@article{Du2010, abstract = {BACKGROUND: High-throughput profiling of DNA methylation status of CpG islands is crucial to understand the epigenetic regulation of genes. The microarray-based Infinium methylation assay by Illumina is one platform for low-cost high-throughput methylation profiling. Both Beta-value and M-value statistics have been used as metrics to measure methylation levels. However, there are no detailed studies of their relations and their strengths and limitations. RESULTS: We demonstrate that the relationship between the Beta-value and M-value methods is a Logit transformation, and show that the Beta-value method has severe heteroscedasticity for highly methylated or unmethylated CpG sites. In order to evaluate the performance of the Beta-value and M-value methods for identifying differentially methylated CpG sites, we designed a methylation titration experiment. The evaluation results show that the M-value method provides much better performance in terms of Detection Rate (DR) and True Positive Rate (TPR) for both highly methylated and unmethylated CpG sites. Imposing a minimum threshold of difference can improve the performance of the M-value method but not the Beta-value method. We also provide guidance for how to select the threshold of methylation differences. CONCLUSIONS: The Beta-value has a more intuitive biological interpretation, but the M-value is more statistically valid for the differential analysis of methylation levels. Therefore, we recommend using the M-value method for conducting differential methylation analysis and including the Beta-value statistics when reporting the results to investigators.}, author = {Du, Pan and Zhang, Xiao and Huang, Chiang-Ching and Jafari, Nadereh and Kibbe, Warren a and Hou, Lifang and Lin, Simon M}, doi = {10.1186/1471-2105-11-587}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Du et al. - 2010 - Comparison of Beta-value and M-value methods for quantifying methylation levels by microarray analysis.pdf:pdf}, issn = {1471-2105}, journal = {BMC bioinformatics}, keywords = {CpG Islands,DNA Methylation,Data Interpretation,Microarray Analysis,Microarray Analysis: methods,Statistical}, mendeley-groups = {450k Analysis}, month = {jan}, number = {1}, pages = {587}, pmid = {21118553}, publisher = {BioMed Central Ltd}, title = {{Comparison of Beta-value and M-value methods for quantifying methylation levels by microarray analysis.}}, url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3012676{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {11}, year = {2010} } @misc{RCoreTeam2014, address = {Vienna, Austria}, author = {{R Core Team}}, publisher = {R Foundation for Statistical Computing}, title = {{R: A language and environment for statistical computing}}, url = {http://www.r-project.org/}, year = {2014} } @article{Huber2015, author = {{Huber} and {W.} and {Carey} and V. J. and {Gentleman} and {R.} and {Anders} and {S.} and {Carlson} and {M.} and {Carvalho} and B. S. and {Bravo} and H. C. and {Davis} and {S.} and {Gatto} and {L.} and {Girke} and {T.} and {Gottardo} and {R.} and {Hahne} and {F.} and {Hansen} and K. D. and {Irizarry} and R. A. and {Lawrence} and {M.} and {Love} and M. I. and {MacDonald} and {J.} and {Obenchain} and {V.} and {{Ole's}} and A. K. and {{Pag`es}} and {H.} and {Reyes} and {A.} and {Shannon} and {P.} and {Smyth} and G. K. and {Tenenbaum} and {D.} and {Waldron} and {L.} and {Morgan} and {M.}}, title = {{O}rchestrating high-throughput genomic analysis with {B}ioconductor}, journal = {Nature Methods}, year = {2015}, volume = {12}, number = {2}, pages = {115--121}, url = {http://www.nature.com/nmeth/journal/v12/n2/full/nmeth.3252.html}, } @article{Zhang2013, abstract = {Regulatory T cells (Treg) prevent the emergence of autoimmune disease. Prototypic natural Treg (nTreg) can be reliably identified by demethylation at the Forkhead-box P3 (FOXP3) locus. To explore the methylation landscape of nTreg, we analyzed genome-wide methylation in human naive nTreg (rTreg) and conventional naive CD4(+) T cells (Naive). We detected 2315 differentially methylated cytosine-guanosine dinucleotides (CpGs) between these 2 cell types, many of which clustered into 127 regions of differential methylation (RDMs). Activation changed the methylation status of 466 CpGs and 18 RDMs in Naive but did not alter DNA methylation in rTreg. Gene-set testing of the 127 RDMs showed that promoter methylation and gene expression were reciprocally related. RDMs were enriched for putative FOXP3-binding motifs. Moreover, CpGs within known FOXP3-binding regions in the genome were hypomethylated. In support of the view that methylation limits access of FOXP3 to its DNA targets, we showed that increased expression of the immune suppressive receptor T-cell immunoglobulin and immunoreceptor tyrosine-based inhibitory motif domain (TIGIT), which delineated Treg from activated effector T cells, was associated with hypomethylation and FOXP3 binding at the TIGIT locus. Differential methylation analysis provides insight into previously undefined human Treg signature genes and their mode of regulation.