ding},
title = {Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2005},
volume = {27},
pages = {1226--1238}
}
@inproceedings{Bon10,
author = {G. Bontempi and
P.E. Meyer},
title = {Causal filter selection in microarray data},
booktitle = {ICML},
year = {2010},
pages = {95-102},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@ARTICLE{Fle04,
author = {F. Fleuret and I. Guyon},
title = {Fast Binary Feature Selection with Conditional Mutual Information},
journal = {Journal of Machine Learning Research},
year = {2004},
volume = {5},
pages = {1531--1555}
}
@Article{Huy10,
author = "Huynh-Thu, V.A. and Irrthum, A. and Wehenkel, L. and Geurts, P.",
title = "Inferring regulatory networks from expression data using tree-based methods",
journal = "Plos ONE",
number = "9",
volume = "5",
pages = "e12776",
month = "sept",
year = "2010",
keywords = "bioinformatics, machine learning",
url = "http://www.montefiore.ulg.ac.be/services/stochastic/pubs/2010/HIWG10"
}
@article{mod10,
author = {The modENCODE Consortium and Roy, S. and Ernst, J. and Kharchenko, P.V. and Kheradpour, P. and Negre, N. and Eaton, M.L. and Landolin, J.M. and Bristow, C.A. and Ma, L. and Lin, M.F. and Washietl, S. and Arshinoff, B.I. and Ay, F. and Meyer, P.E. and Robine, N. and Washington, N.L. and Di Stefano, L. and Berezikov, E. and Brown, C.D. and Candeias, R. and Carlson, J.W. and Carr, A. and Jungreis, I. and Marbach, D. and Sealfon, R. and Tolstorukov, M.Y. and Will, S. and Alekseyenko, A.A. and Artieri, C. and Booth, B.W. and Brooks, A.N. and Dai, Q. and Davis, C.A. and Duff, M.O. and Feng, X. and Gorchakov, A.A. and Gu, T. and Henikoff, J.G. and Kapranov, P. and Li, R. and MacAlpine, H.K. and Malone, J. and Minoda, A. and Nordman, J. and Okamura, K. and Perry, M. and Powell, S.K. and Riddle, N.C. and Sakai, A. and Samsonova, A. and Sandler, J.E. and Schwartz, Y.B. and Sher, N. and Spokony, R. and Sturgill, D. and van Baren, M. and Wan, K.H. and Yang, L. and Yu, C. and Feingold, E. and Good, P. and Guyer, M. and Lowdon, R. and Ahmad, K. and Andrews, J. and Berger, B. and Brenner, S.E. and Brent, M.R. and Cherbas, L. and Elgin, S.C.R. and Gingeras, T.R. and Grossman, R. and Hoskins, R.A. and Kaufman, T.C. and Kent, W. and Kuroda, M.I. and Orr-Weaver, T. and Perrimon, N. and Pirrotta, V. and Posakony, J.W. and Ren, B. and Russell, S. and Cherbas, P. and Graveley, B.R. and Lewis, S. and Micklem, G. and Oliver, B. and Park, P.J. and Celniker, S.E. and Henikoff, S. and Karpen, G.H. and Lai, E.C. and MacAlpine, D.M. and Stein, L.D. and White, K.P. and Kellis, M.},
title = {Identification of Functional Elements and Regulatory Circuits by Drosophila modENCODE},
volume = {330},
number = {6012},
pages = {1787-1797},
year = {2010},
doi = {10.1126/science.1198374},
abstract ={To gain insight into how genomic information is translated into cellular and developmental programs, the Drosophila model organism Encyclopedia of DNA Elements (modENCODE) project is comprehensively mapping transcripts, histone modifications, chromosomal proteins, transcription factors, replication proteins and intermediates, and nucleosome properties across a developmental time course and in multiple cell lines. We have generated more than 700 data sets and discovered protein-coding, noncoding, RNA regulatory, replication, and chromatin elements, more than tripling the annotated portion of the Drosophila genome. Correlated activity patterns of these elements reveal a functional regulatory network, which predicts putative new functions for genes, reveals stage- and tissue-specific regulators, and enables gene-expression prediction. Our results provide a foundation for directed experimental and computational studies in Drosophila and related species and also a model for systematic data integration toward comprehensive genomic and functional annotation.},
URL = {http://www.sciencemag.org/content/330/6012/1787.abstract},
eprint = {http://www.sciencemag.org/content/330/6012/1787.full.pdf},
journal = {Science}
}
@article{Bac03,
added-at = {2009-03-24T13:33:04.000+0100},
address = {Cambridge, MA, USA},
author = {Bach, F.R. and Jordan, M.I.},
biburl = {http://www.bibsonomy.org/bibtex/2875dda0001e84208aab5d0b501b07726/capacityplanning},
description = {Umeshwar-References},
interhash = {67d4f9c62ed39cdee9193c741597a86a},
intrahash = {875dda0001e84208aab5d0b501b07726},
issn = {1533-7928},
journal = {J. Mach. Learn. Res.},
keywords = {umeshwar},
pages = {1--48},
publisher = {MIT Press},
timestamp = {2009-03-24T13:33:04.000+0100},
title = {Kernel independent component analysis},
volume = 3,
year = 2003
}
@inproceedings{Kon02,
author = {Kondor, R.I. and Lafferty, J.D.},
title = {Diffusion Kernels on Graphs and Other Discrete Input Spaces},
booktitle = {Proceedings of the Nineteenth International Conference on Machine Learning},
series = {ICML '02},
year = {2002},
isbn = {1-55860-873-7},
pages = {315--322},
numpages = {8},
url = {http://dl.acm.org/citation.cfm?id=645531.655996},
acmid = {655996},
publisher = {Morgan Kaufmann Publishers Inc.},
address = {San Francisco, CA, USA},
}
@article{Ram11,
added-at = {2011-03-22T00:00:00.000+0100},
author = {Ram, R. and Chetty, M.},
biburl = {http://www.bibsonomy.org/bibtex/2617d1fe629577df269a1372ce43bce71/dblp},
ee = {http://dx.doi.org/10.1109/TCBB.2009.70},
interhash = {f902af5972188d5e774caa279857d02b},
intrahash = {617d1fe629577df269a1372ce43bce71},
journal = {IEEE/ACM Trans. Comput. Biology Bioinform.},
keywords = {dblp},
number = 2,
pages = {353-367},
timestamp = {2011-03-22T00:00:00.000+0100},
title = {A Markov-Blanket-Based Model for Gene Regulatory Network Inference.},
url = {http://dblp.uni-trier.de/db/journals/tcbb/tcbb8.html#RamC11},
volume = 8,
year = 2011
}
@article{Yam03,
author = {Yamanishi, Y. and Vert, J.-P. and Nakaya, A. and Kanehisa, M.},
title = {Extraction of correlated gene clusters from multiple genomic data by generalized kernel canonical correlation analysis},
volume = {19},
number = {suppl 1},
pages = {i323-i330},
year = {2003},
doi = {10.1093/bioinformatics/btg1045},
abstract ={Motivation: A major issue in computational biology is the reconstruction of
pathways from several genomic datasets, such as expression data,
protein interaction data and phylogenetic profiles. As a first
step toward this goal, it is important to investigate the amount
of correlation which exists between these data.Results: These methods are successfully tested on their ability to
recognize operons in the Escherichia coli genome, from
the comparison of three datasets corresponding to
functional relationships between genes in metabolic pathways,
geometrical relationships along the chromosome, and
co-expression relationships as observed by gene
expression data.Contact: yoshi@kuicr.kyoto-u.ac.jp
},
URL = {http://bioinformatics.oxfordjournals.org/content/19/suppl_1/i323.abstract},
eprint = {http://bioinformatics.oxfordjournals.org/content/19/suppl_1/i323.full.pdf+html},
journal = {Bioinformatics}
}
@INPROCEEDINGS{Aka06,
author = {S. Akaho},
title = {A Kernel Method For Canonical Correlation Analysis},
booktitle = {In Proceedings of the International Meeting of the Psychometric Society (IMPS2001},
year = {2001},
publisher = {Springer-Verlag}
}
@techreport{Mur01,
abstract = {There are essentially two kinds of approaches for learning the structure of Bayesian Networks ({BNs}) from data. The first approach tries to find a graph which satis es all the constraints implied by the empirical conditional independencies measured in the data [{PV91}, {SGS00a}, Shi00]. The second approach searches through the space of models (either {DAGs} or {PDAGs}), and uses some scoring metric (typically Bayesian or some approximation, such as {BIC}/{MDL}) to evaluate the models [{CH92}, Hec95, Hec98,...},
author = {Murphy, K.},
citeulike-article-id = {757899},
citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.29.1655},
institution = {Comp. Sci. Div., UC Berkeley},
keywords = {bayesian, bayesnet, learning, structure},
posted-at = {2006-07-13 18:14:59},
priority = {2},
title = {Learning Bayes net structure from sparse data sets},
url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.29.1655},
year = {2001}
}
@article{KEGG,
abstract = {{KEGG} (Kyoto Encyclopedia of Genes and Genomes) is a knowledge base for systematic analysis of gene functions, linking genomic information with higher order functional information. The genomic information is stored in the {GENES} database, which is a collection of gene catalogs for all the completely sequenced genomes and some partial genomes with up-to-date annotation of gene functions. The higher order functional information is stored in the {PATHWAY} database, which contains graphical representations of cellular processes, such as metabolism, membrane transport, signal transduction and cell cycle. The {PATHWAY} database is supplemented by a set of ortholog group tables for the information about conserved subpathways (pathway motifs), which are often encoded by positionally coupled genes on the chromosome and which are especially useful in predicting gene functions. A third database in {KEGG} is {LIGAND} for the information about chemical compounds, enzyme molecules and enzymatic reactions. {KEGG} provides Java graphics tools for browsing genome maps, comparing two genome maps and manipulating expression maps, as well as computational tools for sequence comparison, graph comparison and path computation. The {KEGG} databases are daily updated and made freely available (http://www.genome.ad.jp/kegg/ ).},
address = {Institute for Chemical Research, Kyoto University, Uji, Kyoto 611-0011, Japan. kanehisa@kuicr.kyoto-u.ac.jp},
author = {Kanehisa, M. and Goto, S.},
citeulike-article-id = {949045},
citeulike-linkout-0 = {http://dx.doi.org/10.1093/nar/28.1.27},
citeulike-linkout-1 = {http://nar.oxfordjournals.org/content/28/1/27.abstract},
citeulike-linkout-2 = {http://nar.oxfordjournals.org/content/28/1/27.full.pdf},
citeulike-linkout-3 = {http://nar.oxfordjournals.org/cgi/content/abstract/28/1/27},
citeulike-linkout-4 = {http://view.ncbi.nlm.nih.gov/pubmed/10592173},
citeulike-linkout-5 = {http://www.hubmed.org/display.cgi?uids=10592173},
day = {01},
doi = {10.1093/nar/28.1.27},
issn = {1362-4962},
journal = {Nucleic Acids Research},
keywords = {kegg, pathway},
month = jan,
number = {1},
pages = {27--30},
pmid = {10592173},
posted-at = {2008-01-11 15:29:26},
priority = {1},
publisher = {Oxford University Press},
title = {{KEGG}: Kyoto Encyclopedia of Genes and Genomes},
url = {http://dx.doi.org/10.1093/nar/28.1.27},
volume = {28},
year = {2000}
}
@article{Tsu03,
author = {Tsuda, K. and Akaho, S. and Asai, K.},
title = {The em algorithm for kernel matrix completion with auxiliary data},
journal = {J. Mach. Learn. Res.},
issue_date = {12/1/2003},
volume = {4},
month = dec,
year = {2003},
issn = {1532-4435},
pages = {67--81},
numpages = {15},
url = {http://dx.doi.org/10.1162/153244304322765649},
doi = {10.1162/153244304322765649},
acmid = {945369},
publisher = {JMLR.org},
}
@ARTICLE{Buh03,
title = {Boosting With the L2 Loss: Regression and Classification},
author = {B\"uhlmann, P. and B., Yu},
year = {2003},
journal = {Journal of the American Statistical Association},
volume = {98},
pages = {324-339},
url = {http://EconPapers.repec.org/RePEc:bes:jnlasa:v:98:y:2003:p:324-339}
}
@article{Sac05,
author = {Sachs, K. and Perez, O. and Pe'er, D. and Lauffenburger, D.A. and Nolan, G.P.},
title = {Causal Protein-Signaling Networks Derived from Multiparameter Single-Cell Data},
volume = {308},
number = {5721},
pages = {523-529},
year = {2005},
doi = {10.1126/science.1105809},
abstract ={Machine learning was applied for the automated derivation of causal influences in cellular signaling networks. This derivation relied on the simultaneous measurement of multiple phosphorylated protein and phospholipid components in thousands of individual primary human immune system cells. Perturbing these cells with molecular interventions drove the ordering of connections between pathway components, wherein Bayesian network computational methods automatically elucidated most of the traditionally reported signaling relationships and predicted novel interpathway network causalities, which we verified experimentally. Reconstruction of network models from physiologically relevant primary single cells might be applied to understanding native-state tissue signaling biology, complex drug actions, and dysfunctional signaling in diseased cells.},
URL = {http://www.sciencemag.org/content/308/5721/523.abstract},
eprint = {http://www.sciencemag.org/content/308/5721/523.full.pdf},
journal = {Science}
}
@article{lee1997survival,
title={Survival analysis in public health research},
author={Lee, Elisa T and Go, Oscar T},
journal={Annual review of public health},
volume={18},
number={1},
pages={105--134},
year={1997},
publisher={Annual Reviews 4139 El Camino Way, PO Box 10139, Palo Alto, CA 94303-0139, USA}
}
@article{Fri00a,
added-at = {2006-02-02T22:05:10.000+0100},
author = {Friedman, J. and Hastie, T. and Tibshirani, R.},
biburl = {http://www.bibsonomy.org/bibtex/2590a45a22e9a772d19a381fd868a7599/sb3000},
interhash = {0770dac98721a5e27c043b984cd5894e},
intrahash = {590a45a22e9a772d19a381fd868a7599},
journal = {The Annals of Statistics},
keywords = {boosting},
number = 2,
timestamp = {2006-02-02T22:05:10.000+0100},
title = {{Additive Logistic Regression: a Statistical View of Boosting}},
volume = 38,
year = 2000
}
@ARTICLE{Efr04,
author = {B. Efron and T. Hastie and I. Johnstone and R. Tibshirani},
title = {Least angle regression},
journal = {Annals of Statistics},
year = {2004},
volume = {32},
pages = {407--499}
}
@article{Zou03,
added-at = {2012-04-11T20:17:05.000+0200},
author = {Zou, H. and Hastie, T.},
biburl = {http://www.bibsonomy.org/bibtex/2a893a057f765cead73b0613125258457/jabreftest},
groups = {public},
interhash = {220dcd59724a3fbc51190c29947b25b1},
intrahash = {a893a057f765cead73b0613125258457},
journal = {Journal of the Royal Statistical Society: Series B (Statistical Methodology)},
keywords = {jabref:noKeywordAssigned},
number = 2,
pages = {301--320},
timestamp = {2012-04-11T20:17:05.000+0200},
title = {Regularization and Variable Selection via the Elastic Net },
username = {jabreftest},
volume = {67 },
year = 2003
}
@article{Hoe70,
added-at = {2009-01-29T03:39:09.000+0100},
author = {Hoerl, A.E. and Kennard, R.W.},
biburl = {http://www.bibsonomy.org/bibtex/2257711fd5e6222fce40b8fbcb66a906a/swpark81},
interhash = {6468748d5b4b1f5d02107b4c131e9ea6},
intrahash = {257711fd5e6222fce40b8fbcb66a906a},
journal = {Technometrics},
keywords = {ridge-regg},
pages = {55--67},
timestamp = {2009-01-29T03:39:09.000+0100},
title = {Ridge Regression: Biased
Estimation for Nonorthogonal Problems},
volume = 12,
year = 1970
}
@article{Cox93,
added-at = {2010-03-25T16:34:29.000+0100},
author = {Cox, D.R. and Wermuth, N.},
biburl = {http://www.bibsonomy.org/bibtex/2ce6c4b40374a994466357b20f88043b8/3mta3},
doi = {10.1214/ss/1177010887},
file = {cox1993.pdf:Papers/cox1993.pdf:PDF},
fjournal = {Statistical Science. A Review Journal of the Institute of Mathematical Statistics},
interhash = {b8b34eb8258ad480c8f1039f073428a7},
intrahash = {ce6c4b40374a994466357b20f88043b8},
issn = {0883-4237},
journal = {Statistical Science},
keywords = {jabref:noKeywordAssigned},
mrclass = {62H99},
mrnumber = {MR1243593 (94e:62063)},
note = {With comments and a rejoinder by the authors},
number = 3,
pages = {204--218},
timestamp = {2010-03-25T16:34:29.000+0100},
title = {Linear dependencies represented by chain graphs},
volume = 8,
year = 1993
}
@book{Has03,
author = {Hastie, T. and Tibshirani, R. and Friedman, J.H.},
citeulike-article-id = {161814},
citeulike-linkout-0 = {http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20\&path=ASIN/0387952845},
citeulike-linkout-1 = {http://www.amazon.de/exec/obidos/redirect?tag=citeulike01-21\&path=ASIN/0387952845},
citeulike-linkout-2 = {http://www.amazon.fr/exec/obidos/redirect?tag=citeulike06-21\&path=ASIN/0387952845},
citeulike-linkout-3 = {http://www.amazon.jp/exec/obidos/ASIN/0387952845},
citeulike-linkout-4 = {http://www.amazon.co.uk/exec/obidos/ASIN/0387952845/citeulike00-21},
citeulike-linkout-5 = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20\&path=ASIN/0387952845},
citeulike-linkout-6 = {http://www.worldcat.org/isbn/0387952845},
citeulike-linkout-7 = {http://books.google.com/books?vid=ISBN0387952845},
citeulike-linkout-8 = {http://www.amazon.com/gp/search?keywords=0387952845\&index=books\&linkCode=qs},
citeulike-linkout-9 = {http://www.librarything.com/isbn/0387952845},
day = {30},
edition = {Corrected},
howpublished = {Hardcover},
isbn = {0387952845},
keywords = {machine-learning, statistic},
month = jul,
posted-at = {2007-02-13 15:09:19},
priority = {2},
publisher = {Springer},
title = {The Elements of Statistical Learning},
url = {http://www.worldcat.org/isbn/0387952845},
year = {2003}
}
@article{Bre00,
author = {Brenner, N. and Strong, S.P. and Koberle, R.P. and Bialek, W.P. and De~Ruyter~Van~Steveninck, R.R. },
title = {Synergy in a Neural Code},
journal = {Neural Comput.},
issue_date = {July 2000},
volume = {12},
number = {7},
month = jul,
year = {2000},
issn = {0899-7667},
pages = {1531--1552},
numpages = {22},
url = {http://dx.doi.org/10.1162/089976600300015259},
doi = {10.1162/089976600300015259},
acmid = {1121322},
publisher = {MIT Press},
address = {Cambridge, MA, USA},
}
@Article{Alt11,
title = {Structural Influence of gene networks on their inference: Analysis of C3NET},
author = {G. Altay and F. Emmert-Streib},
journal = {Submitted},
year = {2011},
volume={},
url = {http://cran.r-project.org/web/packages/c3net/index.html},
}
@Manual{minet,
title = {minet: Mutual Information Network Inference},
author = {P.E. Meyer and F. Lafitte and G. Bontempi},
year = {2007},
note = {R package version 1.8.0},
url = {http://www.ulb.ac.be/di/mlg},
}
@Article{Alt10,
AUTHOR = {Altay, G. and Emmert-Streib, F.},
TITLE = {Inferring the conservative causal core of gene regulatory networks},
JOURNAL = {BMC Systems Biology},
VOLUME = {4},
YEAR = {2010},
NUMBER = {1},
PAGES = {132},
URL = {http://www.biomedcentral.com/1752-0509/4/132},
DOI = {10.1186/1752-0509-4-132},
PubMedID = {20920161},
ISSN = {1752-0509},
ABSTRACT = {BACKGROUND:Inferring gene regulatory networks from large-scale expression data is an important problem that received much attention in recent years. These networks have the potential to gain insights into causal molecular interactions of biological processes. Hence, from a methodological point of view, reliable estimation methods based on observational data are needed to approach this problem practically.RESULTS:In this paper, we introduce a novel gene regulatory network inference (GRNI) algorithm, called C3NET. We compare C3NET with four well known methods, ARACNE, CLR, MRNET and RN, conducting in-depth numerical ensemble simulations and demonstrate also for biological expression data from E. coli that C3NET performs consistently better than the best known GRNI methods in the literature. In addition, it has also a low computational complexity. Since C3NET is based on estimates of mutual information values in conjunction with a maximization step, our numerical investigations demonstrate that our inference algorithm exploits causal structural information in the data efficiently.CONCLUSIONS:For systems biology to succeed in the long run, it is of crucial importance to establish methods that extract large-scale gene networks from high-throughput data that reflect the underlying causal interactions among genes or gene products. Our method can contribute to this endeavor by demonstrating that an inference algorithm with a neat design permits not only a more intuitive and possibly biological interpretation of its working mechanism but can also result in superior results.},
}
@article{Sim11,
abstract = {The inference of gene regulatory networks from gene expression data is a difficult problem because the performance of the inference algorithms depends on a multitude of different factors. In this paper we study two of these. First, we investigate the influence of discrete mutual information ({MI}) estimators on the global and local network inference performance of the {C3NET} algorithm. More precisely, we study different {MI} estimators (Empirical, {Miller-Madow}, Shrink and {Sch\"{u}rmann-Grassberger}) in combination with discretization methods (equal frequency, equal width and global equal width discretization). We observe the best global and local inference performance of {C3NET} for the {Miller-Madow} estimator with an equal width discretization. Second, our numerical analysis can be considered as a systems approach because we simulate gene expression data from an underlying gene regulatory network, instead of making a distributional assumption to sample thereof. We demonstrate that despite the popularity of the latter approach, which is the traditional way of studying {MI} estimators, this is in fact not supported by simulated and biological expression data because of their heterogeneity. Hence, our study provides guidance for an efficient design of a simulation study in the context of network inference, supporting a systems approach.},
author = {de Matos Simoes, R. and Emmert-Streib, F.},
citeulike-article-id = {10178928},
citeulike-linkout-0 = {http://dx.doi.org/10.1371/journal.pone.0029279},
day = {29},
doi = {10.1371/journal.pone.0029279},
journal = {PLoS ONE},
keywords = {networkinference},
month = dec,
number = {12},
pages = {e29279+},
posted-at = {2011-12-29 22:41:51},
priority = {2},
publisher = {Public Library of Science},
title = {Influence of Statistical Estimators of Mutual Information and Data Heterogeneity on the Inference of Gene Regulatory Networks},
url = {http://dx.doi.org/10.1371/journal.pone.0029279},
volume = {6},
year = {2011}
}
@article{Luo08,
abstract = {Overall, our work demonstrates that {MI3} outperforms the frequently used control methods, and provides a powerful method for inferring mechanistic relationships underlying biological and other complex systems. The {MI3} method is implemented in R in the "mi3" package, available under the {GNU} {GPL} from http://sysbio.engin.umich.edu/\~{}luow/downloads.php and from the R package archive {CRAN}.},
author = {Luo, W. and Hankenson, K.D. and Woolf, P.J.},
citeulike-article-id = {3477138},
citeulike-linkout-0 = {http://dx.doi.org/10.1186/1471-2105-9-467},
citeulike-linkout-1 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2613931/},
citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/18980677},
citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=18980677},
day = {03},
doi = {10.1186/1471-2105-9-467},
issn = {1471-2105},
journal = {BMC bioinformatics},
keywords = {information, mi3, mutual},
month = nov,
number = {1},
pages = {467+},
pmcid = {PMC2613931},
pmid = {18980677},
posted-at = {2009-05-02 18:27:36},
priority = {0},
title = {Learning transcriptional regulatory networks from high throughput gene expression data using continuous three-way mutual information.},
url = {http://dx.doi.org/10.1186/1471-2105-9-467},
volume = {9},
year = {2008}
}
@article{Wat09,
abstract = {This paper describes the technique designated best performer in the 2nd conference on Dialogue for Reverse Engineering Assessments and Methods ({DREAM2}) Challenge 5 (unsigned genome-scale network prediction from blinded microarray data). Existing algorithms use the pairwise correlations of the expression levels of genes, which provide valuable but insufficient information for the inference of regulatory interactions. Here we present a computational approach based on the recently developed context likelihood of related ({CLR}) algorithm, extracting additional complementary information using the information theoretic measure of synergy and assigning a score to each ordered pair of genes measuring the degree of confidence that the first gene regulates the second. When tested on a set of publicly available Escherichia coli gene-expression data with known assumed ground truth, the synergy augmented {CLR} ({SA}-{CLR}) algorithm had significantly improved prediction performance when compared to {CLR}. There is also enhanced potential for biological discovery as a result of the identification of the most likely synergistic partner genes involved in the interactions.},
author = {Watkinson, J. and Liang, K. and Wang, X. and Zheng, T. and Anastassiou, D.},
citeulike-article-id = {4266759},
citeulike-linkout-0 = {http://dx.doi.org/10.1111/j.1749-6632.2008.03757.x},
citeulike-linkout-1 = {http://www.ingentaconnect.com/content/bsc/nyas/2009/00001158/00000001/art00026},
citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/19348651},
citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=19348651},
doi = {10.1111/j.1749-6632.2008.03757.x},
issn = {1749-6632},
journal = {Annals of the New York Academy of Sciences},
keywords = {leggere},
month = mar,
number = {1},
pages = {302--313},
pmid = {19348651},
posted-at = {2011-04-05 13:51:38},
priority = {3},
publisher = {Blackwell Publishing Inc},
title = {Inference of Regulatory Gene Interactions from Expression Data Using {Three-Way} Mutual Information},
url = {http://dx.doi.org/10.1111/j.1749-6632.2008.03757.x},
volume = {1158},
year = {2009}
}
@article{Sch03a,
abstract = {Entropy and information provide natural measures of correlation among elements in a network. We construct here the information theoretic analog of connected correlation functions: irreducible N-point correlation is measured by a decrease in entropy for the joint distribution of N variables relative to the maximum entropy allowed by all the observed N-1 variable distributions. We calculate the ? connected information? terms for several examples and show that it also enables the decomposition of the information that is carried by a population of elements about an outside source.},
author = {Schneidman, E. and Still, S. and Berry, M.J. and Bialek, W.},
citeulike-article-id = {2689935},
citeulike-linkout-0 = {http://dx.doi.org/10.1103/PhysRevLett.91.238701},
citeulike-linkout-1 = {http://link.aps.org/abstract/PRL/v91/i23/e238701},
citeulike-linkout-2 = {http://link.aps.org/pdf/PRL/v91/i23/e238701},
day = {2},
doi = {10.1103/PhysRevLett.91.238701},
journal = {Physical Review Letters},
keywords = {correlation, entropy, statistics},
month = dec,
number = {23},
pages = {238701+},
posted-at = {2012-03-21 14:03:19},
priority = {2},
publisher = {American Physical Society},
title = {Network Information and Connected Correlations},
url = {http://dx.doi.org/10.1103/PhysRevLett.91.238701},
volume = {91},
year = {2003}
}
@ARTICLE{Sch03,
author = {E. Schneidman and W. Bialek and M.J. Berry~II},
title = {Synergy, Redundancy, and Independence in Population Codes},
journal = {The Journal of Neuroscience},
year = {2003},
volume = {23},
number = {37},
pages = {11539--11553}
}
@article{Var06,
author = {Varadan, V. and Miller, D.M. and Anastassiou, D.},
title = {Computational inference of the molecular logic for synaptic connectivity in C. elegans},
journal = {Bioinformatics},
issue_date = {July 2006},
volume = {22},
number = {14},
month = jul,
year = {2006},
issn = {1367-4803},
pages = {e497--e506},
url = {http://dx.doi.org/10.1093/bioinformatics/btl224},
doi = {10.1093/bioinformatics/btl224},
acmid = {1181986},
publisher = {Oxford University Press},
address = {Oxford, UK},
}
@article{Ana07,
abstract = {Diseases such as cancer are often related to collaborative effects involving interactions of multiple genes within complex pathways, or to combinations of multiple {SNPs}. To understand the structure of such mechanisms, it is helpful to analyze genes in terms of the purely cooperative, as opposed to independent, nature of their contributions towards a phenotype. Here, we present an information-theoretic analysis that provides a quantitative measure of the multivariate synergy and decomposes sets of genes into submodules each of which contains synergistically interacting genes. When the resulting computational tools are used for the analysis of gene expression or {SNP} data, this systems-based methodology provides insight into the biological mechanisms responsible for disease.},
author = {Anastassiou, D.},
citeulike-article-id = {1128558},
citeulike-linkout-0 = {http://dx.doi.org/10.1038/msb4100124},
citeulike-linkout-1 = {http://dx.doi.org/10.1038/msb4100124},
citeulike-linkout-2 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1828751/},
citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/17299419},
citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=17299419},
day = {13},
doi = {10.1038/msb4100124},
issn = {1744-4292},
journal = {Molecular systems biology},
keywords = {disease, synergy},
month = feb,
pmcid = {PMC1828751},
pmid = {17299419},
posted-at = {2010-08-22 17:54:09},
priority = {2},
publisher = {Nature Publishing Group},
title = {Computational analysis of the synergy among multiple interacting genes.},
url = {http://dx.doi.org/10.1038/msb4100124},
volume = {3},
year = {2007}
}
@article{Bro04,
abstract = {Bayesian Networks ({BN}) is a knowledge representation formalism that has been proven to be valuable in biomedicine for constructing decision support systems and for generating causal hypotheses from data. Given the emergence of datasets in medicine and biology with thousands of variables and that current algorithms do not scale more than a few hundred variables in practical domains, new efficient and accurate algorithms are needed to learn high quality {BNs} from data. We present a new algorithm called {Max-Min} {Hill-Climbing} ({MMHC}) that builds upon and improves the Sparse Candidate ({SC}) algorithm; a state-of-the-art algorithm that scales up to datasets involving hundreds of variables provided the generating networks are sparse. Compared to the {SC}, on a number of datasets from medicine and biology, (a) {MMHC} discovers {BNs} that are structurally closer to the data-generating {BN}, (b) the discovered networks are more probable given the data, (c) {MMHC} is computationally more efficient and scalable than {SC}, and (d) the generating networks are not required to be uniformly sparse nor is the user of {MMHC} required to guess correctly the network connectivity},
address = {Discoivery Systems Laboratory, Department of Biomedical Informatics, Vanderbilt University, 2209 Garland Avenue, Nashville, TN 37232, USA. laura.e.brown@vanderbilt.edu},
author = {Brown, L.E. and Tsamardinos, I. and Aliferis, C.F.},
citeulike-article-id = {1325512},
citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/15360905},
citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=15360905},
journal = {Medinfo},
keywords = {graphicalmodel},
number = {Pt 1},
pages = {711--715},
pmid = {15360905},
posted-at = {2007-08-02 13:06:19},
priority = {4},
title = {A novel algorithm for scalable and accurate Bayesian network learning.},
url = {http://view.ncbi.nlm.nih.gov/pubmed/15360905},
volume = {11},
year = {2004}
}
@Manual{GeneNet,
title = {GeneNet: Modeling and Inferring Gene Networks},
author = {J. Sch\"afer and R. Opgen-Rhein and K. Strimmer.},
year = {2009},
note = {R package version 1.2.4},
url = {http://CRAN.R-project.org/package=GeneNet},
}
@article{Mei06,
author = {Meinshausen, Nicolai and B\"{u}hlmann, Peter},
citeulike-article-id = {2823189},
citeulike-linkout-0 = {http://dx.doi.org/10.1214/009053606000000281},
citeulike-linkout-1 = {http://www.ams.org/mathscinet-getitem?mr=2278363},
comment = {Zero entries in the inverse covariance matrix of a multivariate normal distribution correspond to conditional independence restrictions between variables. So people can use covariance matrix with multivariate normal distribution assumption to find independencies. In this paper, it showed another neighborhood selection scheme for sparse high-dimensional graphs with the Lasso.
Neighborhood selection ? cast to Standard regression problem ? solved by Lasso
, lasso: when p is 1, ridge: when p is 2.
It is well known that the estimates have a parsimonious property for p <=1 only, while the optimization problem is only convex for p >=1. Larger lambda tends to shrink the size of the estimated set. Lasso coefficient estimation is not necessarily unique, but if uniqueness fails, the set of solutions is still convex and all our results about neighborhoods hold for any solution.
The probability of falsely including nodes into the neighborhood estimate for node a is vanishing exponentially fast. ? The probability of including all neighboring variables into the estimate converges to 1. Consistent neighborhood estimation with the Lasso is possible but asymptotic considerations give little advice on how to choose the penalty parameter.
Covariance Selection. We can estimate neighborhood of each node consistently
Apply neighborhood selection to each node in the graph and estimate of the edge set E of graph G is then given by},
doi = {10.1214/009053606000000281},
issn = {0090-5364},
journal = {The Annals of Statistics},
keywords = {l1, lasso, learning, neighborhood, norm, selection, structure},
month = jun,
mrnumber = {MR2278363},
number = {3},
pages = {1436--1462},
posted-at = {2010-09-26 19:05:54},
priority = {0},
title = {{High-dimensional graphs and variable selection with the Lasso}},
url = {http://dx.doi.org/10.1214/009053606000000281},
volume = {34},
year = {2006}
}
@article{Tib96,
added-at = {2009-04-04T18:01:35.000+0200},
author = {Tibshirani, R.},
biburl = {http://www.bibsonomy.org/bibtex/290e648276aa6cd3c601e7c0a54366233/dieudonnew},
interhash = {334927808d42a9a6bf8eae717fed41b3},
intrahash = {90e648276aa6cd3c601e7c0a54366233},
journal = {Journal of the Royal Statistical Society (Series B)},
keywords = {imported},
pages = {267-288},
timestamp = {2009-04-04T18:01:35.000+0200},
title = {Regression Shrinkage and Selection via the Lasso},
volume = 58,
year = 1996
}
@Article{Led03,
author={Ledoit, O. and Wolf, M.},
title={Improved estimation of the covariance matrix of stock returns with an application to portfolio selection},
journal={Journal of Empirical Finance},
year=2003,
volume={10},
number={5},
pages={603-621},
month={December},
keywords={},
abstract={No abstract is available for this item.},
url={http://ideas.repec.org/a/eee/empfin/v10y2003i5p603-621.html}
}
@inproceedings{Kon08,
title = {Nested q-Partial Graphs for Genetic Network Inference from Small n, Large p Microarray Data},
author = {K. Kontos and G. Bontempi},
year = {2008},
doi = {http://dx.doi.org/10.1007/978-3-540-70600-7_21},
researchr = {http://researchr.org/publication/KontosB08},
cites = {0},
citedby = {0},
pages = {273-287},
booktitle = {Bioinformatics Research and Development, Second International Conference, BIRD 2008, Vienna, Austria, July 7-9, 2008, Proceedings},
volume = {13},
series = {Communications in Computer and Information Science},
publisher = {Springer},
isbn = {978-3-540-70598-7},
}
@article{Won03,
added-at = {2010-03-25T16:35:41.000+0100},
author = {Wong, Frederick and Carter, Christopher K. and Kohn, Robert},
biburl = {http://www.bibsonomy.org/bibtex/2f133e8fa1e05cfffd102e7617314f0b9/3mta3},
coden = {BIOKAX},
doi = {10.1093/biomet/90.4.809},
file = {wong2003.pdf:Papers/wong2003.pdf:PDF},
fjournal = {Biometrika},
interhash = {ce11b215c7a29e11e529a354464ac629},
intrahash = {f133e8fa1e05cfffd102e7617314f0b9},
issn = {0006-3444},
journal = {Biometrika},
keywords = {Structural},
mrclass = {62J10 (62F10)},
mrnumber = {MR2024759 (2004i:62132)},
number = 4,
pages = {809--830},
timestamp = {2010-03-25T16:35:41.000+0100},
title = {Efficient estimation of covariance selection models},
volume = 90,
year = 2003
}
@article{Bos08,
author = {Boscolo, Riccardo and Liao, James C. and Roychowdhury, Vwani P.},
title = {An Information Theoretic Exploratory Method for Learning Patterns of Conditional Gene Coexpression from Microarray Data},
journal = {IEEE/ACM Trans. Comput. Biol. Bioinformatics},
issue_date = {January 2008},
volume = {5},
number = {1},
month = jan,
year = {2008},
issn = {1545-5963},
pages = {15--24},
numpages = {10},
url = {http://dx.doi.org/10.1109/TCBB.2007.1056},
doi = {10.1109/TCBB.2007.1056},
acmid = {1343573},
publisher = {IEEE Computer Society Press},
address = {Los Alamitos, CA, USA},
keywords = {Gene expression data, Statistical analysis, Information theory, Co-information, Entropy},
}
@inproceedings{Fri99,
author = {N. Friedman and
I. Nachman and
D. Pe'er},
title = {Learning Bayesian Network Structure from Massive Datasets:
The "Sparse Candidate" Algorithm},
booktitle = {UAI},
year = {1999},
pages = {206-215},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@INPROCEEDINGS{Coo99,
AUTHOR = "G. Cooper and C. Yoo",
TITLE = "Causal Discovery from a Mixture of Experimental and Observational Data",
BOOKTITLE = "Proceedings of the Fifteenth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-99)",
PUBLISHER = "Morgan Kaufmann",
ADDRESS = "San Francisco, CA",
YEAR = "1999",
PAGES = "116--125"
}
@article{Imo06,
title = "Error tolerant model for incorporating biological knowledge with expression data in estimating gene†networks",
journal = "Statistical Methodology",
volume = "3",
number = "1",
pages = "1 - 16",
year = "2006",
note = "Bioinformatics",
issn = "1572-3127",
doi = "10.1016/j.stamet.2005.09.013",
url = "http://www.sciencedirect.com/science/article/pii/S1572312705000675",
author = "S. Imoto and T. Higuchi and T. Goto and S. Miyano",
keywords = "Microarray data",
keywords = "Biological knowledge",
keywords = "Error tolerant model",
keywords = "Gene network",
keywords = "Bayesian network"
}
@ARTICLE{Imo02,
author = {S. Imoto and K. Sunyong and T. Goto and S. Aburatani and K. Tashiro and S. Kuhara and S. Miyano},
title = {Bayesian network and nonparametric heteroscedastic regression for nonlinear modeling of genetic network},
journal = {Proc. 1st IEEE Computer Society Bioinformatics Conference},
year = {2002},
volume = {1},
pages = {219--227}
}
@Manual{Gel12,
title = {arm: Data Analysis Using Regression and Multilevel/Hierarchical
Models},
author = {A. Gelman and Y.-S. Su and M. Yajima and J. Hill and M.G. Pittau and J. Kerman and T. Zheng},
year = {2012},
note = {R package version 1.5-04},
url = {http://CRAN.R-project.org/package=arm},
}
@article{Muk08,
author = {Mukherjee, Sach and Speed, Terence P.},
title = {Network inference using informative priors},
volume = {105},
number = {38},
pages = {14313-14318},
year = {2008},
doi = {10.1073/pnas.0802272105},
abstract ={Recent years have seen much interest in the study of systems characterized by multiple interacting components. A class of statistical models called graphical models, in which graphs are used to represent probabilistic relationships between variables, provides a framework for formal inference regarding such systems. In many settings, the object of inference is the network structure itself. This problem of ?network inference? is well known to be a challenging one. However, in scientific settings there is very often existing information regarding network connectivity. A natural idea then is to take account of such information during inference. This article addresses the question of incorporating prior information into network inference. We focus on directed models called Bayesian networks, and use Markov chain Monte Carlo to draw samples from posterior distributions over network structures. We introduce prior distributions on graphs capable of capturing information regarding network features including edges, classes of edges, degree distributions, and sparsity. We illustrate our approach in the context of systems biology, applying our methods to network inference in cancer signaling.},
URL = {http://www.pnas.org/content/105/38/14313.abstract},
eprint = {http://www.pnas.org/content/105/38/14313.full.pdf+html},
journal = {Proceedings of the National Academy of Sciences}
}
@Article{Dje08,
AUTHOR = {Djebbari, A. and Quackenbush, J.},
TITLE = {Seeded Bayesian Networks: Constructing genetic networks from microarray data},
JOURNAL = {BMC Systems Biology},
VOLUME = {2},
YEAR = {2008},
NUMBER = {1},
PAGES = {57},
URL = {http://www.biomedcentral.com/1752-0509/2/57},
DOI = {10.1186/1752-0509-2-57},
PubMedID = {18601736},
ISSN = {1752-0509},
ABSTRACT = {BACKGROUND:DNA microarrays and other genomics-inspired technologies provide large datasets that often include hidden patterns of correlation between genes reflecting the complex processes that underlie cellular metabolism and physiology. The challenge in analyzing large-scale expression data has been to extract biologically meaningful inferences regarding these processes - often represented as networks - in an environment where the datasets are often imperfect and biological noise can obscure the actual signal. Although many techniques have been developed in an attempt to address these issues, to date their ability to extract meaningful and predictive network relationships has been limited. Here we describe a method that draws on prior information about gene-gene interactions to infer biologically relevant pathways from microarray data. Our approach consists of using preliminary networks derived from the literature and/or protein-protein interaction data as seeds for a Bayesian network analysis of microarray results.RESULTS:Through a bootstrap analysis of gene expression data derived from a number of leukemia studies, we demonstrate that seeded Bayesian Networks have the ability to identify high-confidence gene-gene interactions which can then be validated by comparison to other sources of pathway data.CONCLUSION:The use of network seeds greatly improves the ability of Bayesian Network analysis to learn gene interaction networks from gene expression data. We demonstrate that the use of seeds derived from the biomedical literature or high-throughput protein-protein interaction data, or the combination, provides improvement over a standard Bayesian Network analysis, allowing networks involving dynamic processes to be deduced from the static snapshots of biological systems that represent the most common source of microarray data. Software implementing these methods has been included in the widely used TM4 microarray analysis package.},
}
@inproceedings{Bun91,
author = {Buntine, Wray},
title = {Theory refinement on Bayesian networks},
booktitle = {Proceedings of the seventh conference (1991) on Uncertainty in artificial intelligence},
year = {1991},
isbn = {1-55860-203-8},
location = {Los Angeles, California, United States},
pages = {52--60},
numpages = {9},
url = {http://dl.acm.org/citation.cfm?id=114098.114105},
acmid = {114105},
publisher = {Morgan Kaufmann Publishers Inc.},
address = {San Francisco, CA, USA},
}
@book{Gel03,
abstract = {{Incorporating new and updated information, this second edition of THE bestselling text in Bayesian data analysis continues to emphasize practice over theory, describing how to conceptualize, perform, and critique statistical analyses from a Bayesian perspective. Its world-class authors provide guidance on all aspects of Bayesian data analysis and include examples of real statistical analyses, based on their own research, that demonstrate how to solve complicated problems. Changes in the new edition include: \&\#183;Stronger focus on MCMC\&\#183;Revision of the computational advice in Part III\&\#183;New chapters on nonlinear models and decision analysis\&\#183;Several additional applied examples from the authors' recent research\&\#183;Additional chapters on current models for Bayesian data analysis such as nonlinear models, generalized linear mixed models, and more\&\#183;Reorganization of chapters 6 and 7 on model checking and data collectionBayesian computation is currently at a stage where there are many reasonable ways to compute any given posterior distribution. However, the best approach is not always clear ahead of time. Reflecting this, the new edition offers a more pluralistic presentation, giving advice on performing computations from many perspectives while making clear the importance of being aware that there are different ways to implement any given iterative simulation computation. The new approach, additional examples, and updated information make Bayesian Data Analysis an excellent introductory text and a reference that working scientists will use throughout their professional life.}},
author = {Gelman, A. and Carlin, J.B. and Stern, H.S. and Rubin, D.B.},
citeulike-article-id = {105949},
citeulike-linkout-0 = {http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20\&path=ASIN/158488388X},
citeulike-linkout-1 = {http://www.amazon.de/exec/obidos/redirect?tag=citeulike01-21\&path=ASIN/158488388X},
citeulike-linkout-2 = {http://www.amazon.fr/exec/obidos/redirect?tag=citeulike06-21\&path=ASIN/158488388X},
citeulike-linkout-3 = {http://www.amazon.jp/exec/obidos/ASIN/158488388X},
citeulike-linkout-4 = {http://www.amazon.co.uk/exec/obidos/ASIN/158488388X/citeulike00-21},
citeulike-linkout-5 = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20\&path=ASIN/158488388X},
citeulike-linkout-6 = {http://www.worldcat.org/isbn/158488388X},
citeulike-linkout-7 = {http://books.google.com/books?vid=ISBN158488388X},
citeulike-linkout-8 = {http://www.amazon.com/gp/search?keywords=158488388X\&index=books\&linkCode=qs},
citeulike-linkout-9 = {http://www.librarything.com/isbn/158488388X},
day = {29},
edition = {2},
howpublished = {Hardcover},
isbn = {158488388X},
keywords = {bayesian, book, chr, loan, probabilisticmodeling},
month = jul,
posted-at = {2006-01-20 20:01:54},
priority = {3},
publisher = {Chapman and Hall/CRC},
title = {Bayesian Data Analysis, Second Edition (Chapman \& {Hall/CRC} Texts in Statistical Science)},
url = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20\&path=ASIN/158488388X},
year = {2003}
}
@article{Sch98,
author = {Sch\"{o}lkopf, B. and Smola, A. and M\"{u}ller, K.-R.},
title = {Nonlinear component analysis as a kernel eigenvalue problem},
journal = {Neural Comput.},
issue_date = {July 1, 1998},
volume = {10},
number = {5},
month = jul,
year = {1998},
issn = {0899-7667},
pages = {1299--1319},
numpages = {21},
url = {http://dx.doi.org/10.1162/089976698300017467},
doi = {10.1162/089976698300017467},
acmid = {295960},
publisher = {MIT Press},
address = {Cambridge, MA, USA},
}
@inproceedings{Ver04,
author = {J.-P. Vert and
Y. Yamanishi},
title = {Supervised Graph Inference},
booktitle = {NIPS},
year = {2004},
ee = {http://books.nips.cc/papers/files/nips17/NIPS2004_0471.pdf},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@article{Ble07,
abstract = {Inference and reconstruction of biological networks from heterogeneous data is currently an active research subject with several important applications in systems biology. The problem has been attacked from many different points of view with varying degrees of success. In particular, predicting new edges with a reasonable false discovery rate is highly demanded for practical applications, but remains extremely challenging due to the sparsity of the networks of interest.},
address = {Institut de Math\'{e}matiques et de Mod\'{e}lisation de Montpellier, UMR CNRS 5149, Equipe de Probabilit\'{e}s et Statistique, Universit\'{e} Montpellier II, CC 051, Place Eug\`{e}ne Bataillon, 34095 Montpellier Cedex 5, France.},
author = {Bleakley, K. and Biau, G. and Vert, J.-P.},
citeulike-article-id = {10951784},
citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btm204},
comment = {10.1093/bioinformatics/btm204},
doi = {10.1093/bioinformatics/btm204},
issn = {1367-4803},
journal = {Bioinformatics (Oxford, England)},
keywords = {computing, modelling, networks, systems-biology},
number = {13},
pages = {65},
pdf = {\\mvmsan.mvm.ed.ac.uk\smcmhome\amacleod\papers\byDATE\2007\0707\bleakley\_bioinformatics\_2007.pdf},
posted-at = {2012-07-27 15:43:06},
priority = {2},
title = {Supervised reconstruction of biological networks with local models.},
url = {http://dx.doi.org/10.1093/bioinformatics/btm204},
volume = {23},
year = {2007}
}
@ARTICLE{Wil06,
title = {Low-Order Conditional Independence Graphs for Inferring Genetic Networks},
author = {Wille, A. and B\"uhlmann, P.},
year = {2006},
journal = {Statistical Applications in Genetics and Molecular Biology},
volume = {5},
number = {1},
pages = {1},
abstract = {As a powerful tool for analyzing full conditional (in-)dependencies between random variables, graphical models have become increasingly popular to infer genetic networks based on gene expression data. However, full (unconstrained) conditional relationships between random variables can be only estimated accurately if the number of observations is relatively large in comparison to the number of variables, which is usually not fulfilled for high-throughput genomic data. Recently, simplified graphical modeling approaches have been proposed to determine dependencies between gene expression profiles. For sparse graphical models such as genetic networks, it is assumed that the zero- and first-order conditional independencies still reflect reasonably well the full conditional independence structure between variables. Moreover, low-order conditional independencies have the advantage that they can be accurately estimated even when having only a small number of observations. Therefore, using only zero- and first-order conditional dependencies to infer the complete graphical model can be very useful. Here, we analyze the statistical and probabilistic properties of these low-order conditional independence graphs (called 0-1 graphs). We find that for faithful graphical models, the 0-1 graph contains at least all edges of the full conditional independence graph (concentration graph). For simple structures such as Markov trees, the 0-1 graph even coincides with the concentration graph. Furthermore, we present some asymptotic results and we demonstrate in a simulation study that despite their simplicity, 0-1 graphs are generally good estimators of sparse graphical models. Finally, the biological relevance of some applications is summarized.},
keywords = {Computational Biology/Bioinformatics; Graphical modeling; Gene expression},
url = {http://EconPapers.repec.org/RePEc:bpj:sagmbi:v:5:y:2006:i:1:n:1}
}
@Article{Wil04,
AUTHOR = {Wille, A. and Zimmermann, P. and Vranova, E. and Furholz, A. and Laule, O. and Bleuler, S. and Hennig, L. and Prelic, A. and von~Rohr, P. and Thiele, L. and Zitzler, E. and Gruissem, W. and B\"uhlmann, P.},
TITLE = {Sparse graphical Gaussian modeling of the isoprenoid gene network in Arabidopsis thaliana},
JOURNAL = {Genome Biology},
VOLUME = {5},
YEAR = {2004},
NUMBER = {11},
PAGES = {R92},
URL = {http://genomebiology.com/2004/5/11/R92},
DOI = {10.1186/gb-2004-5-11-r92},
PubMedID = {15535868},
ISSN = {1465-6906},
ABSTRACT = {We present a novel graphical Gaussian modeling approach for reverse engineering of genetic regulatory networks with many genes and few observations. When applying our approach to infer a gene network for isoprenoid biosynthesis in Arabidopsis thaliana, we detect modules of closely connected genes and candidate genes for possible cross-talk between the isoprenoid pathways. Genes of downstream pathways also fit well into the network. We evaluate our approach in a simulation study and using the yeast galactose network.},
}
@Article{Mag04,
AUTHOR = {Magwene, Paul and Kim, Junhyong},
TITLE = {Estimating genomic coexpression networks using first-order conditional independence},
JOURNAL = {Genome Biology},
VOLUME = {5},
YEAR = {2004},
NUMBER = {12},
PAGES = {R100},
URL = {http://genomebiology.com/2004/5/12/R100},
DOI = {10.1186/gb-2004-5-12-r100},
PubMedID = {15575966},
ISSN = {1465-6906},
ABSTRACT = {We describe a computationally efficient statistical framework for estimating networks of coexpressed genes. This framework exploits first-order conditional independence relationships among gene-expression measurements to estimate patterns of association. We use this approach to estimate a coexpression network from microarray gene-expression measurements from Saccharomyces cerevisiae. We demonstrate the biological utility of this approach by showing that a large number of metabolic pathways are coherently represented in the estimated network. We describe a complementary unsupervised graph search algorithm for discovering locally distinct subgraphs of a large weighted graph. We apply this algorithm to our coexpression network model and show that subgraphs found using this approach correspond to particular biological processes or contain representatives of distinct gene families.},
}
@article{Fue04,
abstract = {{MOTIVATION}: A major challenge of systems biology is to infer biochemical interactions from large-scale observations, such as transcriptomics, proteomics and metabolomics. We propose to use a partial correlation analysis to construct approximate Undirected Dependency Graphs from such large-scale biochemical data. This approach enables a distinction between direct and indirect interactions of biochemical compounds, thereby inferring the underlying network topology. {RESULTS}: The method is first thoroughly evaluated with a large set of simulated data. Results indicate that the approach has good statistical power and a low False Discovery Rate even in the presence of noise in the data. We then applied the method to an existing data set of yeast gene expression. Several small gene networks were inferred and found to contain genes known to be collectively involved in particular biochemical processes. In some of these networks there are also uncharacterized {ORFs} present, which lead to hypotheses about their functions. {AVAILABILITY}: Programs running in {MS}-Windows and Linux for applying zeroth, first, second and third order partial correlation analysis can be downloaded at: {http://mendes.vbi.vt.edu/tiki-index.php?page=Software}. {SUPPLEMENTARY} {INFORMATION}: Supplementary information can be found at: {URL} to be decided.},