}, author = {Zhang, Yuxia and Maksimovic, Jovana and Naselli, Gaetano and Qian, Junyan and Chopin, Michael and Blewitt, Marnie E and Oshlack, Alicia and Harrison, Leonard C}, doi = {10.1182/blood-2013-02-481788}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Zhang et al. - 2013 - Genome-wide DNA methylation analysis identifies hypomethylated genes regulated by FOXP3 in human regulatory T cell.pdf:pdf}, issn = {1528-0020}, journal = {Blood}, keywords = {Amino Acid Motifs,CpG Islands,DNA Methylation,Epigenesis, Genetic,Forkhead Transcription Factors,Forkhead Transcription Factors: genetics,Forkhead Transcription Factors: metabolism,Gene Expression Regulation,Genome, Human,Humans,Immunophenotyping,Male,Oligonucleotide Array Sequence Analysis,Oligonucleotide Array Sequence Analysis: methods,Promoter Regions, Genetic,Protein Binding,Protein Structure, Tertiary,T-Lymphocytes, Regulatory,T-Lymphocytes, Regulatory: cytology}, month = {oct}, number = {16}, pages = {2823--36}, pmid = {23974203}, title = {{Genome-wide DNA methylation analysis identifies hypomethylated genes regulated by FOXP3 in human regulatory T cells.}}, url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3798997{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {122}, year = {2013} } @article{Cruickshank2013, abstract = {BACKGROUND: Preterm birth confers a high risk of adverse long term health outcomes for survivors, yet the underlying molecular mechanisms are unclear. We hypothesized that effects of preterm birth can be mediated through measurable epigenomic changes throughout development. We therefore used a longitudinal birth cohort to measure the epigenetic mark of DNA methylation at birth and 18 years comparing survivors of extremely preterm birth with infants born at term. METHODS: Using 12 extreme preterm birth cases and 12 matched, term controls, we extracted DNA from archived neonatal blood spots and blood collected in a similar way at 18 years of age. DNA methylation was measured at 347,789 autosomal locations throughout the genome using Infinium HM450 arrays. Representative methylation differences were confirmed by Sequenom MassArray EpiTYPER. RESULTS: At birth we found 1,555 sites with significant differences in methylation between term and preterm babies. At 18 years of age, these differences had largely resolved, suggesting that DNA methylation differences at birth are mainly driven by factors relating to gestational age, such as cell composition and/or maturity. Using matched longitudinal samples, we found evidence for an epigenetic legacy associated with preterm birth, identifying persistent methylation differences at ten genomic loci. Longitudinal comparisons of DNA methylation at birth and 18 years uncovered a significant overlap between sites that were differentially-methylated at birth and those that changed with age. However, we note that overlapping sites may either differ in the same (300/1,555) or opposite (431/1,555) direction during gestation and aging respectively. CONCLUSIONS: We present evidence for widespread methylation differences between extreme preterm and term infants at birth that are largely resolved by 18 years of age. These results are consistent with methylation changes associated with blood cell development, cellular composition, immune induction and age at these time points. Finally, we identified ten probes significantly associated with preterm individuals and with greater than 5{\%} methylation discordance at birth and 18 years that may reflect a long term epigenetic legacy of preterm birth.}, author = {Cruickshank, Mark N and Oshlack, Alicia and Theda, Christiane and Davis, Peter G and Martino, David and Sheehan, Penelope and Dai, Yun and Saffery, Richard and Doyle, Lex W and Craig, Jeffrey M}, doi = {10.1186/gm500}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Cruickshank et al. - 2013 - Analysis of epigenetic changes in survivors of preterm birth reveals the effect of gestational age and evide.pdf:pdf}, issn = {1756-994X}, journal = {Genome medicine}, keywords = {10,5,96,com,content,genome medicine 2013,genomemedicine,http,ickshank et al}, mendeley-groups = {Methylation/EWAS}, month = {jan}, number = {10}, pages = {96}, pmid = {24134860}, title = {{Analysis of epigenetic changes in survivors of preterm birth reveals the effect of gestational age and evidence for a long term legacy.