address = {Virginia Polytechnic Institute and State University, Virginia Bioinformatics Institute, 1880 Pratt Drive, Blacksburg 24061, USA. alf@vbi.vt.edu },
author = {Fuente, A. and Bing, N. and Hoeschele, I. and Mendes, P.},
citeulike-article-id = {1366617},
citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/15284096},
citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=15284096},
day = {12},
issn = {1367-4803},
journal = {Bioinformatics},
keywords = {partial\_correlation, reverse\_engineering},
month = dec,
number = {18},
pages = {3565--3574},
pmid = {15284096},
posted-at = {2007-06-06 00:11:55},
priority = {2},
title = {Discovery of meaningful associations in genomic data using partial correlation coefficients.},
url = {http://view.ncbi.nlm.nih.gov/pubmed/15284096},
volume = {20},
year = {2004}
}
@article{Ver03a,
abstract = {Motivation: A promising way to make sense out of gene expression profiles is to relate them to the activity of metabolic and signalling pathways. Each pathway usually involves many genes, such as enzymes, which can themselves participate in many pathways. The set of all known pathways can therefore be represented by a complex network of genes. Searching for regularities in the set of gene expression profiles with respect to the topology of this gene network is a way to automatically extract active pathways and their associated patterns of activity.},
address = {Centre de G\'{e}ostatistique, Ecole des Mines de Paris, 35 rue Saint-Honor\'{e}, 77305 Fontainebleau cedex, France Bioinformatics center, Institute for Chemical Research, Kyoto University, Gokasho, Uji, Kyoto 611-0011, Japan.},
author = {Vert, J.-P. and Kanehisa, Minoru},
citeulike-article-id = {363628},
citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btg1084},
citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/content/19/suppl\_2/ii238.abstract},
citeulike-linkout-2 = {http://bioinformatics.oxfordjournals.org/content/19/suppl\_2/ii238.full.pdf},
citeulike-linkout-3 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/19/suppl\_2/ii238},
citeulike-linkout-4 = {http://view.ncbi.nlm.nih.gov/pubmed/14534196},
citeulike-linkout-5 = {http://www.hubmed.org/display.cgi?uids=14534196},
day = {27},
doi = {10.1093/bioinformatics/btg1084},
issn = {1460-2059},
journal = {Bioinformatics},
keywords = {interaction},
month = sep,
number = {suppl 2},
pages = {ii238--ii244},
pmid = {14534196},
posted-at = {2008-09-14 03:39:48},
priority = {2},
publisher = {Oxford University Press},
title = {Extracting active pathways from gene expression data},
url = {http://dx.doi.org/10.1093/bioinformatics/btg1084},
volume = {19},
year = {2003}
}
@article{Ver03,
author="Vert, J.-P.",
title="Graph-driven features extraction from microarray data using diffusion kernels and kernel cca",
journal="Advances in Neural Information Processing Systems",
ISSN="",
publisher="",
year="2003",
volume="",
number="",
pages="",
URL="http://ci.nii.ac.jp/naid/10021201067/en/",
DOI="",
}
@INPROCEEDINGS{Ng01,
author = {A.Y. Ng and M.I. Jordan and Y. Weiss},
title = {On Spectral Clustering: Analysis and an algorithm},
booktitle = {Advances in Neural Information Processing Systems },
year = {2001},
pages = {849--856},
publisher = {MIT Press}
}
@inproceedings{Pav01,
author = {Pavlidis, P. and Weston, J. and Cai, J. and Grundy, W.N.},
title = {Gene functional classification from heterogeneous data},
booktitle = {Proceedings of the fifth annual international conference on Computational biology},
series = {RECOMB '01},
year = {2001},
isbn = {1-58113-353-7},
location = {Montreal, Quebec, Canada},
pages = {249--255},
numpages = {7},
url = {http://doi.acm.org/10.1145/369133.369228},
doi = {10.1145/369133.369228},
acmid = {369228},
publisher = {ACM},
address = {New York, NY, USA},
}
@article{Tra08,
author = {Tranchevent, L.-C. and Barriot, R. and Yu, S. and Van~Vooren, S. and Van~Loo, P. and Coessens, B. and De~Moor, B. and Aerts, S. and Moreau, Y.},
title = {Endeavour update: a web resource for gene prioritization in multiple species},
volume = {36},
number = {suppl 2},
pages = {W377-W384},
year = {2008},
doi = {10.1093/nar/gkn325},
abstract ={Endeavour (http://www.esat.kuleuven.be/endeavourweb; this web site is free and open to all users and there is no login requirement) is a web resource for the prioritization of candidate genes. Using a training set of genes known to be involved in a biological process of interest, our approach consists of (i) inferring several models (based on various genomic data sources), (ii) applying each model to the candidate genes to rank those candidates against the profile of the known genes and (iii) merging the several rankings into a global ranking of the candidate genes. In the present article, we describe the latest developments of Endeavour. First, we provide a web-based user interface, besides our Java client, to make Endeavour more universally accessible. Second, we support multiple species: in addition to Homo sapiens, we now provide gene prioritization for three major model organisms: Mus musculus, Rattus norvegicus and Caenorhabditis elegans. Third, Endeavour makes use of additional data sources and is now including numerous databases: ontologies and annotations, protein?protein interactions, cis-regulatory information, gene expression data sets, sequence information and text-mining data. We tested the novel version of Endeavour on 32 recent disease gene associations from the literature. Additionally, we describe a number of recent independent studies that made use of Endeavour to prioritize candidate genes for obesity and Type II diabetes, cleft lip and cleft palate, and pulmonary fibrosis.},
URL = {http://nar.oxfordjournals.org/content/36/suppl_2/W377.abstract},
eprint = {http://nar.oxfordjournals.org/content/36/suppl_2/W377.full.pdf+html},
journal = {Nucleic Acids Research}
}
@article{Yam04,
author = {Yamanishi, Y. and Vert, J.-P. and Kanehisa, M.},
title = {Protein network inference from multiple genomic data: a supervised approach},
journal = {Bioinformatics},
issue_date = {January 2004},
volume = {20},
number = {1},
month = jan,
year = {2004},
issn = {1367-4803},
pages = {363--370},
numpages = {8},
url = {http://dx.doi.org/10.1093/bioinformatics/bth910},
doi = {10.1093/bioinformatics/bth910},
acmid = {1093264},
publisher = {Oxford University Press},
address = {Oxford, UK},
}
@article{Tra10,
author = "Tranchevent, L{\'e}on-Charles and Capdevila, F.B. and Nitsch, N. and De Moor, Bart and De Causmaecker, Patrick and Moreau, Yves",
title = "A guide to web tools to prioritize candidate genes",
journal = "Briefings in Bioinformatics",
volume = "12",
number = "1",
pages = "22--32",
month = Jan,
year = "2010",
url = "https://lirias.kuleuven.be/handle/123456789/260982",
}
@ARTICLE{Jak04,
author = {Aleks Jakulin and Ivan Bratko},
title = {Quantifying and visualizing attribute interactions: An approach based on entropy},
journal = {http://arxiv.org/abs/cs.AI/0308002 v3},
year = {2004},
volume = {308002},
pages = {3}
}
@article{Dou11,
abstract = {
Gene regulatory network models are a major area of study in systems and computational biology and the construction of network models is among the most important problems in these disciplines. The critical epistemological issue concerns validation. Validity can be approached from two different perspectives (i) given a hypothesized network model, its scientific validity relates to the ability to make predictions from the model that can be checked against experimental observations; and (ii) the validity of a network inference procedure must be evaluated relative to its ability to infer a network from sample points generated by the network. This article examines both perspectives in the framework of a distance function between two networks. It considers some of the obstacles to validation and provides examples of both validation paradigms.
},
author = {Dougherty, Edward R.},
citeulike-article-id = {8487763},
citeulike-linkout-0 = {http://dx.doi.org/10.1093/bib/bbq078},
citeulike-linkout-1 = {http://bib.oxfordjournals.org/content/12/3/245.abstract},
citeulike-linkout-2 = {http://bib.oxfordjournals.org/content/12/3/245.full.pdf},
citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/21183477},
citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=21183477},
day = {1},
doi = {10.1093/bib/bbq078},
issn = {1477-4054},
journal = {Briefings in bioinformatics},
keywords = {networks},
month = may,
number = {3},
pages = {245--252},
pmid = {21183477},
posted-at = {2011-05-06 16:54:01},
priority = {2},
title = {Validation of gene regulatory networks: scientific and inferential.},
url = {http://dx.doi.org/10.1093/bib/bbq078},
volume = {12},
year = {2011}
}
@article{Pee11,
abstract = {
The flood of genome-wide data generated by high-throughput technologies currently provides biologists with an unprecedented opportunity: to manipulate, query, and reconstruct functional molecular networks of cells. Here, we outline three underlying principles and six strategies to infer network models from genomic data. Then, using cancer as an example, we describe experimental and computational approaches to infer "differential" networks that can identify genes and processes driving disease phenotypes. In conclusion, we discuss how a network-level understanding of cancer can be used to predict drug response and guide therapeutics.
Copyright {\copyright} 2011 Elsevier Inc. All rights reserved.
},
author = {Pe'er, D. and Hacohen, N.},
citeulike-article-id = {9038742},
citeulike-linkout-0 = {http://www.cell.com//abstract/S0092-8674(11)00237-6},
citeulike-linkout-1 = {http://dx.doi.org/10.1016/j.cell.2011.03.001},
citeulike-linkout-2 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3082135/},
citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/21414479},
citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=21414479},
day = {18},
doi = {10.1016/j.cell.2011.03.001},
issn = {1097-4172},
journal = {Cell},
keywords = {biological\_networks, gene\_networks},
month = mar,
number = {6},
pages = {864--873},
pmcid = {PMC3082135},
pmid = {21414479},
posted-at = {2011-05-11 10:55:24},
priority = {2},
publisher = {Cell Press},
title = {Principles and strategies for developing network models in cancer.},
url = {http://dx.doi.org/10.1016/j.cell.2011.03.001},
volume = {144},
year = {2011}
}
@article{Iki10,
abstract = {The dataset used in this work and a running version of the software tool is available for download from the web site {http://www.cs.newcastle.edu.au/\~{}mendes/softwareGIM}.html.},
author = {Ikin, A. and Riveros, C. and Moscato, P. and Mendes, A.},
booktitle = {Bioinformatics},
citeulike-article-id = {6343355},
citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btp652},
citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/26/2/283},
citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/19965878},
citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=19965878},
day = {15},
doi = {10.1093/bioinformatics/btp652},
issn = {1367-4811},
journal = {Bioinformatics (Oxford, England)},
keywords = {mining, network, silico, systems},
month = jan,
number = {2},
pages = {283--284},
pmid = {19965878},
posted-at = {2010-01-20 22:13:55},
priority = {2},
title = {The Gene Interaction Miner: a new tool for data mining contextual information for protein-protein interaction analysis.},
url = {http://dx.doi.org/10.1093/bioinformatics/btp652},
volume = {26},
year = {2010}
}
@article{Hof05,
abstract = {{iHOP} is freely accessible at {http://www.pdg.cnb.uam.es/UniPub}/{iHOP}/},
address = {National Center of Biotechnology, CNB-CSIC Campus de la UAM. Madrid E-28049, Spain.},
author = {Hoffmann, R. and Valencia, A.},
citeulike-article-id = {361474},
citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/bti1142},
citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/21/suppl\_2/ii252},
citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/16204114},
citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=16204114},
day = {1},
doi = {10.1093/bioinformatics/bti1142},
issn = {1367-4811},
journal = {Bioinformatics (Oxford, England)},
keywords = {text-mining},
month = sep,
pmid = {16204114},
posted-at = {2005-11-28 06:25:19},
priority = {2},
title = {Implementing the {iHOP} concept for navigation of biomedical literature.},
url = {http://dx.doi.org/10.1093/bioinformatics/bti1142},
volume = {21 Suppl 2},
year = {2005}
}
@article{Mos08,
abstract = {{BACKGROUND}::Most successful computational approaches for protein function prediction integrate multiple genomics and proteomics data sources to make inferences about the function of unknown proteins. The most accurate of these algorithms have long running times, making them unsuitable for real-time protein function prediction in large genomes. As a result, the predictions of these algorithms are stored in static databases that can easily become outdated. We propose a new algorithm, {GeneMANIA}, that is as accurate as the leading methods, while capable of predicting protein function in {real-time.RESULTS}::We use a fast heuristic algorithm, derived from ridge regression, to integrate multiple functional association networks and predict gene function from a single process-specific network using label propagation. Our algorithm is efficient enough to be deployed on a modern webserver and is as accurate as, or more so than, the leading methods on the {MouseFunc} I benchmark and a new yeast function prediction benchmark; it is robust to redundant and irrelevant data and requires, on average, less than ten seconds of computation time on tasks from these {benchmarks.CONCLUSION}::{GeneMANIA} is fast enough to predict gene function on-the-fly while achieving state-of-the-art accuracy. A prototype version of a {GeneMANIA}-based webserver is available at http://morrislab.med.utoronto.ca/prototype webcite.},
address = {Department of Computer Science, University of Toronto, King's College Road, Toronto, ON, M5S 3G4, Canada.},
author = {Mostafavi, S. and Ray, D. and Farley, D.W. and Grouios, C. and Morris, Q.},
citeulike-article-id = {3279454},
citeulike-linkout-0 = {http://dx.doi.org/10.1186/gb-2008-9-s1-s4},
citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/18613948},
citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=18613948},
doi = {10.1186/gb-2008-9-s1-s4},
issn = {1465-6906},
journal = {Genome Biology},
keywords = {function\_prediction, gene\_function},
number = {Suppl 1},
pages = {S4+},
pmid = {18613948},
posted-at = {2011-08-11 15:25:42},
priority = {2},
title = {{GeneMANIA}: a real-time multiple association network integration algorithm for predicting gene function},
url = {http://dx.doi.org/10.1186/gb-2008-9-s1-s4},
volume = {9},
year = {2008}
}
@article{Fer11,
abstract = {Motivation: Widespread availability of low-cost, full genome sequencing will introduce new challenges for bioinformatics.},
author = {Fernald, Guy H. and Capriotti, Emidio and Daneshjou, Roxana and Karczewski, Konrad J. and Altman, Russ B.},
citeulike-article-id = {9318168},
citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btr295},
citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/content/early/2011/05/19/bioinformatics.btr295.abstract},
citeulike-linkout-2 = {http://bioinformatics.oxfordjournals.org/content/early/2011/05/19/bioinformatics.btr295.full.pdf},
citeulike-linkout-3 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/27/13/1741},
citeulike-linkout-4 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3117361/},
citeulike-linkout-5 = {http://view.ncbi.nlm.nih.gov/pubmed/21596790},
citeulike-linkout-6 = {http://www.hubmed.org/display.cgi?uids=21596790},
day = {01},
doi = {10.1093/bioinformatics/btr295},
issn = {1460-2059},
journal = {Bioinformatics},
month = jul,
number = {13},
pages = {1741--1748},
pmcid = {PMC3117361},
pmid = {21596790},
posted-at = {2011-06-20 19:48:54},
priority = {2},
publisher = {Oxford University Press},
title = {Bioinformatics challenges for personalized medicine},
url = {http://dx.doi.org/10.1093/bioinformatics/btr295},
volume = {27},
year = {2011}
}
@Article{Yng09,
AUTHOR = {Yngvadottir, Bryndis and MacArthur, Daniel and Jin, Hanjun and Tyler-Smith, Chris},
TITLE = {The promise and reality of personal genomics},
JOURNAL = {Genome Biology},
VOLUME = {10},
YEAR = {2009},
NUMBER = {9},
PAGES = {237},
URL = {http://genomebiology.com/2009/10/9/237},
DOI = {10.1186/gb-2009-10-9-237},
PubMedID = {19723346},
ISSN = {1465-6906},
ABSTRACT = {The publication of the highest-quality and best-annotated personal genome yet tells us much about sequencing technology, something about genetic ancestry, but still little of medical relevance.},
}
@article{Mar07,
added-at = {2009-04-03T22:34:55.000+0200},
author = {Markowetz, Florian and Spang, Rainer},
biburl = {http://www.bibsonomy.org/bibtex/22338808cf68761ec3e7ca0f954d25310/tmcphillips},
interhash = {7a31ba18b23fdaecee35aa719ca0d4ba},
intrahash = {2338808cf68761ec3e7ca0f954d25310},
journal = {BMC Bioinformatics},
keywords = {NetworkInference},
pages = {S5},
timestamp = {2009-04-03T22:34:55.000+0200},
title = {Inferring cellular networks -- a review},
url = {http://www.biomedcentral.com/1471-2105/8/S6/S5},
volume = 8,
year = 2007
}
@article{Fri04,
abstract = {High-throughput genome-wide molecular assays, which probe cellular networks from different perspectives, have become central to molecular biology. Probabilistic graphical models are useful for extracting meaningful biological insights from the resulting data sets. These models provide a concise representation of complex cellular networks by composing simpler submodels. Procedures based on well-understood principles for inferring such models from data facilitate a model-based methodology for analysis and discovery. This methodology and its capabilities are illustrated by several recent applications to gene expression data.},
address = {School of Computer Science and Engineering, Hebrew University, 91904 Jerusalem, Israel. nir@cs.huji.ac.il},
author = {Friedman, N.},
citeulike-article-id = {100166},
citeulike-linkout-0 = {http://dx.doi.org/10.1126/science.1094068},
citeulike-linkout-1 = {http://www.sciencemag.org/content/sci;303/5659/799.abstract},
citeulike-linkout-2 = {http://www.sciencemag.org/content/sci;303/5659/799.full.pdf},
citeulike-linkout-3 = {http://www.sciencemag.org/cgi/content/abstract/303/5659/799},
citeulike-linkout-4 = {http://view.ncbi.nlm.nih.gov/pubmed/14764868},
citeulike-linkout-5 = {http://www.hubmed.org/display.cgi?uids=14764868},
day = {06},
doi = {10.1126/science.1094068},
issn = {1095-9203},
journal = {Science},
keywords = {grn, grn\_inference, review},
month = feb,
number = {5659},
pages = {799--805},
pmid = {14764868},
posted-at = {2009-10-05 15:21:52},
priority = {2},
publisher = {American Association for the Advancement of Science},
title = {Inferring Cellular Networks Using Probabilistic Graphical Models},
url = {http://dx.doi.org/10.1126/science.1094068},
volume = {303},
year = {2004}
}
@book{Sha04,
author = {J. Shawe-Taylor and Nello Christianini},
publisher = {Cambridge University Press},
title = {Kernel Methods for Pattern Analysis},
year = {2004}
}
@article{Hai12,
author = {Haibe-Kains, B. and Olsen, C. and Djebbari, A. and Bontempi, G. and Correll, M. and Bouton, C. and Quackenbush, J.},
title = {{Predictive networks: a flexible, open source, web application for integration and analysis of human gene networks.}},
journal = {Nucleic acids research},
year = {2012},
volume = {40},
number = {D1},
pages = {D866--D875},
month = jan,
annote = {http://sourceforge.net/projects/predictivenets/text}
}
@article{Lag07,
author = {Kasper Lage and E Olof Karlberg and, Zenia M Storling and Pall Olason and Anders G Pedersen and Olga Rigina and Anders M Hinsby and Zeynep T\"umer and Flemming Pociot and Niels Tommerup and Yves Moreau and S?ren Brunak},
title = {A human phenome-interactome network of protein complexes implicated in genetic disorders},
journal = {Nature Biotechnology},
volume={25},
year = {2007},
}
@article{Aer09,
author = {S. Aerts and S. Vilain and S. Hu and L.-C. Tranchevent and R. Barriot and J.
Yan and Y. Moreau and B.A. Hassan and X.-J. Quan},
title = {Integrating Computational Biology and Forward Genetics in Drosophila},
journal = {PLoS Genetics},
volume={5},
year = {2009},
}
@article{Yip08,
abstract = {
{MOTIVATION}: An important problem in systems biology is reconstructing complete networks of interactions between biological objects by extrapolating from a few known interactions as examples. While there are many computational techniques proposed for this network reconstruction task, their accuracy is consistently limited by the small number of high-confidence examples, and the uneven distribution of these examples across the potential interaction space, with some objects having many known interactions and others few. {RESULTS}: To address this issue, we propose two computational methods based on the concept of training set expansion. They work particularly effectively in conjunction with kernel approaches, which are a popular class of approaches for fusing together many disparate types of features. Both our methods are based on semi-supervised learning and involve augmenting the limited number of gold-standard training instances with carefully chosen and highly confident auxiliary examples. The first method, prediction propagation, propagates highly confident predictions of one local model to another as the auxiliary examples, thus learning from information-rich regions of the training network to help predict the information-poor regions. The second method, kernel initialization, takes the most similar and most dissimilar objects of each object in a global kernel as the auxiliary examples. Using several sets of experimentally verified protein-protein interactions from yeast, we show that training set expansion gives a measurable performance gain over a number of representative, state-of-the-art network reconstruction methods, and it can correctly identify some interactions that are ranked low by other methods due to the lack of training examples of the involved proteins.
},
author = {Yip, K.Y. and Gerstein, M.},
citeulike-article-id = {3579614},
citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btn602},
citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/25/2/243?etoc},
citeulike-linkout-2 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2639005/},
citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/19015141},
citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=19015141},
day = {15},
doi = {10.1093/bioinformatics/btn602},
issn = {1367-4811},
journal = {Bioinformatics (Oxford, England)},
keywords = {biological, interactions, network},
month = jan,
number = {2},
pages = {243--250},
pmcid = {PMC2639005},
pmid = {19015141},
posted-at = {2009-01-30 16:33:36},
priority = {2},
title = {Training set expansion: an approach to improving the reconstruction of biological networks from limited and uneven reliable interactions.},
url = {http://dx.doi.org/10.1093/bioinformatics/btn602},
volume = {25},
year = {2008}
}
@article{Nit10,
abstract = {{BACKGROUND}:Discovering novel disease genes is still challenging for diseases for which no prior knowledge - such as known disease genes or disease-related pathways - is available. Performing genetic studies frequently results in large lists of candidate genes of which only few can be followed up for further investigation. We have recently developed a computational method for constitutional genetic disorders that identifies the most promising candidate genes by replacing prior knowledge by experimental data of differential gene expression between affected and healthy {individuals.To} improve the performance of our prioritization strategy, we have extended our previous work by applying different machine learning approaches that identify promising candidate genes by determining whether a gene is surrounded by highly differentially expressed genes in a functional association or protein-protein interaction {network.RESULTS}:We have proposed three strategies scoring disease candidate genes relying on network-based machine learning approaches, such as kernel ridge regression, heat kernel, and Arnoldi kernel approximation. For comparison purposes, a local measure based on the expression of the direct neighbors is also computed. We have benchmarked these strategies on 40 publicly available knockout experiments in mice, and performance was assessed against results obtained using a standard procedure in genetics that ranks candidate genes based solely on their differential expression levels (Simple Expression Ranking). Our results showed that our four strategies could outperform this standard procedure and that the best results were obtained using the Heat Kernel Diffusion Ranking leading to an average ranking position of 8 out of 100 genes, an {AUC} value of 92.3\% and an error reduction of 52.8\% relative to the standard procedure approach which ranked the knockout gene on average at position 17 with an {AUC} value of {83.7\%.CONCLUSION}:In this study we could identify promising candidate genes using network based machine learning approaches even if no knowledge is available about the disease or phenotype.},
author = {Nitsch, D. and Goncalves, J. and Ojeda, F. and de Moor, B. and Moreau, Y.},
citeulike-article-id = {7842694},
citeulike-linkout-0 = {http://dx.doi.org/10.1186/1471-2105-11-460},
citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/20840752},
citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=20840752},
day = {14},
doi = {10.1186/1471-2105-11-460},
issn = {1471-2105},
journal = {BMC Bioinformatics},
keywords = {prioritization},
month = sep,
number = {1},
pages = {460+},
pmid = {20840752},
posted-at = {2010-09-29 10:11:21},
priority = {2},
title = {Candidate gene prioritization by network analysis of differential expression using machine learning approaches},
url = {http://dx.doi.org/10.1186/1471-2105-11-460},
volume = {11},
year = {2010}
}
@article{DeB07,
abstract = {Motivation: Hunting disease genes is a problem of primary importance in biomedical research. Biologists usually approach this problem in two steps: first a set of candidate genes is identified using traditional positional cloning or high-throughput genomics techniques; second, these genes are further investigated and validated in the wet lab, one by one. To speed up discovery and limit the number of costly wet lab experiments, biologists must test the candidate genes starting with the most probable candidates. So far, biologists have relied on literature studies, extensive queries to multiple databases and hunches about expected properties of the disease gene to determine such an ordering. Recently, we have introduced the data mining tool {ENDEAVOUR} (Aerts et al., 2006), which performs this task automatically by relying on different genome-wide data sources, such as Gene Ontology, literature, microarray, sequence and {more.Results}: In this article, we present a novel kernel method that operates in the same setting: based on a number of different views on a set of training genes, a prioritization of test genes is obtained. We furthermore provide a thorough learning theoretical analysis of the method's guaranteed performance. Finally, we apply the method to the disease data sets on which {ENDEAVOUR} (Aerts et al., 2006) has been benchmarked, and report a considerable improvement in empirical {performance.Availability}: The {MATLAB} code used in the empirical results will be made publicly {available.Contact}:tijl.debie@gmail.com or yves.moreau@esat.kuleuven.be},
address = {Department of Engineering Mathematics, University of Bristol, University Walk, BS8 1TR, Bristol, UK. tijl.debie@gmail.com},
author = {De Bie, T. and Tranchevent, L.-C. and van Oeffelen, L.M.M. and Moreau, Y.},
citeulike-article-id = {1651881},
citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btm187},
citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/23/13/i125},
citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/17646288},
citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=17646288},
day = {1},
doi = {10.1093/bioinformatics/btm187},
issn = {1460-2059},
journal = {Bioinformatics},
keywords = {data, fusion, nc2if},
month = jul,
number = {13},
pages = {i125--i132},
pmid = {17646288},
posted-at = {2009-06-09 14:49:38},
priority = {2},
title = {Kernel-based data fusion for gene prioritization},
url = {http://dx.doi.org/10.1093/bioinformatics/btm187},
volume = {23},
year = {2007}
}
@article{Nit09,
abstract = {Genetic studies (in particular linkage and association studies) identify chromosomal regions involved in a disease or phenotype of interest, but those regions often contain many candidate genes, only a few of which can be followed-up for biological validation. Recently, computational methods to identify (prioritize) the most promising candidates within a region have been proposed, but they are usually not applicable to cases where little is known about the phenotype (no or few confirmed disease genes, fragmentary understanding of the biological cascades involved). We seek to overcome this limitation by replacing knowledge about the biological process by experimental data on differential gene expression between affected and healthy individuals. Considering the problem from the perspective of a gene/protein network, we assess a candidate gene by considering the level of differential expression in its neighborhood under the assumption that strong candidates will tend to be surrounded by differentially expressed neighbors. We define a notion of soft neighborhood where each gene is given a contributing weight, which decreases with the distance from the candidate gene on the protein network. To account for multiple paths between genes, we define the distance using the Laplacian exponential diffusion kernel. We score candidates by aggregating the differential expression of neighbors weighted as a function of distance. Through a randomization procedure, we rank candidates by p-values. We illustrate our approach on four monogenic diseases and successfully prioritize the known disease causing genes.},
author = {Nitsch, D. and Tranchevent, L.-C. and Thienpont, B. and Thorrez, L. and Van~Esch, H. and Devriendt, K. and Moreau, Y.},
citeulike-article-id = {4510796},
citeulike-linkout-0 = {http://dx.doi.org/10.1371/journal.pone.0005526},
day = {13},
doi = {10.1371/journal.pone.0005526},
journal = {PLoS ONE},
keywords = {differential, expression, gwas, network, priorization, region},
month = may,
number = {5},
pages = {e5526+},
posted-at = {2009-09-28 15:42:31},
priority = {2},
publisher = {Public Library of Science},
title = {Network Analysis of Differential Expression for the Identification of {Disease-Causing} Genes},
url = {http://dx.doi.org/10.1371/journal.pone.0005526},
volume = {4},
year = {2009}
}
@article{Fra06,
abstract = {
Most common genetic disorders have a complex inheritance and may result from variants in many genes, each contributing only weak effects to the disease. Pinpointing these disease genes within the myriad of susceptibility loci identified in linkage studies is difficult because these loci may contain hundreds of genes. However, in any disorder, most of the disease genes will be involved in only a few different molecular pathways. If we know something about the relationships between the genes, we can assess whether some genes (which may reside in different loci) functionally interact with each other, indicating a joint basis for the disease etiology. There are various repositories of information on pathway relationships. To consolidate this information, we developed a functional human gene network that integrates information on genes and the functional relationships between genes, based on data from the Kyoto Encyclopedia of Genes and Genomes, the Biomolecular Interaction Network Database, Reactome, the Human Protein Reference Database, the Gene Ontology database, predicted protein-protein interactions, human yeast two-hybrid interactions, and microarray co-expressions. We applied this network to interrelate positional candidate genes from different disease loci and then tested 96 heritable disorders for which the Online Mendelian Inheritance in Man database reported at least three disease genes. Artificial susceptibility loci, each containing 100 genes, were constructed around each disease gene, and we used the network to rank these genes on the basis of their functional interactions. By following up the top five genes per artificial locus, we were able to detect at least one known disease gene in 54\% of the loci studied, representing a 2.8-fold increase over random selection. This suggests that our method can significantly reduce the cost and effort of pinpointing true disease genes in analyses of disorders for which numerous loci have been reported but for which most of the genes are unknown.
},
address = {Complex Genetics Section, Department of Biomedical Genetics-Department of Medical Genetics, University Medical Centre Utrecht, Utrecht, The Netherlands.},
author = {Franke, Lude and van Bakel, Harm and Fokkens, Like and de Jong, Edwin D. and Egmont-Petersen, Michael and Wijmenga, Cisca},
citeulike-article-id = {624114},
citeulike-linkout-0 = {http://dx.doi.org/10.1086/504300},
citeulike-linkout-1 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1474084/},
citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/16685651},
citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=16685651},
doi = {10.1086/504300},
issn = {0002-9297},
journal = {American journal of human genetics},
keywords = {bio, ppi},
month = jun,
number = {6},
pages = {1011--1025},
pmcid = {PMC1474084},
pmid = {16685651},
posted-at = {2006-06-29 21:07:20},
priority = {2},
title = {Reconstruction of a functional human gene network, with an application for prioritizing positional candidate genes.},
url = {http://dx.doi.org/10.1086/504300},
volume = {78},
year = {2006}
}
@article{Aer06,
abstract = {The identification of genes involved in health and disease remains a challenge. We describe a bioinformatics approach, together with a freely accessible, interactive and flexible software termed Endeavour, to prioritize candidate genes underlying biological processes or diseases, based on their similarity to known genes involved in these phenomena. Unlike previous approaches, ours generates distinct prioritizations for multiple heterogeneous data sources, which are then integrated, or fused, into a global ranking using order statistics. In addition, it offers the flexibility of including additional data sources. Validation of our approach revealed it was able to efficiently prioritize 627 genes in disease data sets and 76 genes in biological pathway sets, identify candidates of 16 mono- or polygenic diseases, and discover regulatory genes of myeloid differentiation. Furthermore, the approach identified a novel gene involved in craniofacial development from a {2-Mb} chromosomal region, deleted in some patients with {DiGeorge}-like birth defects. The approach described here offers an alternative integrative method for gene discovery.},
author = {Aerts, S. and Lambrechts, D. and Maity, S. and Van~Loo, P. and Coessens, B. and De~Smet, F. and Tranchevent, L.-C. and De~Moor, B. and Marynen, P. and Hassan, B. and Carmeliet, P. and Moreau, Y.},
citeulike-article-id = {615632},
citeulike-linkout-0 = {http://dx.doi.org/10.1038/nbt1203},
citeulike-linkout-1 = {http://dx.doi.org/10.1038/nbt1203},
citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/16680138},
citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=16680138},
day = {05},
doi = {10.1038/nbt1203},
issn = {1087-0156},
journal = {Nat Biotech},
keywords = {phenotype},
month = may,
number = {5},
pages = {537--544},
pmid = {16680138},
posted-at = {2008-10-29 15:40:04},
priority = {2},
publisher = {Nature Publishing Group},
title = {Gene prioritization through genomic data fusion},
url = {http://dx.doi.org/10.1038/nbt1203},
volume = {24},
year = {2006}
}
@article{Gus05,
abstract = {We construct a gene-to-gene regulatory network from time-series data of expression levels for the whole genome of the yeast Saccharomyces cerevisae, in a case where the number of measurements is much smaller than the number of genes in the network. This network is analyzed with respect to present biological knowledge of all genes (according to the Gene Ontology database), and we find some of its large-scale properties to be in accordance with known facts about the organism. The linear modeling employed here has been explored several times, but due to lack of any validation beyond investigating individual genes, it has been seriously questioned with respect to its applicability to biological systems. Our results show the adequacy of the approach and make further investigations of the model meaningful.},
author = {Gustafsson, M and Hornquist, M and Lombardi, A},
doi = {10.1109/TCBB.2005.35},
file = {:Users/catolsen/Library/Application Support/Mendeley Desktop/Downloaded/Gustafsson, Hornquist, Lombardi - 2005 - Constructing and analyzing a large-scale gene-to-gene regulatory network Lasso-constrained inference and biological validation.pdf:pdf},
institution = {Department of Science and Technology, Link\"{o}ping University (Campus Norrk\"{o}ping), Norrk\"{o}ping, Sweden. mikgu@itn.liu.se},
issn = {15455963},
journal = {IEEEACM Transactions on Computational Biology and Bioinformatics},
keywords = {algorithms,biological,computer simulation,gene expression profiling,gene expression profiling methods,gene expression regulation,gene expression regulation physiology,models,oligonucleotide array sequence analysis,oligonucleotide array sequence analysis methods,protein interaction mapping,protein interaction mapping methods,saccharomyces cerevisiae,saccharomyces cerevisiae metabolism,saccharomyces cerevisiae proteins,saccharomyces cerevisiae proteins metabolism,signal transduction,signal transduction physiology},
number = {3},
pages = {254--261},
pmid = {17044188},
publisher = {IEEE Computer Society Press},
title = {{Constructing and analyzing a large-scale gene-to-gene regulatory network Lasso-constrained inference and biological validation}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/17044188},
volume = {2},
year = {2005}
}
@article{Gel08,
author = {Gelman, A. and Jakulin, A. and Grazia~Pittau, M. and Su, Y.-S.},
citeulike-article-id = {7946427},
journal = {The Annals of Applied Statistics},
keywords = {bayes, glm, r},
number = {4},
pages = {1360--1383},
posted-at = {2011-11-03 14:54:01},
priority = {2},
title = {A weakly informative default prior distribution for logistic and other regression models},
volume = {2},
year = {2008}
}
@article{Smo11,
abstract = {Cytoscape is a popular bioinformatics package for biological network visualization and data integration. Version 2.8 introduces two powerful new {features--Custom} Node Graphics and Attribute Equations--which can be used jointly to greatly enhance Cytoscape's data integration and visualization capabilities. Custom Node Graphics allow an image to be projected onto a node, including images generated dynamically or at remote locations. Attribute Equations provide Cytoscape with spreadsheet-like functionality in which the value of an attribute is computed dynamically as a function of other attributes and network properties. Availability and implementation: Cytoscape is a desktop Java application released under the Library Gnu Public License ({LGPL}). Binary install bundles and source code for Cytoscape 2.8 are available for download from http://cytoscape.org.},
author = {Smoot, M.E. and Ono, K. and Ruscheinski, J. and Wang, P.-L.L. and Ideker, T.},
citeulike-article-id = {8420314},
citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btq675},
citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/content/early/2010/12/12/bioinformatics.btq675.abstract},
citeulike-linkout-2 = {http://bioinformatics.oxfordjournals.org/content/early/2010/12/12/bioinformatics.btq675.full.pdf},
citeulike-linkout-3 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/27/3/431},
citeulike-linkout-4 = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3031041/},
citeulike-linkout-5 = {http://view.ncbi.nlm.nih.gov/pubmed/21149340},
citeulike-linkout-6 = {http://www.hubmed.org/display.cgi?uids=21149340},
day = {1},
doi = {10.1093/bioinformatics/btq675},
issn = {1367-4811},
journal = {Bioinformatics (Oxford, England)},
keywords = {cytoscape},
month = feb,
number = {3},
pages = {431--432},
pmcid = {PMC3031041},
pmid = {21149340},
posted-at = {2011-02-01 13:47:39},
priority = {2},
title = {Cytoscape 2.8: new features for data integration and network visualization.},
url = {http://dx.doi.org/10.1093/bioinformatics/btq675},
volume = {27},
year = {2011}
}
@article{Tetrad,
author = {R. Scheines and P. Spirtes and C. Glymour and C. Meek},
title = {Tetrad II: Tools for Causal Modeling. User's manual},
year = {1994},
volume={},
journal={Hillsdale, NJ: Erlbaum},
masid = {3850139}
}
@article{Put10,
abstract = {Reverse-engineering gene networks from expression profiles is a difficult problem for which a multitude of techniques have been developed over the last decade. The yearly organized {DREAM} challenges allow for a fair evaluation and unbiased comparison of these methods.},
author = {Pinna, Andrea and Soranzo, Nicola and de la Fuente, Alberto},
citeulike-article-id = {8003897},
citeulike-linkout-0 = {http://dx.doi.org/10.1371/journal.pone.0012912},
day = {11},
doi = {10.1371/journal.pone.0012912},
journal = {PLoS ONE},
keywords = {networks},
month = oct,
number = {10},
pages = {e12912+},
posted-at = {2010-10-14 19:32:58},
priority = {2},
publisher = {Public Library of Science},
title = {From Knockouts to Networks: Establishing Direct {Cause-Effect} Relationships through Graph Analysis},
url = {http://dx.doi.org/10.1371/journal.pone.0012912},
volume = {5},
year = {2010}
}
@article{Yip10,
author = {Yip, Kevin Y. and Alexander, Roger P. and Yan, Koon-Kiu and Gerstein, Mark},
citeulike-article-id = {6644318},
citeulike-linkout-0 = {http://dx.doi.org/10.1371/journal.pone.0008121},
citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/20126643},
citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=20126643},
day = {26},
doi = {10.1371/journal.pone.0008121},
issn = {1932-6203},
journal = {PLoS ONE},
keywords = {dream, network, reconstruction},
month = jan,
number = {1},
pages = {e8121+},
pmid = {20126643},
posted-at = {2010-05-18 19:52:55},
priority = {3},
publisher = {Public Library of Science},
title = {Improved Reconstruction of In Silico Gene Regulatory Networks by Integrating Knockout and Perturbation Data},
url = {http://dx.doi.org/10.1371/journal.pone.0008121},
volume = {5},
year = {2010}
}
@article {Gev07,
author = {Gevaert, O. and Van~Vooren, S. and De~Moor, B.},
title = {A Framework for Elucidating Regulatory Networks Based on Prior Information and Expression Data},
journal = {Annals of the New York Academy of Sciences},
volume = {1115},
number = {1},
publisher = {Blackwell Publishing Inc},
issn = {1749-6632},
url = {http://dx.doi.org/10.1196/annals.1407.002},
doi = {10.1196/annals.1407.002},
pages = {240--248},
keywords = {Bayesian networks, regulatory networks, prior information},
year = {2007},
}
@article{Kat05,
author = {Kato, T. and Tsuda, K. and Asai, K.},
title = {Selective integration of multiple biological data for supervised network inference},
journal = {Bioinformatics},
volume = {21},
issue = {10},
month = {May},
year = {2005},
issn = {1367-4803},
pages = {2488--2495},
numpages = {8},
url = {http://portal.acm.org/citation.cfm?id=1094112.1094148},
doi = {10.1093/bioinformatics/bti339},
acmid = {1094148},
publisher = {Oxford University Press},
address = {Oxford, UK},
}
@INPROCEEDINGS{Ide00,
author = {Trey E. Ideker and Vesteinn Thorsson and Richard M. Karp},
title = {Discovery of regulatory interactions through perturbation: Inference and experimental design},
booktitle = {In Pacific Symposium on Biocomputing 5},
year = {2000},
pages = {302--313}
}
@Article{Kig04,
AUTHOR = {Kightley, D A and Chandra, N and Elliston, K},
TITLE = {Inferring gene regulatory networks from raw data--a molecular epistemics approach.},
JOURNAL = {Pac Symp Biocomput},
VOLUME = {},
YEAR = {2004},
NUMBER = {},
PAGES = {510-20},
URL = {http://www.biomedsearch.com/nih/Inferring-gene-regulatory-networks-from/14992529.html},
PubMedID = {14992529},
ISSN = {1793-5091},
}
@article{Tam03,
abstract = {We present a statistical method for estimating gene networks and detecting promoter elements simultaneously. When estimating a network from gene expression data alone, a common problem is that the number of microarrays is limited compared to the number of variables in the network model, making accurate estimation a difficult task. Our method overcomes this problem by integrating the microarray gene expression data and the {DNA} sequence information into a Bayesian network model. The basic idea of our method is that, if a parent gene is a transcription factor, its children may share a consensus motif in their promoter regions of the {DNA} sequences. Our method detects consensus motifs based on the structure of the estimated network, then re-estimates the network using the result of the motif detection. We continue this iteration until the network becomes stable. To show the effectiveness of our method, we conducted Monte Carlo simulations and applied our method to Saccharomyces cerevisiae data as a real application. Contact: tamada@ims.u-tokyo.ac.jp},
address = {Human Genome Center, Institute of Medical Science, The University of Tokyo, 4-6-1 Shirokanedai, Minato-ku, Tokyo, 108-8639, Japan Graduate School of Genetic Resource Technology, Kyushu University, 6-10-1 Hakozaki, Higashi-ku, Fukuoka, 812-8581, Japan.},
author = {Tamada, Y. and Kim, S. and Bannai, H. and Imoto, S. and Tashiro, K. and Kuhara, S. and Miyano, S.},
citeulike-article-id = {452877},
citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/14534194},
citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=14534194},
issn = {1367-4803},
journal = {Bioinformatics},
keywords = {bayesian, dataintegration, expressiondata, sequencedata},
month = oct,
pmid = {14534194},
posted-at = {2005-12-29 16:39:43},
priority = {3},
title = {Estimating gene networks from gene expression data by combining {B}ayesian network model with promoter element detection.},
url = {http://view.ncbi.nlm.nih.gov/pubmed/14534194},
volume = {19 Suppl 2},
year = {2003}
}
@INPROCEEDINGS{Che99,
author = {Ting Chen and Hongyu L. He and George M. Church},
title = {Modeling Gene Expression With Differential Equations},
booktitle = {Pac. Symp. Biocomput},
year = {1999},
pages = {29--40}
}
@Article{Bas05,
abstract = {{Abstract. Inferring the metabolic pathways that control the cell cycles is a challenging and difficult task. However, its importance in the process of understanding living organisms has been leading to the development of several models to infer gene regulatory networks from DNA microarray data. In the last years, many works have been adding biological information to those models to improve the obtained results. In this work, we add prior biological knowledge into a Bayesian Network model with non parametric regression and analyze the effects caused by such information in the results. 1}},
author = {Bastos, Gustavo and Guimar\~{a}es, Katia S.},
citeulike-article-id = {4943995},
citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.110.8673},
posted-at = {2009-06-24 14:14:29},
priority = {2},
year={2005},
title = {{Analyzing the Effect of Prior Knowledge in Genetic Regulatory Network Inference}},
url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.110.8673},
journal = {eletronic}
}
@INPROCEEDINGS{Har02,
author = {A.J. Hartemink and D.K. Gifford and T.S. Jaakkola and R.A. Young},
title = {Combining location and expression data for principled discovery of genetic regulatory network models},
booktitle = {Proc. of the Pacific Symp. on Biocomputing},
year = {2002},
volume={7},
pages = {437--449}
}
@article{Weh07,
author = {Werhli, A. and Husmeier, D.},
citeulike-article-id = {1639384},
citeulike-linkout-0 = {http://www.bepress.com/sagmb/vol6/iss1/art15/},
journal = {Statistical Applications in Genetics and Molecular Biology},
keywords = {bayes, structure-learning},
number = {1},
posted-at = {2007-09-09 18:39:43},
priority = {2},
title = {Reconstructing Gene Regulatory Networks with Bayesian Networks by Combining Expression Data with Multiple Sources of Prior Knowledge},
url = {http://www.bepress.com/sagmb/vol6/iss1/art15/},
volume = {6},
year = {2007}
}
@INPROCEEDINGS{Imo03,
author = {S. Imoto and T. Higuchi and T. Goto and K. Tashiro and S. Kuhara and S. Miyano},
title = {Combining microarrays and biological knowledge for estimating gene networks via Bayesian networks},
booktitle = {In Proceedings of the IEEE Computer Society Bioinformatics Conference (CSB 03},
year = {2003},
pages = {104--113},
publisher = {IEEE}
}
@Article{Hus07,
AUTHOR = {Husmeier, D. and Werhli, A.V},
TITLE = {Bayesian integration of biological prior knowledge into the reconstruction of gene regulatory networks with Bayesian networks.},
JOURNAL = {Comput Syst Bioinformatics Conf},
VOLUME = {6},
YEAR = {2007},
NUMBER = {},
PAGES = {85-95},
URL = {http://www.biomedsearch.com/nih/Bayesian-integration-biological-prior-knowledge/17951815.html},
PubMedID = {17951815},
ISSN = {1752-7791},
}
@article{Phi04,
author = {Phillip P. Le and Amit Bahl and Lyle H. Ungar},
title = {Using prior knowledge to improve genetic network reconstruction from microarray data},
journal = {in Silico Biology},
volume = {4},
year = {2004},
masid = {1702357}
}
@article{Anj09,
author = {Anjum, S. and Doucet, A. and Holmes, C.C.},
title = {A boosting approach to structure learning of graphs with and without prior knowledge},
journal = {Bioinformatics},
volume = {25},
issue = {22},
month = {November},
year = {2009},
issn = {1367-4803},
pages = {2929--2936},
numpages = {8},
url = {http://portal.acm.org/citation.cfm?id=1666867.1666873},
doi = {10.1093/bioinformatics/btp485},
acmid = {1666873},
publisher = {Oxford University Press},
address = {Oxford, UK},
}
@article{Cas00,
author = {R. Castelo and
A. Siebes},
title = {Priors on network structures. {B}iasing the search for {B}ayesian
networks},
journal = {Int. J. Approx. Reasoning},
volume = {24},
number = {1},
year = {2000},
pages = {39-57},
ee = {http://dx.doi.org/10.1016/S0888-613X(99)00041-9},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@article{Chr09,
author = {Christley, Scott AND Nie, Qing AND Xie, Xiaohui},
journal = {PLoS ONE},
publisher = {Public Library of Science},
title = {Incorporating Existing Network Information into Gene Network Inference},
year = {2009},
month = {08},
volume = {4},
url = {http://dx.doi.org/10.1371%2Fjournal.pone.0006799},
pages = {e6799},
abstract = {
One methodology that has met success to infer gene networks from gene expression data is based upon ordinary differential equations (ODE). However new types of data continue to be produced, so it is worthwhile to investigate how to integrate these new data types into the inference procedure. One such data is physical interactions between transcription factors and the genes they regulate as measured by ChIP-chip or ChIP-seq experiments. These interactions can be incorporated into the gene network inference procedure as a priori network information. In this article, we extend the ODE methodology into a general optimization framework that incorporates existing network information in combination with regularization parameters that encourage network sparsity. We provide theoretical results proving convergence of the estimator for our method and show the corresponding probabilistic interpretation also converges. We demonstrate our method on simulated network data and show that existing network information improves performance, overcomes the lack of observations, and performs well even when some of the existing network information is incorrect. We further apply our method to the core regulatory network of embryonic stem cells utilizing predicted interactions from two studies as existing network information. We show that including the prior network information constructs a more closely representative regulatory network versus when no information is provided.