}}, url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3978871{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {5}, year = {2013} } @article{Aryee2014, abstract = {MOTIVATION: The recently released Infinium HumanMethylation450 array (the '450k' array) provides a high-throughput assay to quantify DNA methylation (DNAm) at ?450 000 loci across a range of genomic features. Although less comprehensive than high-throughput sequencing-based techniques, this product is more cost-effective and promises to be the most widely used DNAm high-throughput measurement technology over the next several years. RESULTS: Here we describe a suite of computational tools that incorporate state-of-the-art statistical techniques for the analysis of DNAm data. The software is structured to easily adapt to future versions of the technology. We include methods for preprocessing, quality assessment and detection of differentially methylated regions from the kilobase to the megabase scale. We show how our software provides a powerful and flexible development platform for future methods. We also illustrate how our methods empower the technology to make discoveries previously thought to be possible only with sequencing-based methods. AVAILABILITY AND IMPLEMENTATION: http://bioconductor.org/packages/release/bioc/html/minfi.html. CONTACT: khansen@jhsph.edu; rafa@jimmy.harvard.edu SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.}, author = {Aryee, Martin J and Jaffe, Andrew E and Corrada-Bravo, Hector and Ladd-Acosta, Christine and Feinberg, Andrew P and Hansen, Kasper D and Irizarry, Rafael a}, doi = {10.1093/bioinformatics/btu049}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Aryee et al. - 2014 - Minfi a flexible and comprehensive Bioconductor package for the analysis of Infinium DNA methylation microarrays.pdf:pdf}, issn = {1367-4811}, journal = {Bioinformatics (Oxford, England)}, keywords = {2014,informatics advance access published,january 28}, mendeley-groups = {Software,450k Analysis}, month = {may}, number = {10}, pages = {1363--9}, pmid = {24478339}, title = {{Minfi: a flexible and comprehensive Bioconductor package for the analysis of Infinium DNA methylation microarrays.}}, url = {http://www.ncbi.nlm.nih.gov/pubmed/24478339}, volume = {30}, year = {2014} } @article{Phipson2016, abstract = {DNA methylation is one of the most commonly studied epigenetic modifications due to its role in both disease and development. The Illumina HumanMethylation450 BeadChip is a cost-effective way to profile {\textgreater}450?000 CpGs across the human genome, making it a popular platform for profiling DNA methylation. Here we introduce missMethyl, an R package with a suite of tools for performing normalization, removal of unwanted variation in differential methylation analysis, differential variability testing and gene set analysis for the 450K array. AVAILABILITY AND IMPLEMENTATION: missMethyl is an R package available from the Bioconductor project at www.bioconductor.org. CONTACT: alicia.oshlack@mcri.edu.auSupplementary information: Supplementary data are available at Bioinformatics online.}, author = {Phipson, Belinda and Maksimovic, Jovana and Oshlack, Alicia}, doi = {10.1093/bioinformatics/btv560}, issn = {1367-4811}, journal = {Bioinformatics (Oxford, England)}, month = {jan}, number = {2}, pages = {286--288}, pmid = {26424855}, title = {{missMethyl: an R package for analyzing data from Illumina's HumanMethylation450 platform.}}, url = {http://bioinformatics.oxfordjournals.org/content/32/2/286}, volume = {32}, year = {2016} } @article{Pidsley2013, abstract = {BACKGROUND: As the most stable and experimentally accessible epigenetic mark, DNA methylation is of great interest to the research community. The landscape of DNA methylation across tissues, through development and in disease pathogenesis is not yet well characterized. Thus there is a need for rapid and cost effective methods for assessing genome-wide levels of DNA methylation. The Illumina Infinium HumanMethylation450 (450K) BeadChip is a very useful addition to the available methods for DNA methylation analysis but its complex design, incorporating two different assay methods, requires careful consideration. Accordingly, several normalization schemes have been published. We have taken advantage of known DNA methylation patterns associated with genomic imprinting and X-chromosome inactivation (XCI), in addition to the performance of SNP genotyping assays present on the array, to derive three independent metrics which we use to test alternative schemes of correction and normalization. These metrics also have potential utility as quality scores for datasets. RESULTS: The standard index of DNA methylation at any specific CpG site is $\beta$ = M/(M + U + 100) where M and U are methylated and unmethylated signal