},
number = {8},
doi = {10.1371/journal.pone.0006799}
}
@article{Bar99,
abstract = {Systems as diverse as genetic networks or the World Wide Web are best described as networks with complex topology. A common property of many large networks is that the vertex connectivities follow a scale-free power-law distribution. This feature was found to be a consequence of two generic mechanisms: (i) networks expand continuously by the addition of new vertices, and (ii) new vertices attach preferentially to sites that are already well connected. A model based on these two ingredients reproduces the observed stationary scale-free distributions, which indicates that the development of large networks is governed by robust self-organizing phenomena that go beyond the particulars of the individual systems.},
address = {Department of Physics, University of Notre Dame, Notre Dame, IN 46556, USA.},
author = {Barabasi, A. L. and Albert, R.},
citeulike-article-id = {90557},
citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/10521342},
citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=10521342},
day = {15},
issn = {1095-9203},
journal = {Science (New York, N.Y.)},
keywords = {complexity, eni, graph, networks, scalefree, theory},
month = oct,
number = {5439},
pages = {509--512},
pmid = {10521342},
posted-at = {2006-02-08 01:49:16},
priority = {2},
title = {Emergence of scaling in random networks},
url = {http://view.ncbi.nlm.nih.gov/pubmed/10521342},
volume = {286},
year = {1999}
}
@article{Pri10,
author = {Prill, R.J. AND Marbach, D. AND Saez-Rodriguez, J. AND Sorger, P.K. AND Alexopoulos, L.G. AND Xue, X. AND Clarke, N.D. AND Altan-Bonnet, G. AND Stolovitzky, G.},
journal = {PLoS ONE},
publisher = {Public Library of Science},
title = {Towards a Rigorous Assessment of Systems Biology Models: The DREAM3 Challenges},
year = {2010},
month = {02},
volume = {5},
url = {http://dx.doi.org/10.1371%2Fjournal.pone.0009202},
pages = {e9202},
abstract = {
Background
Systems biology has embraced computational modeling in response to the quantitative nature and increasing scale of contemporary data sets. The onslaught of data is accelerating as molecular profiling technology evolves. The Dialogue for Reverse Engineering Assessments and Methods (DREAM) is a community effort to catalyze discussion about the design, application, and assessment of systems biology models through annual reverse-engineering challenges.
Methodology and Principal Findings
We describe our assessments of the four challenges associated with the third DREAM conference which came to be known as the DREAM3 challenges: signaling cascade identification, signaling response prediction, gene expression prediction, and the DREAM3 in silico network challenge. The challenges, based on anonymized data sets, tested participants in network inference and prediction of measurements. Forty teams submitted 413 predicted networks and measurement test sets. Overall, a handful of best-performer teams were identified, while a majority of teams made predictions that were equivalent to random. Counterintuitively, combining the predictions of multiple teams (including the weaker teams) can in some cases improve predictive power beyond that of any single method.
Conclusions
DREAM provides valuable feedback to practitioners of systems biology modeling. Lessons learned from the predictions of the community provide much-needed context for interpreting claims of efficacy of algorithms described in the scientific literature.
},
number = {2},
doi = {10.1371/journal.pone.0009202}
}
@Article{Mar10,
abstract = {Numerous methods have been developed for inferring gene
regulatory networks from expression data, however, both
their absolute and comparative performance remain poorly
understood. In this paper, we introduce a framework for
critical performance assessment of methods for gene
network inference. We present an in silico benchmark
suite that we provided as a blinded, community-wide
challenge within the context of the DREAM (Dialogue on
Reverse Engineering Assessment and Methods) project. We
assess the performance of 29 gene-network-inference
methods, which have been applied independently by
participating teams. Performance profiling reveals that
current inference methods are affected, to various
degrees, by different types of systematic prediction
errors. In particular, all but the best-performing method
failed to accurately infer multiple regulatory inputs
(combinatorial regulation) of genes. The results of this
community-wide experiment show that reliable network
inference from gene expression data remains an unsolved
problem, and they indicate potential ways of network
reconstruction improvements.},
affiliation = {EPFL},
author = {Marbach, D. and Prill, R.J. and Schaffter,
T. and Mattiussi, C. and Floreano, D. and
Stolovitzky, G.},
details = {http://infoscience.epfl.ch/record/148228},
documenturl = {http://infoscience.epfl.ch/record/148228/files/Marbach2010.pdf},
doi = {10.1073/pnas.0913357107},
extra-id = {000276374400031},
journal = {Proceedings of the {N}ational {A}cademy of {S}ciences},
keywords = {DREAM challenge; community experiment; reverse
engineering; transcriptional regulatory networks;
performance assessment},
note = {WingX},
number = {14},
oai-id = {oai:infoscience.epfl.ch:148228},
oai-set = {article; fulltext-public; fulltext},
pages = {6286--6291},
review = {NON-REVIEWED},
status = {PUBLISHED},
submitter = {161219},
title = {Revealing strengths and weaknesses of methods for gene network inference},
unit = {LIS},
volume = {107},
year = 2010
}
@article{Guy08,
author = {I. Guyon and
C.F. Aliferis and
G.F. Cooper and
A. Elisseeff and
J.-P. Pellet and
P. Spirtes and
A.R. Statnikov},
title = {Design and Analysis of the Causation and Prediction Challenge},
journal = {Journal of Machine Learning Research - Proceedings Track},
volume = {3},
year = {2008},
pages = {1-33},
ee = {http://www.jmlr.org/proceedings/papers/v3/guyon08a.html},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@article{Scu10,
author = "M. Scutari",
title = "Learning {B}ayesian Networks with the bnlearn {R} Package",
journal = "Journal of Statistical Software",
volume = "35",
number = "3",
pages = "1--22",
day = "16",
month = "7",
year = "2010",
CODEN = "JSSOBK",
ISSN = "1548-7660",
bibdate = "2010-05-13",
URL = "http://www.jstatsoft.org/v35/i03",
accepted = "2010-05-13",
acknowledgement = "",
keywords = "",
submitted = "2009-09-30",
}
@article{Jor10,
title={Metastasis-Associated Gene Expression Changes Predict Poor Outcomes in Patients with Dukes Stage B and C Colorectal Cancer},
author={Jorissen RN and Gibbs P and Christie M and Prakash S et al.},
year={2010},
journal={Clin Cancer Res}
}
@article{War10,
title={The GeneMANIA prediction server: biological network integration for gene prioritization and predicting gene function},
author={Warde-Farley, D and Donaldson, SL and Comes, O and Zuberi, K and Badrawi, R and Chao, P and Franz, M and Grouios, C and Kazi, F and Lopes, CT and Maitland, A and Mostafavi, S and Montojo, J and Shao, Q and Wright, G and Bader, GD and Morris, Q},
journal={Nucleid Acids Res.},
year={2010}
}
@inproceedings{Ols09a,
Author = {C. Olsen and P.E. Meyer and G. Bontempi},
Booktitle = {Proceedings of the 5th Benelux Bioinformatics Conference (BBC09)},
Title = {Poster: Inferring causal relationships using information-theoretic measures },
Year = {2009}}
@ARTICLE{Ali10a,
author = {C.F. Aliferis and A. Statnikov and I. Tsamardinos and S. Mani and X.D. Koutsoukos},
title = {Local causal and Markov blanket induction for causal discovery and feature selection for classification. Part II: Analysis and extensions},
journal = {Journal of Machine Learning Research},
year = {2010},
pages = {2010}
}
@article{Ali10,
author = {Aliferis, C.F. and Statnikov, A. and Tsamardinos, I. and Mani, S. and Koutsoukos, X.D.},
title = {Local Causal and Markov Blanket Induction for Causal Discovery and Feature Selection for Classification Part II: Analysis and Extensions},
journal = {J. Mach. Learn. Res.},
volume = {11},
month = {March},
year = {2010},
issn = {1532-4435},
pages = {235--284},
numpages = {50},
url = {http://portal.acm.org/citation.cfm?id=1756006.1756014},
acmid = {1756014},
publisher = {MIT Press},
address = {Cambridge, MA, USA},
}
@article {Cam09,
author = {Di Camillo, B. and Toffolo, G. and Cobelli, C.},
title = "A Gene Network Simulator to Assess Reverse Engineering Algorithms",
journal = "Annals of the New York Academy of Sciences",
volume = "1158",
year = "March 2009",
pages = "125-142(18)",
url = {http://www.ingentaconnect.com/content/bsc/nyas/2009/00001158/00000001/art00013},
doi = "doi:10.1111/j.1749-6632.2008.03756.x"
}
@article{Li09,
abstract = {One of the important goals in systems biology is to infer transcription network based on gene expression data. Validation of the reconstructed network often requires benchmark datasets, e.g. gene expression data, which are usually unattainable. Synthetic datasets are therefore often needed to test the structure learning algorithms in a fast and reproducible manner. However, due to the lack of knowledge about the gene expression profiles, synthetic datasets may not resemble the biological reality. Here we present a computational tool, namely, ReTRN (Real Transcriptional Regulatory Networks) for extracting subnetworks from known transcription network and for generating corresponding gene expression data. By comparing with other implementations, we demonstrate that the network generated by ReTRN possesses scale free property, which resembles the biological reality. Moreover, ReTRN simultaneously generates gene expression data reflecting the temporal relationship in gene expression. We conclude that ReTRN provides a valid alternative to existing implementation and can be widely used in systems biology research.},
author = {Li, Y. and Zhu, Y. and Bai, X. and Cai, H. and Ji, W.i and Guo, D.},
citeulike-article-id = {5657255},
citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.ygeno.2009.08.009},
citeulike-linkout-1 = {http://linkinghub.elsevier.com/retrieve/pii/S0888754309001992},
day = {25},
doi = {10.1016/j.ygeno.2009.08.009},
issn = {08887543},
journal = {Genomics},
month = {August},
posted-at = {2009-08-27 14:27:03},
volume={},
title = {ReTRN: a retriever of real transcriptional regulatory network and expression data for evaluating structure learning algorithm},
url = {http://dx.doi.org/10.1016/j.ygeno.2009.08.009},
year = {2009}
}
@article{Mar09,
author={D. Marbach and C. Mattiussi and D. Floreano},
journal={Journal of Computational Biology. To appear.},
volume={},
title={Generating Realistic in silico Gene Networks for Performance Assessment of Reverse Engineering Methods},
year={2009}
}
@article{Aka74,
abstract = {The history of the development of statistical hypothesis testing in time series analysis is reviewed briefly and it is pointed out that the hypothesis testing procedure is not adequately defined as the procedure for statistical model identification. The classical maximum likelihood estimation procedure is reviewed and a new estimate minimum information theoretical criterion (AIC) estimate (MAICE) which is designed for the purpose of statistical identification is introduced. When there are several competing models the MAICE is defined by the model and the maximum likelihood estimates of the parameters which give the minimum of AIC defined by AIC = (-2)log-(maximum likelihood) + 2(number of independently adjusted parameters within the model). MAICE provides a versatile procedure for statistical model identification which is free from the ambiguities inherent in the application of conventional hypothesis testing procedure. The practical utility of MAICE in time series analysis is demonstrated with some numerical examples.},
author = {Akaike, H.},
citeulike-article-id = {849862},
citeulike-linkout-0 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1100705},
journal = {Automatic Control, IEEE Transactions on},
keywords = {aic, model, selection, statistical},
number = {6},
pages = {716--723},
posted-at = {2006-09-19 17:26:06},
priority = {5},
title = {A new look at the statistical model identification},
url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1100705},
volume = {19},
year = {1974}
}
@article{Sch78,
abstract = {The problem of selecting one of a number of models of different dimensions is treated by finding its Bayes solution, and evaluating the leading terms of its asymptotic expansion. These terms are a valid large-sample criterion beyond the Bayesian context, since they do not depend on the a priori distribution.},
author = {Schwarz, Gideon},
citeulike-article-id = {90008},
citeulike-linkout-0 = {http://dx.doi.org/10.2307/2958889},
citeulike-linkout-1 = {http://www.jstor.org/stable/2958889},
doi = {10.2307/2958889},
journal = {The Annals of Statistics},
keywords = {model, selection},
number = {2},
pages = {461--464},
posted-at = {2005-06-02 06:42:21},
priority = {4},
title = {Estimating the Dimension of a Model},
url = {http://dx.doi.org/10.2307/2958889},
volume = {6},
year = {1978}
}
@article{Tsu95,
author = {Tsujishita, Toru},
title = {On triple mutual information},
journal = {Adv. Appl. Math.},
volume = {16},
number = {3},
year = {1995},
issn = {0196-8858},
pages = {269--274},
doi = {http://dx.doi.org/10.1006/aama.1995.1013},
publisher = {Academic Press, Inc.},
address = {Orlando, FL, USA},
}
@inproceedings{Fay96,
author = {Fayyad, U. and Piatetsky-Shapiro, G. and Smyth, P.},
title = {The {KDD} Process for Extracting Useful Knowledge from Volumes of Data},
booktitle = {Communication of the ACM},
pages = {27-34},
year = {1996},
volume = {29},
month = {November},
url = {citeseer.ist.psu.edu/fayyad96kdd.html} }
@InCollection{Kol07,
author = "Koller, D. and Friedman, N. and Getoor, L. and Taskar, B.",
title = "Graphical Models in a Nutshell",
booktitle = "An Introduction to Statistical Relational Learning",
year = "2007",
editor = "L. Getoor and B. Taskar",
publisher = "MIT Press",
}
@book{Shi02,
abstract = {{Bill Shipley explores the logical and methodological relationships between correlation and causation. He presents a series of statistical methods that can test, and potentially discover, cause-effect relationships between variables in situations where it is not possible to conduct randomized, or experimentally controlled, studies. Many of these methods are quite new and most are generally unknown to biologists. Besides describing how to conduct these statistical tests, he also puts the methods into historical context and explains when they can and cannot justifiably be used to test causal claims. Hb ISBN (2000); 0-521-79153-7}},
author = {Shipley, B.},
citeulike-article-id = {487580},
citeulike-linkout-0 = {http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20&path=ASIN/0521529212},
citeulike-linkout-1 = {http://www.amazon.de/exec/obidos/redirect?tag=citeulike01-21&path=ASIN/0521529212},
citeulike-linkout-2 = {http://www.amazon.fr/exec/obidos/redirect?tag=citeulike06-21&path=ASIN/0521529212},
citeulike-linkout-3 = {http://www.amazon.jp/exec/obidos/ASIN/0521529212},
citeulike-linkout-4 = {http://www.amazon.co.uk/exec/obidos/ASIN/0521529212/citeulike00-21},
citeulike-linkout-5 = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/0521529212},
citeulike-linkout-6 = {http://www.worldcat.org/isbn/0521529212},
citeulike-linkout-7 = {http://books.google.com/books?vid=ISBN0521529212},
citeulike-linkout-8 = {http://www.amazon.com/gp/search?keywords=0521529212&index=books&linkCode=qs},
citeulike-linkout-9 = {http://www.librarything.com/isbn/0521529212},
howpublished = {Paperback},
isbn = {0521529212},
keywords = {books, causality, graphicalmodels, pathanalysis, scanned, sem, statistics, structuralequations},
month = {August},
posted-at = {2008-11-26 19:32:57},
priority = {2},
publisher = {{Cambridge University Press}},
title = {Cause and Correlation in Biology : A User's Guide to Path Analysis, Structural Equations and Causal Inference},
url = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/0521529212},
year = {2002}
}
@INPROCEEDINGS{Ver92,
author = {T. Verma and J. Pearl},
title = {An Algorithm for Deciding if a Set of Observed Independencies Has a Causal Explanation},
booktitle = {Proc. of the Eighth Conference on Uncertainty in Artificial Intelligence},
year = {1992},
pages = {323--330},
publisher = {Morgan Kaufmann}
}
@article{Wu06,
author = {Wu, X. and Ye, Y.},
title = {Exploring gene causal interactions using an enhanced constraint-based method},
journal = {Pattern Recogn.},
volume = {39},
number = {12},
year = {2006},
issn = {0031-3203},
pages = {2439--2449},
doi = {http://dx.doi.org/10.1016/j.patcog.2006.05.003},
publisher = {Elsevier Science Inc.},
address = {New York, NY, USA},
}
@misc{Roo08,
author = "T.Roos and T. Heikkil{\"a} and P. Myllym{\"a}ki and P. Hoyer",
title = "Computer-assisted stemmatology",
year = "2008",
month = "October",
url = "http://www.cs.helsinki.fi/u/ttonteri/casc/stemma.html",
institution = "Causality workbench repository" }
@misc{Moo08,
author = "J. Mooij and D. Janzing and B. Sch{\"o}lkopf",
title = "Distinguishing between cause and effect",
year = "2008",
month = "October",
url = "http://www.kyb.tuebingen.mpg.de/bs/people/jorism/causality-data/",
institution = "Causality workbench repository" }
@article{Tsa06,
abstract = {We present a new algorithm for Bayesian network structure learning, called Max-Min Hill-Climbing (MMHC). The algorithm combines ideas from local learning, constraint-based, and search-and-score techniques in a principled and effective way. It first reconstructs the skeleton of a Bayesian network and then performs a Bayesian-scoring greedy hill-climbing search to orient the edges. In our extensive empirical evaluation MMHC outperforms on average and in terms of various metrics several prototypical and state-of-the-art algorithms, namely the PC, Sparse Candidate, Three Phase Dependency Analysis, Optimal Reinsertion, Greedy Equivalence Search, and Greedy Search. These are the first empirical results simultaneously comparing most of the major Bayesian network algorithms against each other. MMHC offers certain theoretical advantages, specifically over the Sparse Candidate algorithm, corroborated by our experiments. MMHC and detailed results of our study are publicly available at http://www.dsl-lag.org/supplements/mmhc\_paper/mmhc\_index.html.},
address = {Netherlands},
author = {Tsamardinos, I. and Brown, L.E. and Aliferis, C.},
citeulike-article-id = {969773},
citeulike-linkout-0 = {http://dx.doi.org/10.1007/s10994-006-6889-7},
citeulike-linkout-1 = {http://www.ingentaconnect.com/content/klu/ml/2006/00000065/00000001/00006889},
doi = {10.1007/s10994-006-6889-7},
issn = {0885-6125},
journal = {Machine Learning},
keywords = {bayesiannets, structuresearch},
month = {October},
number = {1},
pages = {31--78},
posted-at = {2007-12-17 07:36:15},
priority = {4},
publisher = {Springer},
title = {The max-min hill-climbing Bayesian network structure learning algorithm},
url = {http://dx.doi.org/10.1007/s10994-006-6889-7},
volume = {65},
year = {2006}
}
@article{Sch05,
abstract = {Inferring large-scale covariance matrices from sparse genomic data is an ubiquitous problem in bioinformatics. Clearly, the widely used standard covariance and correlation estimators are ill-suited for this purpose. As statistically efficient and computationally fast alternative we propose a novel shrinkage covariance estimator that exploits the Ledoit-Wolf (2003) lemma for analytic calculation of the optimal shrinkage intensity. Subsequently, we apply this improved covariance estimator (which has guaranteed minimum mean squared error, is well-conditioned, and is always positive definite even for small sample sizes) to the problem of inferring large-scale gene association networks. We show that it performs very favorably compared to competing approaches both in simulations as well as in application to real expression data.},
address = {Department of Statistics, University of Munich, Germany. schaefer@stat.math.ethz.ch},
author = {Sch\"{a}fer, J. and Strimmer, K.},
citeulike-article-id = {1485976},
citeulike-linkout-0 = {http://dx.doi.org/10.2202/1544-6115.1175},
citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/16646851},
citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=16646851},
doi = {10.2202/1544-6115.1175},
issn = {1544-6115},
journal = {Statistical applications in genetics and molecular biology},
keywords = {shrinkage},
posted-at = {2008-09-12 10:44:01},
priority = {2},
title = {A shrinkage approach to large-scale covariance matrix estimation and implications for functional genomics.},
url = {http://dx.doi.org/10.2202/1544-6115.1175},
volume = {4},
year = {2005}
}
@article{Sch05a,
abstract = {MOTIVATION: Genetic networks are often described statistically using graphical models (e.g. Bayesian networks). However, inferring the network structure offers a serious challenge in microarray analysis where the sample size is small compared to the number of considered genes. This renders many standard algorithms for graphical models inapplicable, and inferring genetic networks an 'ill-posed' inverse problem. METHODS: We introduce a novel framework for small-sample inference of graphical models from gene expression data. Specifically, we focus on the so-called graphical Gaussian models (GGMs) that are now frequently used to describe gene association networks and to detect conditionally dependent genes. Our new approach is based on (1) improved (regularized) small-sample point estimates of partial correlation, (2) an exact test of edge inclusion with adaptive estimation of the degree of freedom and (3) a heuristic network search based on false discovery rate multiple testing. Steps (2) and (3) correspond to an empirical Bayes estimate of the network topology. RESULTS: Using computer simulations, we investigate the sensitivity (power) and specificity (true negative rate) of the proposed framework to estimate GGMs from microarray data. This shows that it is possible to recover the true network topology with high accuracy even for small-sample datasets. Subsequently, we analyze gene expression data from a breast cancer tumor study and illustrate our approach by inferring a corresponding large-scale gene association network for 3883 genes.},
address = {Department of Statistics, University of Munich, Ludwigstrasse 33, D-80539 Munich, Germany.},
author = {Sch\"{a}fer, J. and Strimmer, K.},
citeulike-article-id = {1088995},
citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/15479708},
citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=15479708},
issn = {1367-4803},
journal = {Bioinformatics},
keywords = {genetic\_regulatory\_networks},
month = {March},
number = {6},
pages = {754--764},
posted-at = {2007-02-06 00:59:40},
priority = {5},
title = {An empirical Bayes approach to inferring large-scale gene association networks.},
url = {http://view.ncbi.nlm.nih.gov/pubmed/15479708},
volume = {21},
year = {2005}
}
@ARTICLE{Vic02,
author = {{Victor}, J.D.},
title = "{Binless strategies for estimation of information from neural data}",
journal = {Physical Review E},
year = 2002,
month = nov,
volume = 66,
number = 5,
doi = {10.1103/PhysRevE.66.051903},
adsurl = {http://adsabs.harvard.edu/abs/2002PhRvE..66e1903V},
adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}
@article{Ste02,
abstract = {MOTIVATION: Clustering co-expressed genes usually requires the definition of 'distance' or 'similarity' between measured datasets, the most common choices being Pearson correlation or Euclidean distance. With the size of available datasets steadily increasing, it has become feasible to consider other, more general, definitions as well. One alternative, based on information theory, is the mutual information, providing a general measure of dependencies between variables. While the use of mutual information in cluster analysis and visualization of large-scale gene expression data has been suggested previously, the earlier studies did not focus on comparing different algorithms to estimate the mutual information from finite data. RESULTS: Here we describe and review several approaches to estimate the mutual information from finite datasets. Our findings show that the algorithms used so far may be quite substantially improved upon. In particular when dealing with small datasets, finite sample effects and other sources of potentially misleading results have to be taken into account.},
address = {University Potsdam, Nonlinear Dynamics Group, Germany. steuer@agnld.uni-potsdam.de},
author = {Steuer, R. and Kurths, J. and Daub, C. O. and Weise, J. and Selbig, J.},
citeulike-article-id = {764936},
citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/18.suppl_2.S231},
citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/18/suppl_2/S231},
citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/12386007},
citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=12386007},
doi = {10.1093/bioinformatics/18.suppl_2.S231},
issn = {1367-4803},
journal = {Bioinformatics},
keywords = {information, mutual},
posted-at = {2009-05-01 21:35:19},
priority = {2},
title = {The mutual information: detecting and evaluating dependencies between variables.},
url = {http://dx.doi.org/10.1093/bioinformatics/18.suppl_2.S231},
volume = {18 Suppl 2},
year = {2002}
}
@book{Sil86,
abstract = {{Although there has been a surge of interest in density estimation in recent years, much of the published research has been concerned with purely technical matters with insufficient emphasis given to the technique's practical value. Furthermore, the subject has been rather inaccessible to the general statistician.The account presented in this book places emphasis on topics of methodological importance, in the hope that this will facilitate broader practical application of density estimation and also encourage research into relevant theoretical work. The book also provides an introduction to the subject for those with general interests in statistics. The important role of density estimation as a graphical technique is reflected by the inclusion of more than 50 graphs and figures throughout the text.Several contexts in which density estimation can be used are discussed, including the exploration and presentation of data, nonparametric discriminant analysis, cluster analysis, simulation and the bootstrap, bump hunting, projection pursuit, and the estimation of hazard rates and other quantities that depend on the density. This book includes general survey of methods available for density estimation. The Kernel method, both for univariate and multivariate data, is discussed in detail, with particular emphasis on ways of deciding how much to smooth and on computation aspects. Attention is also given to adaptive methods, which smooth to a greater degree in the tails of the distribution, and to methods based on the idea of penalized likelihood.}},
author = {Silverman, B.W.},
citeulike-article-id = {300228},
citeulike-linkout-0 = {http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20&path=ASIN/0412246201},
citeulike-linkout-1 = {http://www.amazon.de/exec/obidos/redirect?tag=citeulike01-21&path=ASIN/0412246201},
citeulike-linkout-2 = {http://www.amazon.fr/exec/obidos/redirect?tag=citeulike06-21&path=ASIN/0412246201},
citeulike-linkout-3 = {http://www.amazon.jp/exec/obidos/ASIN/0412246201},
citeulike-linkout-4 = {http://www.amazon.co.uk/exec/obidos/ASIN/0412246201/citeulike00-21},
citeulike-linkout-5 = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/0412246201},
citeulike-linkout-6 = {http://www.worldcat.org/isbn/0412246201},
citeulike-linkout-7 = {http://books.google.com/books?vid=ISBN0412246201},
citeulike-linkout-8 = {http://www.amazon.com/gp/search?keywords=0412246201&index=books&linkCode=qs},
citeulike-linkout-9 = {http://www.librarything.com/isbn/0412246201},
howpublished = {Hardcover},
isbn = {0412246201},
keywords = {density-estimation},
month = {April},
posted-at = {2008-01-13 17:43:25},
priority = {2},
publisher = {{Chapman \& Hall/CRC}},
title = {Density Estimation for Statistics and Data Analysis},
url = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/0412246201},
year = {1986}
}
@article{Par02,
abstract = {Mutual information is a good indicator of relevance between variables, and have been used as a measure in several feature selection algorithms. However, calculating the mutual information is difficult, and the performance of a feature selection algorithm depends on the accuracy of the mutual information. In this paper, we propose a new method of calculating mutual information between input and class variables based on the Parzen window, and we apply this to a feature selection algorithm for classification problems.},
author = {Kwak, N. and Choi, Chong-Ho},
booktitle = {Pattern Analysis and Machine Intelligence, IEEE Transactions on},
citeulike-article-id = {2600131},
citeulike-linkout-0 = {http://doi.ieeecomputersociety.org/10.1109/TPAMI.2002.1114861},
citeulike-linkout-1 = {http://dx.doi.org/10.1109/TPAMI.2002.1114861},
citeulike-linkout-2 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1114861},
doi = {10.1109/TPAMI.2002.1114861},
journal = {Pattern Analysis and Machine Intelligence, IEEE Transactions on},
keywords = {feature-selection, mutual-information},
number = {12},
pages = {1667--1671},
posted-at = {2008-06-03 19:07:49},
priority = {2},
title = {Input feature selection by mutual information based on Parzen window},
url = {http://dx.doi.org/10.1109/TPAMI.2002.1114861},
volume = {24},
year = {2002}
}
@ARTICLE{Moo95,
author = {{Moon}, Y.-I. and {Rajagopalan}, B. and {Lall}, U.},
title = "{Estimation of mutual information using kernel density estimators}",
journal = {Phys. Rev. E},
year = 1995,
month = sep,
volume = 52,
pages = {2318-2321},
doi = {10.1103/PhysRevE.52.2318},
adsurl = {http://adsabs.harvard.edu/abs/1995PhRvE..52.2318M},
adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}
@book{Jen07,
author = {Jensen, F.V. and Nielsen, T.D.},
citeulike-article-id = {2354839},
keywords = {bibtex-import},
posted-at = {2008-02-08 21:20:57},
priority = {2},
publisher = {Springer},
title = {Bayesian Networks and Decision Graphs (2nd ed.)},
year = {2007}
}
@misc{Sch02,
abstract = {We discuss algorithms for estimating the Shannon entropy h of finite symbol
sequences with long range correlations. In particular, we consider algorithms
which estimate h from the code lengths produced by some compression algorithm.
Our interest is in describing their convergence with sequence length, assuming
no limits for the space and time complexities of the compression algorithms. A
scaling law is proposed for extrapolation from finite sample lengths. This is
applied to sequences of dynamical systems in non-trivial chaotic regimes, a 1-D
cellular automaton, and to written English texts.},
archivePrefix = {arXiv},
author = {Sch\"urmann, T. and Grassberger, P.},
citeulike-article-id = {2194681},
citeulike-linkout-0 = {http://arxiv.org/abs/cond-mat/0203436},
citeulike-linkout-1 = {http://arxiv.org/pdf/cond-mat/0203436},
eprint = {cond-mat/0203436},
keywords = {entropy, information, markov},
posted-at = {2008-01-04 14:45:44},
priority = {2},
title = {Entropy estimation of symbol sequences},
url = {http://arxiv.org/abs/cond-mat/0203436},
year = {2002}
}
@article{Kri81,
author = {Krichevsky, R. and Trofimov, V.},
citeulike-article-id = {1615347},
journal = {IEEE Trans. Inform. Theory},
keywords = {bibtex-import},
pages = {199--207},
posted-at = {2007-09-03 04:57:48},
priority = {2},
title = {The performance of universal coding},
volume = {27},
year = {1981}
}
@article{But00a,
address = {Children's Hospital Informatics Program and Division of Endocrinology, Department of Medicine, Children's Hospital, 300 Longwood Avenue, Boston, MA 02115, USA. atul\_butte@harvard.edu},
author = {Butte, A.J. and Tamayo, P. and Slonim, D. and Golub, T.R. and Kohane, I.S.},
citeulike-article-id = {577105},
citeulike-linkout-0 = {http://dx.doi.org/10.1073/pnas.220392197},
citeulike-linkout-1 = {http://www.pnas.org/content/97/22/12182.abstract},
citeulike-linkout-2 = {http://www.pnas.org/content/97/22/12182.full.pdf},
citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/11027309},
citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=11027309},
doi = {10.1073/pnas.220392197},
issn = {0027-8424},
journal = {Proc Natl Acad Sci U S A},
keywords = {genetics, networks},
month = {October},
number = {22},
pages = {12182--12186},
posted-at = {2008-10-08 18:01:20},
priority = {2},
title = {Discovering functional relationships between RNA expression and chemotherapeutic susceptibility using relevance networks.},
url = {http://dx.doi.org/10.1073/pnas.220392197},
volume = {97},
year = {2000}
}
@misc{ PROMO08,
author = "Causality workbench team",
title = "{PROMO}: Simple causal effects in time series",
year = 2008,
month = August,
url = "http://www.zurich.ibm.com/~jep/causality/promo.html",
institution = "Causality workbench repository" }
@article{Opg07,
abstract = {BACKGROUND:The use of correlation networks is widespread in the analysis of gene expression and proteomics data, even though it is known that correlations not only confound direct and indirect associations but also provide no means to distinguish between cause and effect. For 'causal' analysis typically the inference of a directed graphical model is required. However, this is rather difficult due to the curse of dimensionality.RESULTS:We propose a simple heuristic for the statistical learning of a high-dimensional 'causal' network. The method first converts a correlation network into a partial correlation graph. Subsequently, a partial ordering of the nodes is established by multiple testing of the log-ratio of standardized partial variances. This allows identifying a directed acyclic causal network as a subgraph of the partial correlation network. We illustrate the approach by analyzing a large Arabidopsis thaliana expression data set. CONCLUSIONS:The proposed approach is a heuristic algorithm that is based on a number of approximations, such as substituting lower order partial correlations by full order partial correlations. Nevertheless, for small samples and for sparse networks the algorithm not only yields sensible first order approximations of the causal structure in high-dimensional genomic data but is also computationally highly efficient. Availability and requirements: The method is implemented in the GeneNet R package (version 1.2.0), available from CRAN and from http://strimmerlab.org/software/genets/. The software includes an R script for reproducing the network analysis of the Arabidopsis thaliana data.},
author = {Opgen-Rhein, R. and Strimmer, K.},
citeulike-article-id = {1538332},
citeulike-linkout-0 = {http://dx.doi.org/10.1186/1752-0509-1-37},
citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/17683609},
citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=17683609},
doi = {10.1186/1752-0509-1-37},
journal = {BMC Systems Biology},
keywords = {bioinformatics, correlation, genenet, networks, statistics},
number = {1},
posted-at = {2009-01-17 19:47:27},
priority = {5},
title = {From correlation to causation networks: a simple approximate learning algorithm and its application to high-dimensional plant gene expression data},
url = {http://dx.doi.org/10.1186/1752-0509-1-37},
volume = {1},
year = {2007}
}
@article{Cas06,
address = {Cambridge, MA, USA},
author = {Castelo, R. and Roverato, A.},
citeulike-article-id = {2098145},
citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1248547.1248641},
issn = {1533-7928},
journal = {J. Mach. Learn. Res.},
keywords = {grn, network\_inference},
pages = {2621--2650},
posted-at = {2007-12-12 12:07:24},
priority = {3},
publisher = {MIT Press},
title = {A Robust Procedure For Gaussian Graphical Model Search From Microarray Data With p Larger Than n},
url = {http://portal.acm.org/citation.cfm?id=1248547.1248641},
volume = {7},
year = {2006}
}
@article{Bro09,
abstract = {We address the problem of improving the reliability of independence-based causal discovery algorithms that results from the execution of statistical independence tests on small data sets, which typically have low reliability. We model the problem as a knowledge base containing a set of independence facts that are related through Pearl's well-known axioms. Statistical tests on finite data sets may result in errors in these tests and inconsistencies in the knowledge base. We resolve these inconsistencies through the use of an instance of the class of defeasible logics called argumentation, augmented with a preference function, that is used to reason about and possibly correct errors in these tests. This results in a more robust conditional independence test, called an argumentative independence test. Our experimental evaluation shows clear positive improvements in the accuracy of argumentative over purely statistical tests. We also demonstrate significant improvements on the accuracy of causal structure discovery from the outcomes of independence tests both on sampled data from randomly generated causal models and on real-world data sets.},
author = {Bromberg, F. and Margaritis, D.},
citeulike-article-id = {4129060},
citeulike-linkout-0 = {http://www.jmlr.org/papers/volume10/bromberg09a/bromberg09a.pdf},
journal = {Journal of Machine Learning Research},
keywords = {argumentation, casual-discovery, sample-size},
month = {February},
pages = {301--340},
posted-at = {2009-03-03 20:08:37},
priority = {2},
title = {Improving the Reliability of Causal Discovery from Small Data Sets Using Argumentation},
url = {http://www.jmlr.org/papers/volume10/bromberg09a/bromberg09a.pdf},
volume = {10},
year = {2009}
}
@TECHREPORT{Chi94,
author = {D. Chickering and D. Geiger and D. Heckerman},
title = {Learning Bayesian Networks is {NP}-Hard},
institution = {Microsoft Research},
year = {1994}
}
@article{Mil55,
title={Information theory in Psychology: Problems and Methods},
author={G.A. Miller},
journal={Free Press},
volume={},
year={1955}
}
@article{Nem02,
abstract = {We study properties of popular near-uniform (Dirichlet) priors for learning
undersampled probability distributions on discrete nonmetric spaces and show
that they lead to disastrous results. However, an Occam-style phase space
argument expands the priors into their infinite mixture and resolves most of
the observed problems. This leads to a surprisingly good estimator of entropies
of discrete distributions.},
journal={arXiv},
archivePrefix = {arXiv},
author = {Nemenman, I. and Shafee, F. and Bialek, W.},
citeulike-article-id = {3816193},
citeulike-linkout-0 = {http://arxiv.org/abs/physics/0108025},
citeulike-linkout-1 = {http://arxiv.org/pdf/physics/0108025},
eprint = {physics/0108025},
keywords = {entropy, information, mutual},
month = {Jan},
posted-at = {2008-12-21 22:18:51},
priority = {2},
title = {Entropy and inference, revisited},
url = {http://arxiv.org/abs/physics/0108025},
volume={},
year = {2002}
}
@article{Mee95a,
abstract = {This paper presents correct algorithms for answering the following two questions; (i) Does there exist a causal explanation consistent with a set of background knowledge which explains all of the observed independence facts in a sample? (ii) Given that there is such a causal explanation what are the causal relationships common to every such causal explanation?},
address = {San Francisco, CA, USA},
author = {Meek, C.},
journal = {Proceedings of the 11th Annual Conference on Uncertainty in Artificial Intelligence (UAI-95)},
citeulike-article-id = {2984965},
citeulike-linkout-0 = {http://209.85.135.104/search?q=cache:j5dLlVq9OmAJ:ftp.andrew.cmu.edu/pub/phil/chris/causal.ps+meek+Causal+inference+and+causal+explanation+with+background+knowledge&hl=de&ct=clnk&cd=1&gl=de},
editor = {Besnard, Philippe and Hanks, Steve},
keywords = {bayesian\_network, causality, dag},
location = {Montreal, QU},
month = {August},
pages = {403--441},
posted-at = {2008-07-10 13:50:54},
priority = {2},
publisher = {Morgan Kaufmann},
title = {Causal Inference and Causal Explanation with Background Knowledge},
url = {http://209.85.135.104/search?q=cache:j5dLlVq9OmAJ:ftp.andrew.cmu.edu/pub/phil/chris/causal.ps+meek+Causal+inference+and+causal+explanation+with+background+knowledge&hl=de&ct=clnk&cd=1&gl=de},
year = {1995}
}
@article{Sun05,
author={E. Sungur},
title={A Note on Directional Dependence in Regression Setting},
journal={Communications in Statistics - Theory and Methods},
year={2006},
vol={34}
}
@article{Hyv99,
abstract = {A common problem encountered in such disciplines as statistics, data analysis, signal processing, and neural network research, is finding a suitable representation of multivariate data. For computational and conceptual simplicity, such a representation is often sought as a linear transformation of the original data. Well-known linear transformation methods include, for example, principal component analysis, factor analysis, and projection pursuit. A recently developed linear transformation...},
author = {Hyv\"arinen, A.},
citeulike-article-id = {802359},
citeulike-linkout-0 = {http://citeseer.ist.psu.edu/hyv99survey.html},
citeulike-linkout-1 = {http://citeseer.lcs.mit.edu/hyv99survey.html},
citeulike-linkout-2 = {http://citeseer.ifi.unizh.ch/hyv99survey.html},
citeulike-linkout-3 = {http://citeseer.comp.nus.edu.sg/hyv99survey.html},
journal = {Neural Computing Surveys},
keywords = {independent-component-analysis},
pages = {94--128},
posted-at = {2008-05-23 12:16:13},
priority = {3},
title = {Survey on independent component analysis},
url = {http://citeseer.ist.psu.edu/hyv99survey.html},
volume = {2},
year = {1999}
}
@ARTICLE{Shi06,
author = {S. Shimizu and P.O. Hoyer and A. Hyv\"arinen and A. Kerminen},
title = {A Linear Non-Gaussian Acyclic Model for Causal Discovery},
journal = {Journal of Machine Learning Research},
year = {2006},
volume = {7},
pages = {2003--2030}
}
@article{Spi05,
author = {P. Spirtes},
citeulike-article-id = {125039},
citeulike-linkout-0 = {http://dx.doi.org/10.1080/1350178042000330887},
citeulike-linkout-1 = {http://www.ingentaconnect.com/content/routledg/rjec/2005/00000012/00000001/art00002},
doi = {10.1080/1350178042000330887},
issn = {1350-178X},
journal = {Journal of Economic Methodology},
keywords = {bayesian, econometrics, graphical, model, network},
month = {March},
number = {1},
pages = {3--34},
posted-at = {2007-07-25 04:25:19},
priority = {2},
publisher = {Routledge, part of the Taylor \& Francis Group},
title = {Graphical models, causal inference, and econometric models},
url = {http://dx.doi.org/10.1080/1350178042000330887},
volume = {12},
year = {2005}
}
@INPROCEEDINGS{Mar99,
author = {D. Margaritis and S. Thrun},
title = {Bayesian Network Induction via Local Neighborhoods},
booktitle = {Advances in Neural Information Processing Systems 12},
year = {1999},
pages = {505--511},
publisher = {MIT Press}
}
@Article{Kim08,
author = {J.-M. Kim and Y.-S. Jung and E.A. Sungur and K.-H. Han and C. Park and I. Sohn},
title = {A copula method for modeling directional dependence of genes.},
journal = {BMC Bioinformatics},
year = {2008},
volume = {9},
pages = {225},
pmid = {18447957},
}
@article{Zha09,
title={Distinguishing causes from effects using nonlinear acyclic causal models},
author={K. Zhang and A. Hyv‰rinen},
journal={{JMLR} Workshop and Conference Proceedings},
year={ 2009}
}
@inproceedings{Hoy06,
author = {P.O. Hoyer and S. Shimizu and A. Hyv‰rinen and Y. Kano and A.J. Kerminen},
booktitle = {ICA},
crossref = {conf/ica/2006},
editor = {Justinian P. Rosca and Deniz Erdogmus and JosÈ Carlos PrÌncipe and Simon Haykin},
interHash = {a725f1cbcf3da1519fe06075fa41c468},
intraHash = {9e13ace08b94847277c5848e45d9584b},
pages = {115-122},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
title = {New Permutation Algorithms for Causal Discovery Using ICA.},
url = {http://dblp.uni-trier.de/db/conf/ica/ica2006.html#HoyerSHKK06},
volume = {3889},
year = {2006},
ee = {http://dx.doi.org/10.1007/11679363_15},
isbn = {3-540-32630-8},
date = {2006-03-01}
}
@article{Zha08,
author = {Zhang, J. and Spirtes, P.},
title = {Detection of Unfaithfulness and Robust Causal Inference},
journal = {Minds Mach.},
volume = {18},
number = {2},
year = {2008},
issn = {0924-6495},
pages = {239--271},
doi = {http://dx.doi.org/10.1007/s11023-008-9096-4},
publisher = {Kluwer Academic Publishers},
address = {Hingham, MA, USA},
}
@ARTICLE{Chi02a,
author = {D.M. Chickering and C. Boutilier},
title = {Optimal structure identification with greedy search},
journal = {Journal of Machine Learning Research},
year = {2002},
volume = {3},
pages = {507--554}
}
@TechReport{Chi02,
author = {D.M. Chickering and C. Meek},
title = {Finding Optimal Bayesian Networks},
institution = {Microsoft Research},
year = 2002,
number = {MSR-TR-2002-42},
}
@book{Ken99,
abstract = {This new edition of the classic statistical book Classical Inference and
Relationship completes the current three-volume set of Kendall's Advanced
Theory of Statistics. It has been fully revised and expanded to over 800
pages, representing the state of the art in classical statistical inference.},
author = {Kendall, M. and Stuart, A. and Ord, K.J. and Arnold, S.},
citeulike-article-id = {3561755},
edition = {6},
howpublished = {Hardcover},
isbn = {0340662301},
keywords = {statistical\_theory},
month = {April},
posted-at = {2008-11-17 21:24:08},
priority = {2},
publisher = {A Hodder Arnold Publication},
title = {Kendall's Advanced Theory of Statistics:Volume 2A -Classical Inference and and the Linear Model (Kendall's Library of Statistics)},
url = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/0340662301},
year = {1999}
}
@PhDThesis{Mee97,
Author="C. Meek",
School="Carnegie Mellon University",
Title="Graphical models: selecting causal and statistical models",
Year="1997",
Address="Pittsburgh, PA"
}
@inproceedings{Doj06,
title = {Learning Bayesian Networks Does Not Have to Be NP-Hard.},
author = {N. Dojer},
booktitle = {MFCS},
editor = {Rastislav Kralovic and Pawel Urzyczyn},
pages = {305-314},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
volume = 4162,
year = 2006,
url = {http://dblp.uni-trier.de/db/conf/mfcs/mfcs2006.html#Dojer06},
description = {dblp},
biburl = {http://www.bibsonomy.org/bibtex/20350af6c716fd2f4d5a0f236fa4d6058/dblp},
keywords = {dblp},
ee = {http://dx.doi.org/10.1007/11821069_27}, isbn = {3-540-37791-3}, date = {2006-11-22}}
@ARTICLE{Lam94,
author = {W. Lam and F. Bacchus},
title = {Learning Bayesian Belief Networks An approach based on the MDL Principle},
journal = {Computational Intelligence},
year = {1994},
volume = {10},
pages = {269--293}
}
@inproceedings{Fri98,
author = {Friedman, N. },
booktitle = {{UAI}},
citeulike-article-id = {1782908},
keywords = {bayesian, bibtex-import, nets, search, structure},
posted-at = {2007-10-18 07:01:33},
priority = {2},
title = {{The Bayesian Structural EM Algorithm}},
url = {{citeseer.ist.psu.edu/article/friedman98bayesian.html}},
year= {1998}
}
@misc{Coo97,
author = {Cooper, G. and Heckerman, D. and Meek, C. },
citeulike-article-id = {838878},
keywords = {bayesian, causality},
month = {February},
posted-at = {2009-03-02 01:39:47},
priority = {2},
title = {{A Bayesian Approach to Causal Discovery}},
year = {1997}
}
@Article{Hec95b,
author = {D. Heckerman and D. Geiger and D.M. Chickering},
title = {Learning {Bayesian} Networks: The Combination of
Knowledge and Statistical Data},
journal = {Machine Learning},
year = 1995,
volume = 20,
pages = {197-243}
}
@inproceedings{Chi95,
author= {D.M. Chickering},
title = {A Transformational Characterization of Equivalent
{Bayesian} Network Structures},
year = 1995,
Booktitle = {Proceedings of Eleventh Conference on Uncertainty in
Artificial Intelligence, {Montreal, QU}},
publisher = {Morgan Kaufmann},
Month = {August},
editors = {S. Hanks and P. Besnard},
pages = {87-98},
}
@ARTICLE{Fri00,
author = {N. Friedman and M. Linial and I. Nachman and D. Pe'er},
title = {Using Bayesian Networks to Analyze Expression Data},
journal = {Journal of Computational Biology},
year = {2000},
volume = {7},
pages = {601--620}
}
@book{Nea03,
author = {Neapolitan, R.E. },
citeulike-article-id = {106361},
howpublished = {Hardcover},
isbn = {0130125342},
keywords = {bayesian, book, dt, lib-hut, loan},
month = {April},
posted-at = {2005-12-29 17:15:09},
priority = {2},
publisher = {Prentice Hall},
title = {Learning Bayesian Networks},
url = {http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20\&path=ASIN/0130125342},
year = {2003}
}
@article{Zha05,
abstract = {In recent years, a few researchers have challenged past dogma and suggested methods (such as the IC algorithm) for inferring causal relationship among variables using steady state observations. In this paper, we present a modified IC (mIC) algorithm that uses entropy to test conditional independence and combines the steady state data with partial prior knowledge of topological ordering in gene regulatory network, for jointly learning the causal relationship among genes. We evaluate our mIC algorithm using the simulated data. The results show that the precision and recall rates are significantly improved compared with using IC algorithm. Finally, we apply the mIC algorithm to microarray data for melanoma. The algorithm identified the important causal relations associated with WNT5A, a gene playing an important role in melanoma, verified by the literatures.},
author = {Zhang, X. and Baral, C. and Kim, S. },
citeulike-article-id = {3463621},
doi = {10.1007/11527770\_69},
journal = {Artificial Intelligence in Medicine},
keywords = {causal},
pages = {524--534},
posted-at = {2009-03-02 20:48:29},
priority = {2},
title = {An Algorithm to Learn Causal Relations Between Genes from Steady State Data: Simulation and Its Application to Melanoma Dataset},
url = {http://dx.doi.org/10.1007/11527770\_69},
year = {2005},
booktitle = {An Algorithm to Learn Causal Relations Between Genes from Steady State Data: Simulation and Its Application to Melanoma Dataset},
publisher = {None}
}
@book{Guy06,
author = {Guyon, I. and Gunn, S. and Nikravesh, M. and Zadeh, L.A.},
title = {Feature Extraction: Foundations and Applications (Studies in Fuzziness and Soft Computing)},
year = {2006},
isbn = {3540354875},
publisher = {Springer-Verlag New York, Inc.},
address = {Secaucus, NJ, USA},
}
@inproceedings{Cow01,
author = {Cowell, R.G.},
title = {Conditions Under Which Conditional Independence and Scoring Methods Lead to Identical Selection of Bayesian Network Models},
booktitle = {UAI '01: Proceedings of the 17th Conference in Uncertainty in Artificial Intelligence},
year = {2001},
isbn = {1-55860-800-1},
pages = {91--97},
publisher = {Morgan Kaufmann Publishers Inc.},
address = {San Francisco, CA, USA},
}
@INPROCEEDINGS{Yan03,
author = {Y. Yang and G.I. Webb},
title = {On Why Discretization Works for Naive-Bayes Classifiers},
booktitle = {Proceedings of the 16th Australian Joint Conference on Artificial Intelligence (AI},
year = {2003},
pages = {440--452}
}
@inproceedings{Dou95,
abstract = {Many supervised machine learning algorithms require a discrete feature space. In this paper, we review previous work on continuous feature discretization, identify defining characteristics of the methods, and conduct an empirical evaluation of several methods. We compare binning, an unsupervised discretization method, to entropy-based and purity-based methods, which are supervised algorithms. We found that the performance of the Naive-Bayes algorithm significantly improved when features were...},
author = {Dougherty, J. and Kohavi, R. and Sahami, M. },
booktitle = {International Conference on Machine Learning},
pages = {194--202},
priority = {2},
title = {Supervised and Unsupervised Discretization of Continuous Features},
url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.47.6141},
year = {1995}
}
@book{Hay94,
address = {New York},
author = {Haykin, S. },
citeulike-article-id = {2429223},
keywords = {neural\_nets},
posted-at = {2008-02-26 12:33:02},
priority = {2},
publisher = {Macmillan},
title = {Neural Networks: A Comprehensive Foundation},
year = {1994}
}
@incollection{Zha05,
abstract = {In recent years, a few researchers have challenged past dogma and suggested methods (such as the IC algorithm) for inferring causal relationship among variables using steady state observations. In this paper, we present a modified IC (mIC) algorithm that uses entropy to test conditional independence and combines the steady state data with partial prior knowledge of topological ordering in gene regulatory network, for jointly learning the causal relationship among genes. We evaluate our mIC algorithm using the simulated data. The results show that the precision and recall rates are significantly improved compared with using IC algorithm. Finally, we apply the mIC algorithm to microarray data for melanoma. The algorithm identified the important causal relations associated with WNT5A, a gene playing an important role in melanoma, verified by the literatures.},
author = {Zhang, Xin and Baral, Chitta and Kim, Seungchan},
citeulike-article-id = {3463621},
citeulike-linkout-0 = {http://dx.doi.org/10.1007/11527770_69},
citeulike-linkout-1 = {http://www.springerlink.com/content/079j38egmdlh31an},
doi = {10.1007/11527770_69},
journal = {Artificial Intelligence in Medicine},
keywords = {causality, expression, gene, network},
pages = {524--534},
posted-at = {2009-07-09 06:28:19},
priority = {2},
title = {An Algorithm to Learn Causal Relations Between Genes from Steady State Data: Simulation and Its Application to Melanoma Dataset},
url = {http://dx.doi.org/10.1007/11527770_69},
year = {2005},
booktitle = {None},
publisher = {None}
}
@incollection{Mee95,
Booktitle={Proceedings of Eleventh Conference on Uncertainty in
Artificial Intelligence, {Montreal, QU}},
publisher={M. Kaufmann},
Month={August},
year={1995},
author={C. Meek},
title={Strong completeness and faithfulness in {B}ayesian networks},
pages={411-418}
}
@article{Guy07,
author = {I. Guyon and C. Aliferis and A. Elisseeff},
title = {Causal feature selection},
year = {2007},
journal={Computational Methods of Feature Selection}
}
@article{Gen89,
author={J. H. Gennari and P. Langley and D. Fisher},