intensities, respectively. Betas ($\beta$s) calculated from raw signal intensities (the default GenomeStudio behavior) perform well, but using 11 methylomic datasets we demonstrate that quantile normalization methods produce marked improvement, even in highly consistent data, by all three metrics. The commonly used procedure of normalizing betas is inferior to the separate normalization of M and U, and it is also advantageous to normalize Type I and Type II assays separately. More elaborate manipulation of quantiles proves to be counterproductive. CONCLUSIONS: Careful selection of preprocessing steps can minimize variance and thus improve statistical power, especially for the detection of the small absolute DNA methylation changes likely associated with complex disease phenotypes. For the convenience of the research community we have created a user-friendly R software package called wateRmelon, downloadable from bioConductor, compatible with the existing methylumi, minfi and IMA packages, that allows others to utilize the same normalization methods and data quality tests on 450K data.}, author = {Pidsley, Ruth and {Y Wong}, Chloe C and Volta, Manuela and Lunnon, Katie and Mill, Jonathan and Schalkwyk, Leonard C}, doi = {10.1186/1471-2164-14-293}, file = {::}, issn = {1471-2164}, journal = {BMC genomics}, keywords = {Chromosomes, Human, X,Chromosomes, Human, X: genetics,Computational Biology,Computational Biology: methods,DNA Methylation,Genomic Imprinting,Humans,Oligonucleotide Array Sequence Analysis,Polymorphism, Single Nucleotide,Polymorphism, Single Nucleotide: genetics,Statistics as Topic}, language = {En}, month = {jan}, number = {1}, pages = {293}, pmid = {23631413}, publisher = {BioMed Central}, title = {{A data-driven approach to preprocessing Illumina 450K methylation array data.}}, url = {http://bmcgenomics.biomedcentral.com/articles/10.1186/1471-2164-14-293}, volume = {14}, year = {2013} } @Manual{Davis2015, title = {methylumi: Handle Illumina methylation data}, author = {Sean Davis and Pan Du and Sven Bilke and Tim Triche and {Jr.} and Moiz Bootwalla}, year = {2015}, note = {R package version 2.16.0}, } @article{Morris2014, abstract = {The Illumina Infinium HumanMethylation450 BeadChip is a new platform for high-throughput DNA methylation analysis. Several methods for normalization and processing of these data have been published recently. Here we present an integrated analysis pipeline offering a choice of the most popular normalization methods while also introducing new methods for calling differentially methylated regions and detecting copy number aberrations. Availability and implementation: ChAMP is implemented as a Bioconductor package in R. The package and the vignette can be downloaded at bioconductor.org}, author = {Morris, Tiffany J and Butcher, Lee M and Feber, Andrew and Teschendorff, Andrew E and Chakravarthy, Ankur R and Wojdacz, Tomasz K and Beck, Stephan}, doi = {10.1093/bioinformatics/btt684}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Morris et al. - 2014 - ChAMP 450k Chip Analysis Methylation Pipeline.pdf:pdf}, issn = {1367-4811}, journal = {Bioinformatics (Oxford, England)}, keywords = {DNA Copy Number Variations,DNA Methylation,Oligonucleotide Array Sequence Analysis,Oligonucleotide Array Sequence Analysis: methods,Software}, mendeley-groups = {Software,450k Analysis}, month = {feb}, number = {3}, pages = {428--30}, pmid = {24336642}, title = {{ChAMP: 450k Chip Analysis Methylation Pipeline.}}, url = {http://www.ncbi.nlm.nih.gov/pubmed/24336642}, volume = {30}, year = {2014} } @article{Aryee2011, abstract = {DNA methylation is a key regulator of gene function in a multitude of both normal and abnormal biological processes, but tools to elucidate its roles on a genome-wide scale are still in their infancy. Methylation sensitive restriction enzymes and microarrays provide a potential high-throughput, low-cost platform to allow methylation profiling. However, accurate absolute methylation estimates have been elusive due to systematic errors and unwanted variability. Previous microarray preprocessing procedures, mostly developed for expression arrays, fail to adequately normalize methylation-related data since they rely on key assumptions that are violated in the case of DNA methylation. We develop a normalization strategy tailored to DNA methylation data and an empirical Bayes percentage methylation estimator that together yield accurate absolute methylation estimates that can be compared across samples. We illustrate the method on data generated to detect methylation differences between tissues and between normal and tumor colon samples.}, author = {Aryee, Martin J and Wu, Zhijin and Ladd-Acosta, Christine and Herb, Brian and Feinberg, Andrew P and Yegnasubramanian, Srinivasan and Irizarry, Rafael a}, doi = {10.1093/biostatistics/kxq055}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Aryee et al. - 2011 - Accurate genome-scale percentage DNA methylation estimates from microarray data.pdf:pdf}, issn = {1468-4357}, journal = {Biostatistics (Oxford, England)}, keywords = {Algorithms,Bayes Theorem,Brain Chemistry,Brain Chemistry: genetics,Colon,Colon: chemistry,Colonic Neoplasms,Colonic Neoplasms: chemistry,DNA,DNA Methylation,DNA Restriction Enzymes,DNA Restriction Enzymes: metabolism,DNA, Neoplasm,DNA, Neoplasm: chemistry,DNA, Neoplasm: metabolism,DNA: chemistry,DNA: metabolism,Epigenomics,Epigenomics: methods,Genome,Humans,Liver,Liver: chemistry,Oligonucleotide Array Sequence Analysis,Oligonucleotide Array Sequence Analysis: methods,Sequence Analysis, DNA,Spleen,Spleen: chemistry,Sulfites,Sulfites: chemistry}, mendeley-groups = {450k Analysis}, month = {apr}, number = {2}, pages = {197--210}, pmid = {20858772}, title = {{Accurate genome-scale percentage DNA methylation estimates from microarray data.}}, url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3062148{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {12}, year = {2011} } @article{Ritchie2015, abstract = {limma is an R/Bioconductor software package that provides an integrated solution for analysing data from gene expression experiments. It contains rich features for handling complex experimental designs and for information borrowing to overcome the problem of small sample sizes. Over the past decade, limma has been a popular choice for gene discovery through differential expression analyses of microarray and high-throughput PCR data. The package contains particularly strong facilities for reading, normalizing and exploring such data. Recently, the capabilities of limma have been significantly expanded in two important directions. First, the package can now perform both differential expression and differential splicing analyses of RNA sequencing (RNA-seq) data. All the downstream analysis tools previously restricted to microarray data are now available for RNA-seq as well. These capabilities allow users to analyse both RNA-seq and microarray data with very similar pipelines. Second, the package is now able to go past the traditional gene-wise expression analyses in a variety of ways, analysing expression profiles in terms of co-regulated sets of genes or in terms of higher-order expression signatures. This provides enhanced possibilities for biological interpretation of gene expression differences. This article reviews the philosophy and design of the limma package, summarizing both new and historical features, with an emphasis on recent enhancements and features that have not been previously described.}, author = {Ritchie, M. E. and Phipson, B. and Wu, D. and Hu, Y. and Law, C. W. and Shi, W. and Smyth, G. K.}, doi = {10.1093/nar/gkv007}, issn = {0305-1048}, journal = {Nucleic Acids Research}, month = {jan}, pages = {gkv007--}, title = {{limma powers differential expression analyses for RNA-sequencing and microarray studies}}, url = {http://nar.oxfordjournals.org/content/early/2015/01/20/nar.gkv007.full}, year = {2015} } @article{Fortin2014, abstract = {We propose an extension to quantile normalization that removes unwanted technical variation using control probes. We adapt our algorithm, functional normalization, to the Illumina 450k methylation array and address the open problem of normalizing methylation data with global epigenetic changes, such as human cancers. Using data sets from The Cancer Genome Atlas and a large case–control study, we show that our algorithm outperforms all existing normalizationmethods with respect to replication of results between experiments, and yields robust results even in the presence of batch effects. Functional normalization can be applied to any microarray platform, provided suitable control probes are available.}, author = {Fortin, JP and Labbe, Aur{\'{e}}lie and Lemire, Mathieu and Zanke, BW}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Fortin et al. - 2014 - Functional normalization of 450k methylation array data improves replication in large cancer studies.pdf:pdf}, journal = {Genome biology}, keywords = {11,15,2014,503,com,genome biology 2014,genomebiology,http,tin et al}, number = {503}, pages = {1--17}, title = {{Functional normalization of 450k methylation array data improves replication in large cancer studies}}, volume = {15}, year = {2014} } @article{Wu2014, abstract = {The Illumina Infinium HumanMethylation450 BeadChip has emerged as one of the most popular platforms for genome wide profiling of DNA methylation. While the technology is wide-spread, systematic technical biases are believed to be present in the data. For