title={Models of incremental concept formation},
journal={Journal of Artificial Intelligence},
year={1989},
volume={40},
pages={11-61},
url={http://www.isrl.uiuc.edu/~amag/langev/paper/gennari89modelsOf.html}
}
@INPROCEEDINGS{Alm91,
author = {H. Almuallim and T.G. Dietterich},
title = {Learning With Many Irrelevant Features},
booktitle = {In Proceedings of the Ninth National Conference on Artificial Intelligence},
year = {1991},
pages = {547--552},
publisher = {AAAI Press}
}
@TECHREPORT{Car94,
author = {R.Caruana and D. Freitag},
title = {How Useful Is Relevance?},
institution = {In: Relevance, Papers from the 1994 AAAI Fall Symposium},
year = {1994}
}
@ARTICLE{Blu97,
author = {A.L. Blum and P. Langley},
title = {Selection of Relevant Features and Examples in Machine Learning},
journal = {Artificial Intelligence},
year = {1997},
volume = {97},
pages = {245--271}
}
@MISC{Koh97,
author = {R. Kohavi and G.H. John},
title = {Wrappers for Feature Subset Selection},
year = {1997}
}
@incollection{Kor08,
author = {K.B. Korb and A.E. Nicholson},
booktitle = {Innovations in Bayesian Networks},
interHash = {49efa842631af97b0da00281446d57f4},
intraHash = {0fec77e8eeefca89674e95da9b5f010c},
pages = {83-116},
publisher = {Springer},
series = {Studies in Computational Intelligence},
title = {The Causal Interpretation of Bayesian Networks.},
url = {http://dblp.uni-trier.de/db/series/sci/sci156.html#KorbN08},
volume = {156},
year = {2008},
ee = {http://dx.doi.org/10.1007/978-3-540-85066-3_4},
isbn = {978-3-540-85065-6},
date = {2008-11-24}
}
@ARTICLE{Hec95a,
author = {D. Heckerman and R. Shachter},
title = {Decision-Theoretic Foundations for Causal Reasoning},
journal = {Journal of Artificial Intelligence Research},
year = {1995},
volume = {3},
pages = {405--430}
}
@INPROCEEDINGS{Sch97,
author = {R. Scheines},
title = {An Introduction to Causal Inference},
booktitle = {Causality in Crisis?},
year = {1997},
pages = {185--200},
publisher = {University of Notre Dame Press}
}
@Article{Man04,
AUTHOR = {Mani, S. and Cooper, G.F},
title = {Causal discovery using a Bayesian local causal discovery algorithm.},
journal = {Stud Health Technol Inform},
VOLUME = {107},
YEAR = {2004},
NUMBER = {Pt 1},
PAGES = {731-5},
URL = {http://www.biomedsearch.com/nih/Causal-discovery-using-Bayesian-local/15360909.html},
PubMedID = {15360909},
ISSN = {0926-9630},
}
@inproceedings{Ver91,
author = {Verma,, T. and Pearl,, J.},
title = {Equivalence and synthesis of causal models},
booktitle = {UAI '90: Proceedings of the Sixth Annual Conference on Uncertainty in Artificial Intelligence},
year = {1991},
isbn = {0-444-89264-8},
pages = {255--270},
publisher = {Elsevier Science Inc.},
address = {New York, NY, USA},
}
@INPROCEEDINGS{Tsa03b,
author = {I. Tsamardinos and C. Aliferis},
title = {Towards Principled Feature Selection: Relevancy, Filters and Wrappers},
booktitle = {Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics},
year = {2003},
publisher = {Morgan Kaufmann Publishers}
}
@INPROCEEDINGS{Tsa03a,
author = {I. Tsamardinos and C. Aliferis and A.R. Statnikov},
title = {Algorithms for Large Scale Markov Blanket Discovery},
booktitle = {The 16th International FLAIRS Conference, St},
year = {2003},
pages = {376--380},
publisher = {AAAI Press}
}
@INPROCEEDINGS{Tsa03,
author = {I. Tsamardinos and C. Aliferis and A. Statnikov},
title = {Time and Sample Efficient Discovery of Markov Blankets And Direct Causal Relations},
booktitle = {Proceedings of the 9th CAN SIGKDD International Conference on Knowledge Discovery and Data Mining},
year = {2003},
pages = {673--678}
}
@MISC{Ali03,
author = {C. Aliferis and I. Tsamardinos and A. Statnikov and C.F. Aliferis M. D and Ph. D and I. Tsamardinos Ph. D},
title = {HITON, A Novel Markov Blanket Algorithm for Optimal Variable Selection},
year = {2003}
}
@TECHREPORT{Bro08,
author = {Brown L.E. and Tsamardinos I.},
title = {Markov Blanket-Based Variable Selection in Feature Space},
institution = {DSL TR-08-01},
year = {2008}
}
@article{Hol86,
abstract = {Problems involving causal inference have dogged at the heels of statistics since its earliest days. Correlation does not imply causation, and yet causal conclusions drawn from a carefully designed experiment are often valid. What can a statistical model say about causation? This question is addressed by using a particular model for causal inference (Holland and Rubin 1983; Rubin 1974) to critique the discussions of other writers on causation and causal inference. These include selected philosophers, medical researchers, statisticians, econometricians, and proponents of causal modeling.},
author = {Holland, P.W. },
citeulike-article-id = {1528727},
doi = {10.2307/2289064},
journal = {Journal of the American Statistical Association},
keywords = {causal},
number = {396},
pages = {945--960},
posted-at = {2009-02-12 15:13:48},
priority = {0},
title = {Statistics and Causal Inference},
url = {http://dx.doi.org/10.2307/2289064},
volume = {81},
year = {1986}
}
@article{Buck04,
title={Chip-chip: considerations for the design, analysis, and application of genome-wide chromatin immunoprecipitation experiments.},
author={M.J. Buck and J.D. Lieb},
year={2004},
journal={Genomics},
volume={83}
}
@article{Chu98,
title={The Transcriptional Program of Sporulation in Budding Yeast},
author={S. Chu and J.L. DeRisi and M. Eisen and J. Mulholland and D. Botstein and P.O. Brown and I. Herskowitz},
year={1998},
journal={Science},
volume={282}
}
@book{Cov90,
Author = {T.M. Cover and J.A. Thomas},
Publisher = {John Wiley \& Sons},
Title = {Elements of Information Theory},
Year = {1990}}
@article{Syn,
abstract = {BACKGROUND: The development of algorithms to infer the structure of gene regulatory networks based on expression data is an important subject in bioinformatics research. Validation of these algorithms requires benchmark data sets for which the underlying network is known. Since experimental data sets of the appropriate size and design are usually not available, there is a clear need to generate well-characterized synthetic data sets that allow thorough testing of learning algorithms in a fast and reproducible manner. RESULTS: In this paper we describe a network generator that creates synthetic transcriptional regulatory networks and produces simulated gene expression data that approximates experimental data. Network topologies are generated by selecting subnetworks from previously described regulatory networks. Interaction kinetics are modeled by equations based on Michaelis-Menten and Hill kinetics. Our results show that the statistical properties of these topologies more closely approximate those of genuine biological networks than do those of different types of random graph models. Several user-definable parameters adjust the complexity of the resulting data set with respect to the structure learning algorithms. CONCLUSION: This network generation technique offers a valid alternative to existing methods. The topological characteristics of the generated networks more closely resemble the characteristics of real transcriptional networks. Simulation of the network scales well to large networks. The generator models different types of biological interactions and produces biologically plausible synthetic gene expression data.},
address = {ESAT-SCD, KU Leuven, Kasteelpark Arenberg 10, B-3001 Heverlee, Belgium. tim.vandenbulcke@esat.kuleuven.be},
author = {Van den Bulcke, T. and Van Leemput, K. and Naudts, B. and van Remortel, P. and Ma, H. and Verschoren, A. and De Moor, B. and Marchal, K. },
citeulike-article-id = {590235},
doi = {10.1186/1471-2105-7-43},
issn = {1471-2105},
journal = {BMC Bioinformatics},
keywords = {artificial, data, expression, gene, inference, learning, network, structure, synthetic},
posted-at = {2006-10-31 09:58:23},
priority = {0},
title = {SynTReN: a generator of synthetic gene expression data for design and analysis of structure learning algorithms.},
url = {http://dx.doi.org/10.1186/1471-2105-7-43},
volume = {7},
year = {2006}
}
@article{DeRi97,
title={Exploring the metabolic and genetic control of gene expression on a genomic scale},
author={J.L. DeRisi and V.R. Iyer and P.O. Brown},
year={1997},
journal={Science},
volume={278(5338)}
}
@article{Din05,
title={Minimum redundancy feature selection from microarray gene expression data},
author={C. Ding and H. Peng},
year={2005},
journal={Journal of Bioinformatics and Computational Biology},
volume={3},
pages = {185-205}
}
@article{Fai07,
Author = {J.J. Faith and B. Hayete and J.T. Thaden et al},
Journal = {PLoS Biology},
Title = {Large-scale mapping and validation of Escherichia coli transcriptional regulation from a compendium of expression profiles},
Volume = {5},
Year = {2007}}
@article{Fere99,
title={Systematic changes in gene expression pattern following adaptive evolution in yeast.},
author={T.L. Ferea and D. Botstein and P.O. Brown and R.F. Rosenzweig},
year={1999},
journal={Proc.Natl.Acad.Sci.},
volume={96}
}
@article{Gar05,
title={Reverse-engineering transcription control networks},
author={T.S. Gardner and J. Faith},
year={2005},
journal={Physics of Life Reviews},
volume={2},
pages = {65-88}
}
@article{Gasc01,
title={Genomic expression responses to DNA-damaging agents and the regulatory role of the yeast ATR homolog Mec1p.},
author={A.P. Gasch and M. Huang and S. Metzner and D.Botstein and S.J. Elledge and P.O. Brown},
year={2001},
journal={Mol.Biol.Cell},
volume={12}
}
@article{Gasc00,
title={Genomic Expression Programs in the Respomse of Yeast Cells to Environmental Changes},
author={A.P. Gasch and P.T. Spellman and C.M. Kao and O. Carmel-Harel and M-B- Eisen and G. Storz and D. Botstein and P.O. Brown},
year={2000},
journal={Mol.Biol.Cell},
volume={11}
}
@article{God07,
title={Effect of 21 Different Nitrogen Sources on Global Gene Expression in the Yeast Saccharomyces cerevisiae},
author={P. Godard and A. Urrestarazu and S. Vissers and K. Kontos and G. Bontempi and J. van Helden and B. Andr{\'e}},
year={2007},
journal={Molecular and Cellular Biology},
volume={27},
pages = {3065-3086}
}
@article{Harb04,
title={Transcriptional regulatory code of a eukaryotic genome.},
author={C.T. Harbison and D.B. Gordon and T.I. Lee and N.J. Rinaldi and K.D. Macisaac and T.W. Danford and N.M. Hannett and J.-B. Tagne and D.B. Reynlds and J. Yoo and E.G. Jennings and J. Zeitlinger and D.K. Pokholok and M. Kellis and P.A. Rolfe and K.T. Takusagawa and E.S. Lander and D.K. Gifford and E. Fraenkel and R.A. Young},
year={2004},
journal={Nature}
}
@MASTERSTHESIS{Hau06,
Author = {J. Hausser},
Month = {August},
school={D\'ept Biosciences and B\^atiment Louis Pasteur and Avenue Jean Capelle and F- Villeurbanne Cedex},
Title = {Improving Entropy Estimation and the Inference of Genetic Regulatory Networks},
Year = {2006}}
@book{haykin99,
Author = {S. Haykin},
Date-Added = {2008-03-14 15:01:05 +0100},
Date-Modified = {2008-03-14 15:01:05 +0100},
Publisher = {Prentice Hall International},
Title = {Neural Networks: A Comprehensive Foundation},
Year = {1999}}
@article{Hugh00,
title={Functional discovery via a compendium of expression profiles.},
author={T.R. Hughes and M.J. Marton and A.R. Jones and C.J. Roberts and R. Stoughton and C.D. Armour and H.A. Bennett and E. Coffey and H. Dai and Y.D. He and M.J. Kidd and A.M. King and M.R. Meaer and D. Slade and P.Y. Lum and S.B. Stepaniants and D.D. Shoemaker and D. Gachotte and K. Chakraburtty and J. Simon and M. Bard and S.H. Friend.},
year={2000},
journal={Cell},
volume={102}
}
@article{Mar06,
Author = {A.A. Margolin and I. Nemenman and K. Basso et al},
Journal = {BMC Bioinformatics},
Title = {ARACNE: an algorithm for the reconstruction of gene regulatory networks in a mammalian cellular context},
Volume = {7},
Year = {2006}}
@article{Mey07,
Author = {P.E. Meyer and K. Kontos and F. Lafitte and G. Bontempi},
Journal = {EURASIP Journal on Bioinformatics and Systems Biology},
volume={Special Issue on Information-Theoretic Methods for Bioinformatics},
Title = {Information-Theoretic Inference of Large Transcriptional Regulatory Networks},
Year = {2007}}
@article{Ogaw00,
title={New Componenets of a System for Phosphate Accumulation and Polyphosphate Metabolism in Saccaromyces cerevisiae Revealed by Genomic Expression Analysis},
author={N. Ogawa and J. DeRisi and P.O. Brown},
year={2000},
journal={Mol.Biol.Cell},
volume={11}
}
@article{Ols08,
title={On the impact of entropy estimator in transcriptional regulatory network inference},
author={C. Olsen and P.E. Meyer and G. Bontempi},
year={2008},
journal={Proceedings of WCSB08},
}
@article{Pan03,
Author = {L. Paninski},
Journal = {Neural Computation},
Title = {Estimation of Entropy and Mutual Information},
volume={},
Year = {2003}}
@article{Mey08,
title={{MINET}: {A}n open source {R}/{B}ioconductor Package for Mutual Information based Network Inference},
author={P.E. Meyer and F. Lafitte and G. Bontempi},
year={2008},
volume={},
journal={BMC Bioinformatics}
}
@article{Mey08a,
title = {Information-theoretic feature selection in microarray data using variable complementarity},
author = {P.E. Meyer and C. Schretter and G. Bontempi},
year = {2008},
journal={IEEE Journal of Selected Topics in Signal Processing}
}
@Manual{Mey07a,
title = {minet: Mutual Information Network Inference},
author = {P.E. Meyer and F. Lafitte and G. Bontempi},
year = {2007},
note = {R package version 1.1.3},
url = {http://www.ulb.ac.be/di/mlg},
}
@article{Sau07,
title={Getting Closer to the Whole Picture},
author={U. Sauer and M. Heinemann and N. Zamboni},
year={2007},
journal={Science},
}
@article{Simo04,
title={Combining pattern discovery and discriminant analysis to predict gene co-regulation},
author={N. Simonis and S.J. Wodak and G.N. Cohen and J. van Helden},
year={2004},
journal={Bioinformatics},
volume={20}
}
@article{Bol01,
title={Unsupervised Profiling Methods for Fraud Detection},
author={R.J. Bolton and D.J. Hand},
year={2001},
journal={Credit Scoring and Credit Control VII},
}
@article{Bol02,
title={Statistical Fraud Detection: A Review},
author={R.J. Bolton and D.J.Hand},
year={2002},
journal={Statistical Science},
}
@article{Steu02,
title={The mutual information: Detecting and evaluating dependencies between variables},
author={R. Steuer and J. Kurths and C.O. Daub and J. Weise and J. Selbig},
year={2002},
journal={Bioinformatics},
}
@inproceedings{Sok06,
Author = {M. Sokolova and N. Japkowicz and S. Szpakowicz.},
Booktitle = {Proceedings of the AAAI'06 workshop on Evaluation Methods for Machine Learning},
Title = {Beyond Accuracy, F-score and ROC: a Family of Discriminant Measures for Performance Evaluation},
Year = {2006}}
@article{Spel98,
title={Comprehensive Identification of Cell Cycle-regulated Genes of the Yeast Saccharomyces cerevisiae by Microarray Hybridization.},
author={P.T. Spellman and G. Sherlock and M.Q. Zhang and V.R. Iyer and K. Anders and M.B. Eisen and P.O. Brown and D. Botstein and B. Futcher},
year={1998},
journal={Mol.Biol.Cell},
volume={9}
}
@INPROCEEDINGS{Yang03,
author = {Y. Yang and G.I. Webb},
title = {On why discretization works for naive-Bayes classifiers},
booktitle = {Proceedings of the 16th Australian Joint Conference on Artificial Intelligence (AI},
year = {2003},
pages = {440--452}
}
@MASTERSTHESIS{Laf07,
author = {F. Lafitte},
title = {Inf{\'e}rence de r{\'e}seaux g{\'e}n{\'e}tiques par des m{\'e}thodes bas{\'e}es sur l'information mutuelle},
school = {Universit{\'e} Libre de Bruxelles (ULB), Belgium},
intitution = {Facult{\'e} des Sciences, D{\'e}partement d'Informatique},
year = {2003},
}
@article{Fuku75,
title={k-Nearest-Neighbor Bayes-Risk Estimation},
author={K. Fukunaga and L.D. Hostetler},
year={1975},
journal={IT},
volume={21},
}
@article{Dau04,
title = {Estimating mutual information using B-spline functions - an improved similarity measure for analysing gene expression data.},
author = {C.O. Daub and R. Steuer and J. Selbig and S. Kloska},
journal = {BMC Bioinformatics},
pages = {118},
url = {http://dblp.uni-trier.de/db/journals/bmcbi/bmcbi5.html#DaubSSK04},
volume = {5},
year = {2004},
description = {dblp},
ee = {http://dx.doi.org/10.1186/1471-2105-5-118}, date = {2006-05-17},
keywords = {dblp }
}
@inproceedings{Wu07,
Author = {L. Wu and P. Neskovic and E. Reyes and E. Festa and W. Heindel},
Booktitle = {ESANN},
Title = {Classifying n-back EEG data using entropy and mutual information features},
Year = {2007}}
@article{Som02,
Author = {E.P. van Someren and L.F.A. Wessels and E. Backer and M.J.T. Reinders},
Journal = {Pharmacogenomics},
Pages = {507-525},
Title = {Genetic network modelling},
Volume = {3},
Year = {2002}}
@book{Edw00,
Author = {D. Edwards},
Title = {Introduction to Graphical Modelling},
Publisher ={Springer},
Year = {2000},
}
@book{Lau96,
Author = {S.L. Lauritzen},
Title = {Graphical Models},
Publisher ={Clarendon Press, Oxford},
Year = {1996},
}
@phdthesis{Mar03,
Author={D. Margaritis},
Title={Learning Bayesian Network Model Structure from Data},
School={Carnegie Mellon University},
Year={2003},
}
@phdthesis{Mey08thesis,
Author={P.E. Meyer},
Title={Information-Theoretic Variable Selection and Network Inference from Microarray Data},
School={Universit{\'e} Libre de Bruxelles, Belgium},
Year={2008}
}
@phdthesis{Kon09,
Author={K. Kontos},
Title={Gaussian Graphical Model Selection for Gene Regulatory Network Reverse Engineering and Function Prediction},
School={Universit{\'e} Libre de Bruxelles, Belgium},
Year={2009}
}
@article{Che01,
Author={J. Cheng and R. Greiner and J. Kelly and D. Bell and W. Liu},
Title={Learning Bayesian networks from data: An information-theory based approach},
Journal={Artificial Intelligence},
Volume={..},
Year={2001},
}
@TECHREPORT{Hec95,
author = {D. Heckerman},
title = {A tutorial on learning with Bayesian networks},
institution = {Microsoft Research},
year = {1995}
}
@article{Coo92,
abstract = {This paper presents a Bayesian method for constructing probabilistic networks from databases. In particular, we focus on constructing Bayesian belief networks. Potential applications include computer-assisted hypothesis testing, automated scientific discovery, and automated construction of probabilistic expert systems. We extend the basic method to handle missing data and hidden (latent) variables. We show how to perform probabilistic inference by averaging over the inferences of multiple belief networks. Results are presented of a preliminary evaluation of an algorithm for constructing a belief network from a database of cases. Finally, we relate the methods in this paper to previous work, and we discuss open problems.},
author = {Cooper, G.F. and Herskovits, E. },
citeulike-article-id = {93880},
issn = {0885-6125},
journal = {Machine Learning},
keywords = {bayesnet},
month = {October},
number = {4},
pages = {309--347},
posted-at = {2005-02-13 02:43:17},
priority = {0},
title = {A Bayesian Method for the Induction of Probabilistic Networks from Data},
url = {http://www.ingentaconnect.com/content/klu/mach/1992/00000009/00000004/00422779},
volume = {09},
year = {1992}
}
@book{Rus03,
Author = {Stuart Russell and Peter Norvig},
Title = {Artificial Intelligence: A Modern Approach},
Publisher ={Pearson Education International},
Year = {2003},
}
@article{But00,
abstract = {Increasing numbers of methodologies are available to find functional genomic clusters in RNA expression data. We describe a technique that computes comprehensive pair-wise mutual information for all genes in such a data set. An association with a high mutual information means that one gene is non-randomly associated with another; we hypothesize this means the two are related biologically. By picking a threshold mutual information and using only associations at or above the threshold, we show how this technique was used on a public data set of 79 RNA expression measurements of 2,467 genes to construct 22 clusters, or Relevance Networks. The biological significance of each Relevance Network is explained.},
address = {Children's Hospital Informatics Program, Boston, MA 02115, USA.},
author = {Butte, A.J. and Kohane, I.S. },
citeulike-article-id = {2239283},
issn = {1793-5091},
journal = {Pac Symp Biocomput},
keywords = {networks, senior-project},
pages = {418--429},
posted-at = {2008-09-24 22:12:46},
priority = {2},
title = {Mutual information relevance networks: functional genomic clustering using pairwise entropy measurements.},
url = {http://view.ncbi.nlm.nih.gov/pubmed/10902190},
volume={5},
year = {2000},
}
@article{Ols09,
title={On the Impact of Entropy Estimation on Transcriptional Regulatory Network Inference Based on Mutual Information},
author={C. Olsen and P.E. Meyer and G. Bontempi},
journal={EURASIP Journal on Bioinformatics and Systems Biology},
Year={2009},
}
@book{Pea00,
abstract = {{Written by one of the pre-eminent researchers in the field, this book provides a comprehensive exposition of modern analysis of causation. It shows how causality has grown from a nebulous concept into a mathematical theory with significant applications in the fields of statistics, artificial intelligence, philosophy, cognitive science, and the health and social sciences. Pearl presents a unified account of the probabilistic, manipulative, counterfactual and structural approaches to causation, and devises simple mathematical tools for analyzing the relationships between causal connections, statistical associations, actions and observations. The book will open the way for including causal analysis in the standard curriculum of statistics, artifical intelligence, business, epidemiology, social science and economics. Students in these areas will find natural models, simple identification procedures, and precise mathematical definitions of causal concepts that traditional texts have tended to evade or make unduly complicated. This book will be of interest to professionals and students in a wide variety of fields. Anyone who wishes to elucidate meaningful relationships from data, predict effects of actions and policies, assess explanations of reported events, or form theories of causal understanding and causal speech will find this book stimulating and invaluable.}},
author = {Pearl, J. },
citeulike-article-id = {485902},
howpublished = {Hardcover},
isbn = {0521773628},
keywords = {action, belief, causality, inference},
month = {March},
posted-at = {2007-04-07 13:50:37},
priority = {3},
publisher = {{Cambridge University Press}},
title = {Causality : Models, Reasoning, and Inference},
url = {http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20\&path=ASIN/0521773628},
year = {2000}
}
@book{Spi01,
address = {Cambridge, MA, USA},
author = {Spirtes, P. and Glymour, C. and Scheines, R. },
citeulike-article-id = {487589},
edition = {Second},
howpublished = {Hardcover},
isbn = {0262194406},
keywords = {graphical-models, learning},
month = {January},
posted-at = {2008-08-13 17:50:21},
priority = {0},
publisher = {The MIT Press},
title = {Causation, Prediction, and Search},
url = {http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20\&path=ASIN/0262194406},
year = {2001}
}
@book{Pea88,
author = {Pearl, J. },
citeulike-article-id = {235332},
howpublished = {Paperback},
isbn = {1558604790},
keywords = {bayesian, graphical, inference, models, networks, probability, theory, uncertain},
month = {September},
posted-at = {2008-11-10 14:58:55},
priority = {2},
publisher = {Morgan Kaufmann},
title = {Probabilistic Reasoning in Intelligent Systems : Networks of Plausible Inference},
url = {http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20\&path=ASIN/1558604790},
year = {1988}
}
@article{Gil54,
Author = {W.J. McGill},
Journal = {Psychometrika},
Title = {Multivariate information transmission},
volume={},
Year = {1954}}
@INPROCEEDINGS{Bel03,
author = {A.J. Bell},