example, this array incorporates two different chemical assays, i.e., Type I and Type II probes, which exhibit different technical characteristics and potentially complicate the computational and statistical analysis. Several normalization methods have been introduced recently to adjust for possible biases. However, there is considerable debate within the field on which normalization procedure should be used and indeed whether normalization is even necessary. Yet despite the importance of the question, there has been little comprehensive comparison of normalization methods. We sought to systematically compare several popular normalization approaches using the Norwegian Mother and Child Cohort Study (MoBa) methylation data set and the technical replicates analyzed with it as a case study. We assessed both the reproducibility between technical replicates following normalization and the effect of normalization on association analysis. Results indicate that the raw data are already highly reproducible, some normalization approaches can slightly improve reproducibility, but other normalization approaches may introduce more variability into the data. Results also suggest that differences in association analysis after applying different normalizations are not large when the signal is strong, but when the signal is more modest, different normalizations can yield very different numbers of findings that meet a weaker statistical significance threshold. Overall, our work provides useful, objective assessment of the effectiveness of key normalization methods.}, author = {Wu, Michael C and Joubert, Bonnie R and Kuan, Pei-fen and H{\aa}berg, Siri E and Nystad, Wenche and Peddada, Shyamal D and London, Stephanie J}, doi = {10.4161/epi.27119}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Wu et al. - 2014 - A systematic assessment of normalization approaches for the Infinium 450K methylation platform.pdf:pdf}, issn = {1559-2308}, journal = {Epigenetics : official journal of the DNA Methylation Society}, keywords = {Adult,CpG Islands,DNA Methylation,Humans,Infant, Newborn,Oligonucleotide Array Sequence Analysis,Oligonucleotide Array Sequence Analysis: methods,Oligonucleotide Array Sequence Analysis: statistic,Reproducibility of Results,Software}, month = {feb}, number = {2}, pages = {318--29}, pmid = {24241353}, title = {{A systematic assessment of normalization approaches for the Infinium 450K methylation platform.}}, url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3962542{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {9}, year = {2014} } @article{Sun2011, abstract = {BACKGROUND: Genome-wide methylation profiling has led to more comprehensive insights into gene regulation mechanisms and potential therapeutic targets. Illumina Human Methylation BeadChip is one of the most commonly used genome-wide methylation platforms. Similar to other microarray experiments, methylation data is susceptible to various technical artifacts, particularly batch effects. To date, little attention has been given to issues related to normalization and batch effect correction for this kind of data. METHODS: We evaluated three common normalization approaches and investigated their performance in batch effect removal using three datasets with different degrees of batch effects generated from HumanMethylation27 platform: quantile normalization at average $\beta$ value (QN$\beta$); two step quantile normalization at probe signals implemented in "lumi" package of R (lumi); and quantile normalization of A and B signal separately (ABnorm). Subsequent Empirical Bayes (EB) batch adjustment was also evaluated. RESULTS: Each normalization could remove a portion of batch effects and their effectiveness differed depending on the severity of batch effects in a dataset. For the dataset with minor batch effects (Dataset 1), normalization alone appeared adequate and "lumi" showed the best performance. However, all methods left substantial batch effects intact in the datasets with obvious batch effects and further correction was necessary. Without any correction, 50 and 66 percent of CpGs were associated with batch effects in Dataset 2 and 3, respectively. After QN$\beta$, lumi or ABnorm, the number of CpGs associated with batch effects were reduced to 24, 32, and 26 percent for Dataset 2; and 37, 46, and 35 percent for Dataset 3, respectively. Additional EB correction effectively removed such remaining non-biological effects. More importantly, the two-step procedure almost tripled the numbers of CpGs associated with the outcome of interest for the two datasets. CONCLUSION: Genome-wide methylation data from Infinium Methylation BeadChip can be susceptible to batch effects with profound impacts on downstream analyses and conclusions. Normalization can reduce part but not all batch effects. EB correction along with normalization is recommended for effective batch effect removal.