title = {The co-information lattice},
booktitle ={Proc. Fourth Int'l Symp. Independent Component Analysis and Blind Signal Separation (ICA '03)},
pages={921-926},
year = {2003}
}
}
@article{Sha48,
title = {A Mathematical Theory of Communication},
author = {C.E. Shannon},
journal = {Bell System Technical Journal},
pages = {379-423, 623-656},
volume = 27,
year = 1948,
description = {dret'd bibliography},
biburl = {http://www.bibsonomy.org/bibtex/2a09141ca7c60ae683da509877fe4bf16/selmarsmit},
keywords = {measures, entropy shannon,},
date-added = {2009-01-14 14:23:28 +0100}, date-modified = {2009-01-14 14:23:59 +0100}, uri = {http://cm.bell-labs.com/cm/ms/what/shannonday/paper.html}}
@INPROCEEDINGS{Hec95c,
author = {D. Heckerman},
title = {A Bayesian approach to learning causal networks},
booktitle = {In Uncertainty in AI: Proceedings of the Eleventh Conference},
year = {1995},
pages = {285--295}
}
@inproceedings{Pea91,
author = {J. Pearl and
T. Verma},
title = {A Theory of Inferred Causation},
booktitle = {KR},
year = {1991},
pages = {441-452},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@article{rubin2015expanding,
title={The expanding role of primary care in cancer control},
author={Rubin, Greg and Berendsen, Annette and Crawford, S Michael and Dommett, Rachel and Earle, Craig and Emery, Jon and Fahey, Tom and Grassi, Luigi and Grunfeld, Eva and Gupta, Sumit and others},
journal={The lancet oncology},
volume={16},
number={12},
pages={1231--1272},
year={2015},
publisher={Elsevier}
}
@article{weinstein2013cancer,
title={The cancer genome atlas pan-cancer analysis project},
author={Weinstein, John N and Collisson, Eric A and Mills, Gordon B and Shaw, Kenna R Mills and Ozenberger, Brad A and Ellrott, Kyle and Shmulevich, Ilya and Sander, Chris and Stuart, Joshua M and Cancer Genome Atlas Research Network and others},
journal={Nature genetics},
volume={45},
number={10},
pages={1113--1120},
year={2013},
publisher={Nature Publishing Group}
}
@article{platforms2015comprehensive,
title={Comprehensive, integrative genomic analysis of diffuse lower-grade gliomas},
author={Platforms, Analytic},
year={2015},
journal = {New England Journal of Medicine},
publisher={Mass Medical Soc},
volume = {372},
number = {26},
pages = {2481-2498}
}
@article{hoadley2014multiplatform,
title={Multiplatform analysis of 12 cancer types reveals molecular classification within and across tissues of origin},
author={Hoadley, Katherine A and Yau, Christina and Wolf, Denise M and Cherniack, Andrew D and Tamborero, David and Ng, Sam and Leiserson, Max DM and Niu, Beifang and McLellan, Michael D and Uzunangelov, Vladislav and others},
journal={Cell},
volume={158},
number={4},
pages={929--944},
year={2014},
publisher={Elsevier}
}
@article{cancer2014integrated,
title={Integrated genomic characterization of papillary thyroid carcinoma},
author={Cancer Genome Atlas Research Network and others},
journal={Cell},
volume={159},
number={3},
pages={676--690},
year={2014},
publisher={Elsevier}
}
@article{cancer2014comprehensive,
title={Comprehensive molecular profiling of lung adenocarcinoma},
author={Cancer Genome Atlas Research Network and others},
journal={Nature},
volume={511},
number={7511},
pages={543--550},
year={2014},
publisher={Nature Publishing Group}
}
@article{cancer2014comprehensive,
title={Comprehensive molecular characterization of gastric adenocarcinoma},
author={Cancer Genome Atlas Research Network and others},
journal={Nature},
year={2014},
publisher={Nature Publishing Group}
}
@article{mclendon2008comprehensive,
title={Comprehensive genomic characterization defines human glioblastoma genes and core pathways},
author={McLendon, Roger and Friedman, Allan and Bigner, Darrell and Van Meir, Erwin G and Brat, Daniel J and Mastrogianakis, Gena M and Olson, Jeffrey J and Mikkelsen, Tom and Lehman, Norman and Aldape, Ken and others},
journal={Nature},
volume={455},
number={7216},
pages={1061--1068},
year={2008},
publisher={Nature Publishing Group}
}
@article{bernstein2010nih,
title={The NIH roadmap epigenomics mapping consortium},
author={Bernstein, Bradley E and Stamatoyannopoulos, John A and Costello, Joseph F and Ren, Bing and Milosavljevic, Aleksandar and Meissner, Alexander and Kellis, Manolis and Marra, Marco A and Beaudet, Arthur L and Ecker, Joseph R and others},
journal={Nature biotechnology},
volume={28},
number={10},
pages={1045--1048},
year={2010},
publisher={Nature Publishing Group}
}
@article{chin2011making,
title={Making sense of cancer genomic data},
author={Chin, Lynda and Hahn, William C and Getz, Gad and Meyerson, Matthew},
journal={Genes \& development},
volume={25},
number={6},
pages={534--555},
year={2011},
publisher={Cold Spring Harbor Lab}
}
@article{goldman2014ucsc,
title={The UCSC Cancer Genomics Browser: update 2015},
author={Goldman, Mary and Craft, Brian and Swatloski, Teresa and Cline, Melissa and Morozova, Olena and Diekhans, Mark and Haussler, David and Zhu, Jingchun},
journal={Nucleic acids research},
pages={gku1073},
year={2014},
publisher={Oxford Univ Press}
}
@article{hinoue2012genome,
title={Genome-scale analysis of aberrant DNA methylation in colorectal cancer},
author={Hinoue, Toshinori and Weisenberger, Daniel J and Lange, Christopher PE and Shen, Hui and Byun, Hyang-Min and Van Den Berg, David and Malik, Simeen and Pan, Fei and Noushmehr, Houtan and van Dijk, Cornelis M and others},
journal={Genome research},
volume={22},
number={2},
pages={271--282},
year={2012},
publisher={Cold Spring Harbor Lab}
}
@article{zhu2014tcga,
title={TCGA-Assembler: open-source software for retrieving and processing TCGA data},
author={Zhu, Yitan and Qiu, Peng and Ji, Yuan},
journal={Nature methods},
volume={11},
number={6},
pages={599--600},
year={2014},
publisher={Nature Publishing Group}
}
@article{samur2013canevolve,
title={canEvolve: a web portal for integrative oncogenomics},
author={Samur, Mehmet Kemal and Yan, Zhenyu and Wang, Xujun and Cao, Qingyi and Munshi, Nikhil C and Li, Cheng and Shah, Parantu K},
journal={PloS one},
volume={8},
number={2},
pages={e56228},
year={2013},
publisher={Public Library of Science}
}
@article{gao2013integrative,
title={Integrative analysis of complex cancer genomics and clinical profiles using the cBioPortal},
author={Gao, Jianjiong and Aksoy, B{\"u}lent Arman and Dogrusoz, Ugur and Dresdner, Gideon and Gross, Benjamin and Sumer, S Onur and Sun, Yichao and Jacobsen, Anders and Sinha, Rileen and Larsson, Erik and others},
journal={Science signaling},
volume={6},
number={269},
pages={pl1--pl1},
year={2013},
publisher={Science Signaling}
}@article{gao2013integrative,
title={Integrative analysis of complex cancer genomics and clinical profiles using the cBioPortal},
author={Gao, Jianjiong and Aksoy, B{\"u}lent Arman and Dogrusoz, Ugur and Dresdner, Gideon and Gross, Benjamin and Sumer, S Onur and Sun, Yichao and Jacobsen, Anders and Sinha, Rileen and Larsson, Erik and others},
journal={Science signaling},
volume={6},
number={269},
pages={pl1--pl1},
year={2013},
publisher={Science Signaling}
}
@article{laird2010principles,
title={Principles and challenges of genome-wide DNA methylation analysis},
author={Laird, Peter W},
journal={Nature Reviews Genetics},
volume={11},
number={3},
pages={191--203},
year={2010},
publisher={Nature Publishing Group}
}
@article{cancer2012comprehensive,
title={Comprehensive molecular characterization of human colon and rectal cancer},
author={Cancer Genome Atlas Network and others},
journal={Nature},
volume={487},
number={7407},
pages={330--337},
year={2012},
publisher={Nature Publishing Group}
}
@article{brennan2013somatic,
title={The somatic genomic landscape of glioblastoma},
author={Brennan, Cameron W and Verhaak, Roel GW and McKenna, Aaron and Campos, Benito and Noushmehr, Houtan and Salama, Sofie R and Zheng, Siyuan and Chakravarty, Debyani and Sanborn, J Zachary and Berman, Samuel H and others},
journal={Cell},
volume={155},
number={2},
pages={462--477},
year={2013},
publisher={Elsevier}
}
@article{wilkerson2010consensusclusterplus,
title={ConsensusClusterPlus: a class discovery tool with confidence assessments and item tracking},
author={Wilkerson, Matthew D and Hayes, D Neil},
journal={Bioinformatics},
volume={26},
number={12},
pages={1572--1573},
year={2010},
publisher={Oxford Univ Press}
}
@article{benjamini1995controlling,
title={Controlling the false discovery rate: a practical and powerful approach to multiple testing},
author={Benjamini, Yoav and Hochberg, Yosef},
journal={Journal of the Royal Statistical Society. Series B (Methodological)},
pages={289--300},
year={1995},
publisher={JSTOR}
}
@article{robinson2010edger,
title={edgeR: a Bioconductor package for differential expression analysis of digital gene expression data},
author={Robinson, Mark D and McCarthy, Davis J and Smyth, Gordon K},
journal={Bioinformatics},
volume={26},
number={1},
pages={139--140},
year={2010},
publisher={Oxford Univ Press}
}
@article{ritchie2015limma,
title={limma powers differential expression analyses for RNA-sequencing and microarray studies},
author={Ritchie, Matthew E and Phipson, Belinda and Wu, Di and Hu, Yifang and Law, Charity W and Shi, Wei and Smyth, Gordon K},
journal={Nucleic acids research},
pages={gkv007},
year={2015},
publisher={Oxford Univ Press}
}
@article{lawrence2013software,
title={Software for computing and annotating genomic ranges},
author={Lawrence, Michael and Huber, Wolfgang and Pages, Herv{\'e} and Aboyoun, Patrick and Carlson, Marc and Gentleman, Robert and Morgan, Martin T and Carey, Vincent J},
journal={PLoS Comput Biol},
volume={9},
number={8},
pages={e1003118},
year={2013},
publisher={Public Library of Science}
}
@article{fang2014dnet,
title={The ‘dnet’approach promotes emerging research on cancer patient survival},
author={Fang, Hai and Gough, Julian},
journal={Genome medicine},
volume={6},
number={8},
pages={1--16},
year={2014},
publisher={Springer}
}
@article{zhu2010chippeakanno,
title={ChIPpeakAnno: a Bioconductor package to annotate ChIP-seq and ChIP-chip data},
author={Zhu, Lihua J and Gazin, Claude and Lawson, Nathan D and Pag{\`e}s, Herv{\'e} and Lin, Simon M and Lapointe, David S and Green, Michael R},
journal={BMC bioinformatics},
volume={11},
number={1},
pages={237},
year={2010},
publisher={BioMed Central Ltd}
}
@article{gentleman2004bioconductor,
title={Bioconductor: open software development for computational biology and bioinformatics},
author={Gentleman, Robert C and Carey, Vincent J and Bates, Douglas M and Bolstad, Ben and Dettling, Marcel and Dudoit, Sandrine and Ellis, Byron and Gautier, Laurent and Ge, Yongchao and Gentry, Jeff and others},
journal={Genome biology},
volume={5},
number={10},
pages={R80},
year={2004},
publisher={BioMed Central Ltd}
}
@article{margolin2006aracne,
title={ARACNE: an algorithm for the reconstruction of gene regulatory networks in a mammalian cellular context},
author={Margolin, Adam A and Nemenman, Ilya and Basso, Katia and Wiggins, Chris and Stolovitzky, Gustavo and Favera, Riccardo D and Califano, Andrea},
journal={BMC bioinformatics},
volume={7},
number={Suppl 1},
pages={S7},
year={2006},
publisher={BioMed Central Ltd}
}
@article{huber2015orchestrating,
title={Orchestrating high-throughput genomic analysis with Bioconductor},
author={Huber, Wolfgang and Carey, Vincent J and Gentleman, Robert and Anders, Simon and Carlson, Marc and Carvalho, Benilton S and Bravo, Hector Corrada and Davis, Sean and Gatto, Laurent and Girke, Thomas and others},
journal={Nature methods},
volume={12},
number={2},
pages={115--121},
year={2015},
publisher={Nature Publishing Group}
}
@article{bullard2010evaluation,
title={Evaluation of statistical methods for normalization and differential expression in mRNA-Seq experiments},
author={Bullard, James H and Purdom, Elizabeth and Hansen, Kasper D and Dudoit, Sandrine},
journal={BMC bioinformatics},
volume={11},
number={1},
pages={94},
year={2010},
publisher={BioMed Central Ltd}
}
@manual{ChIP-seqbioc,
title = {ChIP-seq analysis basics},
author = {Aleksandra Pekowska, Simon Anders},
year = {2015},
month = {6}
}
@article{ghodsi2006dimensionality,
title={Dimensionality reduction a short tutorial},
author={Ghodsi, Ali},
journal={Department of Statistics and Actuarial Science, Univ. of Waterloo, Ontario, Canada},
year={2006}
}
@article{mermel2011gistic2,
title={GISTIC2. 0 facilitates sensitive and confident localization of the targets of focal somatic copy-number alteration in human cancers},
author={Mermel, Craig H and Schumacher, Steven E and Hill, Barbara and Meyerson, Matthew L and Beroukhim, Rameen and Getz, Gad and others},
journal={Genome Biol},
volume={12},
number={4},
pages={R41},
year={2011}
}
@Misc{SummarizedExperiment ,
author = {Morgan M, Obenchain V, Hester J and Pagès H.},
title = {SummarizedExperiment: SummarizedExperiment container. R package version 1.1.0.},
howpublished = {\url{ http://bioconductor.org/packages/SummarizedExperiment/}},
}
@article{risso2011gc,
title={GC-content normalization for RNA-Seq data},
author={Risso, Davide and Schwartz, Katja and Sherlock, Gavin and Dudoit, Sandrine},
journal={BMC bioinformatics},
volume={12},
number={1},
pages={480},
year={2011},
publisher={BioMed Central Ltd}
}
@Misc{gviz,
author = {Hahne F, Durinck S, Ivanek R, Mueller A, Lianoglou S, Tan G, Parsons L and Pai S.},
title = { Gviz: Plotting data and annotation information along genomic coordinates. R package version 1.14.0.},
howpublished = {\url{http://bioconductor.org/packages/AnnotationHub/}},
}
@Misc{annotationHub,
author = {Morgan M, Carlson M, Tenenbaum D and Arora S.},
title = { AnnotationHub: Client to access AnnotationHub resources. R package version 2.2.2.},
howpublished = {\url{http://bioconductor.org/packages/Gviz/}},
}
@Misc{ComplexHeatmap,
author = {Gu Z.},
title = { ComplexHeatmap: Making Complex Heatmaps. R package version 1.7.1},
howpublished = {\url{https://github.com/jokergoo/ComplexHeatmap}},
}
@article{fang2014dnet,
title={The ‘dnet’approach promotes emerging research on cancer patient survival},
author={Fang, Hai and Gough, Julian},
journal={Genome medicine},
volume={6},
number={8},
pages={1--16},
year={2014},
publisher={Springer}
}
@article{rebhan1998genecards,
title={GeneCards: a novel functional genomics compendium with automated data mining and query reformulation support.},
author={Rebhan, Michael and Chalifa-Caspi, Vered and Prilusky, Jaime and Lancet, Doron},
journal={Bioinformatics},
volume={14},
number={8},
pages={656--664},
year={1998},
publisher={Oxford Univ Press}
}
@article{kannan2015public,
title={Public data and open source tools for multi-assay genomic investigation of disease},
author={Kannan, Lavanya and Ramos, Marcel and Re, Angela and El-Hachem, Nehme and Safikhani, Zhaleh and Gendoo, Deena MA and Davis, Sean and Gomez-Cabrero, David and Castelo, Robert and Hansen, Kasper D and others},
journal={Briefings in bioinformatics},
pages={bbv080},
year={2015},
publisher={Oxford Univ Press}
}
@article{rubin2015expanding,
title={The expanding role of primary care in cancer control},
author={Rubin, Greg and Berendsen, Annette and Crawford, S Michael and Dommett, Rachel and Earle, Craig and Emery, Jon and Fahey, Tom and Grassi, Luigi and Grunfeld, Eva and Gupta, Sumit and others},
journal={The lancet oncology},
volume={16},
number={12},
pages={1231--1272},
year={2015},
publisher={Elsevier}
}
@article{platforms2015comprehensive,
title={Comprehensive, integrative genomic analysis of diffuse lower-grade gliomas},
author={Platforms, Analytic},
year={2015},
publisher={Mass Medical Soc}
}
@article{hoadley2014multiplatform,
title={Multiplatform analysis of 12 cancer types reveals molecular classification within and across tissues of origin},
author={Hoadley, Katherine A and Yau, Christina and Wolf, Denise M and Cherniack, Andrew D and Tamborero, David and Ng, Sam and Leiserson, Max DM and Niu, Beifang and McLellan, Michael D and Uzunangelov, Vladislav and others},
journal={Cell},
volume={158},
number={4},
pages={929--944},
year={2014},
publisher={Elsevier}
}
@article{cancer2014integrated,
title={Integrated genomic characterization of papillary thyroid carcinoma},
author={Cancer Genome Atlas Research Network and others},
journal={Cell},
volume={159},
number={3},
pages={676--690},
year={2014},
publisher={Elsevier}
}
@article{cancer2014comprehensive,
title={Comprehensive molecular profiling of lung adenocarcinoma},
author={Cancer Genome Atlas Research Network and others},
journal={Nature},
volume={511},
number={7511},
pages={543--550},
year={2014},
publisher={Nature Publishing Group}
}
@article{cancer2014comprehensive,
title={Comprehensive molecular characterization of gastric adenocarcinoma},
author={Cancer Genome Atlas Research Network and others},
journal={Nature},
year={2014},
publisher={Nature Publishing Group}
}
@article{mclendon2008comprehensive,
title={Comprehensive genomic characterization defines human glioblastoma genes and core pathways},
author={McLendon, Roger and Friedman, Allan and Bigner, Darrell and Van Meir, Erwin G and Brat, Daniel J and Mastrogianakis, Gena M and Olson, Jeffrey J and Mikkelsen, Tom and Lehman, Norman and Aldape, Ken and others},
journal={Nature},
volume={455},
number={7216},
pages={1061--1068},
year={2008},
publisher={Nature Publishing Group}
}
@article{bernstein2010nih,
title={The NIH roadmap epigenomics mapping consortium},
author={Bernstein, Bradley E and Stamatoyannopoulos, John A and Costello, Joseph F and Ren, Bing and Milosavljevic, Aleksandar and Meissner, Alexander and Kellis, Manolis and Marra, Marco A and Beaudet, Arthur L and Ecker, Joseph R and others},
journal={Nature biotechnology},
volume={28},
number={10},
pages={1045--1048},
year={2010},
publisher={Nature Publishing Group}
}
@article{encode2011user,
title={A user’s guide to the encyclopedia of DNA elements (ENCODE)},
author={ENCODE Project Consortium and others},
journal={PLoS Biol},
volume={9},
number={4},
pages={e1001046},
year={2011}
}
@article{yao2015inferring,
title={Inferring regulatory element landscapes and transcription factor networks from cancer methylomes.},
author={Yao, L and Shen, H and Laird, PW and Farnham, PJ and Berman, BP},
journal={Genome biology},
volume={16},
number={1},
pages={105--105},
year={2015}
}
@article{chin2011making,
title={Making sense of cancer genomic data},
author={Chin, Lynda and Hahn, William C and Getz, Gad and Meyerson, Matthew},
journal={Genes \& development},
volume={25},
number={6},
pages={534--555},
year={2011},
publisher={Cold Spring Harbor Lab}
}
@article{gao2013integrative,
title={Integrative analysis of complex cancer genomics and clinical profiles using the cBioPortal},
author={Gao, Jianjiong and Aksoy, B{\"u}lent Arman and Dogrusoz, Ugur and Dresdner, Gideon and Gross, Benjamin and Sumer, S Onur and Sun, Yichao and Jacobsen, Anders and Sinha, Rileen and Larsson, Erik and others},
journal={Science signaling},
volume={6},
number={269},
pages={pl1--pl1},
year={2013},
publisher={Science Signaling}
}@article{gao2013integrative,
title={Integrative analysis of complex cancer genomics and clinical profiles using the cBioPortal},
author={Gao, Jianjiong and Aksoy, B{\"u}lent Arman and Dogrusoz, Ugur and Dresdner, Gideon and Gross, Benjamin and Sumer, S Onur and Sun, Yichao and Jacobsen, Anders and Sinha, Rileen and Larsson, Erik and others},
journal={Science signaling},
volume={6},
number={269},
pages={pl1--pl1},
year={2013},
publisher={Science Signaling}
}
@article{wilks2014cancer,
title={The Cancer Genomics Hub (CGHub): overcoming cancer through the power of torrential data},
author={Wilks, Christopher and Cline, Melissa S and Weiler, Erich and Diehkans, Mark and Craft, Brian and Martin, Christy and Murphy, Daniel and Pierce, Howdy and Black, John and Nelson, Donavan and others},
journal={Database},
volume={2014},
pages={bau093},
year={2014},
publisher={Oxford University Press}
}
@article{laird2010principles,
title={Principles and challenges of genome-wide DNA methylation analysis},
author={Laird, Peter W},
journal={Nature Reviews Genetics},
volume={11},
number={3},
pages={191--203},
year={2010},
publisher={Nature Publishing Group}
}
@article{cancer2012comprehensive,
title={Comprehensive molecular characterization of human colon and rectal cancer},
author={Cancer Genome Atlas Network and others},
journal={Nature},
volume={487},
number={7407},
pages={330--337},
year={2012},
publisher={Nature Publishing Group}
}
@article{brennan2013somatic,
title={The somatic genomic landscape of glioblastoma},
author={Brennan, Cameron W and Verhaak, Roel GW and McKenna, Aaron and Campos, Benito and Noushmehr, Houtan and Salama, Sofie R and Zheng, Siyuan and Chakravarty, Debyani and Sanborn, J Zachary and Berman, Samuel H and others},
journal={Cell},
volume={155},
number={2},
pages={462--477},
year={2013},
publisher={Elsevier}
}
@article{wilkerson2010consensusclusterplus,
title={ConsensusClusterPlus: a class discovery tool with confidence assessments and item tracking},
author={Wilkerson, Matthew D and Hayes, D Neil},
journal={Bioinformatics},
volume={26},
number={12},
pages={1572--1573},
year={2010},
publisher={Oxford Univ Press}
}
@article{cancer2012comprehensive,
title={Comprehensive molecular portraits of human breast tumours},
author={Cancer Genome Atlas Network and others},
journal={Nature},
volume={490},
number={7418},
pages={61--70},
year={2012},
publisher={Nature Publishing Group}
}
@article{benjamini1995controlling,
title={Controlling the false discovery rate: a practical and powerful approach to multiple testing},
author={Benjamini, Yoav and Hochberg, Yosef},
journal={Journal of the Royal Statistical Society. Series B (Methodological)},
pages={289--300},
year={1995},
publisher={JSTOR}
}
@article{robinson2010edger,
title={edgeR: a Bioconductor package for differential expression analysis of digital gene expression data},
author={Robinson, Mark D and McCarthy, Davis J and Smyth, Gordon K},
journal={Bioinformatics},
volume={26},
number={1},
pages={139--140},
year={2010},
publisher={Oxford Univ Press}
}
@article{ritchie2015limma,
title={limma powers differential expression analyses for RNA-sequencing and microarray studies},
author={Ritchie, Matthew E and Phipson, Belinda and Wu, Di and Hu, Yifang and Law, Charity W and Shi, Wei and Smyth, Gordon K},
journal={Nucleic acids research},
pages={gkv007},
year={2015},
publisher={Oxford Univ Press}
}
@article{lawrence2013software,
title={Software for computing and annotating genomic ranges},
author={Lawrence, Michael and Huber, Wolfgang and Pages, Herv{\'e} and Aboyoun, Patrick and Carlson, Marc and Gentleman, Robert and Morgan, Martin T and Carey, Vincent J},
journal={PLoS Comput Biol},
volume={9},
number={8},
pages={e1003118},
year={2013},
publisher={Public Library of Science}
}
@article{fang2014dnet,
title={The ‘dnet’approach promotes emerging research on cancer patient survival},
author={Fang, Hai and Gough, Julian},
journal={Genome medicine},
volume={6},
number={8},
pages={1--16},
year={2014},
publisher={Springer}
}
@article{zhu2010chippeakanno,
title={ChIPpeakAnno: a Bioconductor package to annotate ChIP-seq and ChIP-chip data},
author={Zhu, Lihua J and Gazin, Claude and Lawson, Nathan D and Pag{\`e}s, Herv{\'e} and Lin, Simon M and Lapointe, David S and Green, Michael R},
journal={BMC bioinformatics},
volume={11},
number={1},
pages={237},
year={2010},
publisher={BioMed Central Ltd}
}
@article{gentleman2004bioconductor,
title={Bioconductor: open software development for computational biology and bioinformatics},
author={Gentleman, Robert C and Carey, Vincent J and Bates, Douglas M and Bolstad, Ben and Dettling, Marcel and Dudoit, Sandrine and Ellis, Byron and Gautier, Laurent and Ge, Yongchao and Gentry, Jeff and others},
journal={Genome biology},
volume={5},
number={10},
pages={R80},
year={2004},
publisher={BioMed Central Ltd}
}