}, author = {Sun, Zhifu and Chai, High Seng and Wu, Yanhong and White, Wendy M and Donkena, Krishna V and Klein, Christopher J and Garovic, Vesna D and Therneau, Terry M and Kocher, Jean-Pierre a}, doi = {10.1186/1755-8794-4-84}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Sun et al. - 2011 - Batch effect correction for genome-wide methylation data with Illumina Infinium platform.pdf:pdf}, issn = {1755-8794}, journal = {BMC medical genomics}, keywords = {Adult,CpG Islands,CpG Islands: genetics,DNA Methylation,DNA Methylation: genetics,Databases, Genetic,Genome, Human,Genome, Human: genetics,Humans,Male,Oligonucleotide Array Sequence Analysis,Oligonucleotide Array Sequence Analysis: methods,Reproducibility of Results}, mendeley-groups = {450k Analysis}, month = {jan}, pages = {84}, pmid = {22171553}, title = {{Batch effect correction for genome-wide methylation data with Illumina Infinium platform.}}, url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3265417{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {4}, year = {2011} } @article{Wang2012, abstract = {Nowadays, some researchers normalized DNA methylation arrays data in order to remove the technical artifacts introduced by experimental differences in sample preparation, array processing and other factors. However, other researchers analyzed DNA methylation arrays without performing data normalization considering that current normalizations for methylation data may distort real differences between normal and cancer samples because cancer genomes may be extensively subject to hypomethylation and the total amount of CpG methylation might differ substantially among samples. In this study, using eight datasets by Infinium HumanMethylation27 assay, we systemically analyzed the global distribution of DNA methylation changes in cancer compared to normal control and its effect on data normalization for selecting differentially methylated (DM) genes. We showed more differentially methylated (DM) genes could be found in the Quantile/Lowess-normalized data than in the non-normalized data. We found the DM genes additionally selected in the Quantile/Lowess-normalized data showed significantly consistent methylation states in another independent dataset for the same cancer, indicating these extra DM genes were effective biological signals related to the disease. These results suggested normalization can increase the power of detecting DM genes in the context of diagnostic markers which were usually characterized by relatively large effect sizes. Besides, we evaluated the reproducibility of DM discoveries for a particular cancer type, and we found most of the DM genes additionally detected in one dataset showed the same methylation directions in the other dataset for the same cancer type, indicating that these DM genes were effective biological signals in the other dataset. Furthermore, we showed that some DM genes detected from different studies for a particular cancer type were significantly reproducible at the functional level.}, author = {Wang, Dong and Zhang, Yuannv and Huang, Yan and Li, Pengfei and Wang, Mingyue and Wu, Ruihong and Cheng, Lixin and Zhang, Wenjing and Zhang, Yujing and Li, Bin and Wang, Chenguang and Guo, Zheng}, doi = {10.1016/j.gene.2012.06.075}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Wang et al. - 2012 - Comparison of different normalization assumptions for analyses of DNA methylation data from the cancer genome.pdf:pdf}, issn = {1879-0038}, journal = {Gene}, keywords = {Algorithms,Colorectal Neoplasms,Colorectal Neoplasms: genetics,DNA Methylation,Data Interpretation, Statistical,Databases, Nucleic Acid,Genome, Human,Humans,Kidney Neoplasms,Kidney Neoplasms: genetics,Lung Neoplasms,Lung Neoplasms: genetics,Neoplasms,Neoplasms: genetics,Oligonucleotide Array Sequence Analysis,Oligonucleotide Array Sequence Analysis: statistic,Reproducibility of Results,Stomach Neoplasms,Stomach Neoplasms: genetics}, mendeley-groups = {Methylation/EWAS}, month = {sep}, number = {1}, pages = {36--42}, pmid = {22771920}, publisher = {Elsevier B.V.}, title = {{Comparison of different normalization assumptions for analyses of DNA methylation data from the cancer genome.}}, url = {http://www.ncbi.nlm.nih.gov/pubmed/22771920}, volume = {506}, year = {2012} } @article{Maksimovic2012, abstract = {DNA methylation is the most widely studied epigenetic mark and is known to be essential to normal development and frequently disrupted in disease. The Illumina HumanMethylation450 BeadChip assays the methylation status of CpGs at 485,577 sites across the genome. Here we present Subset-quantile Within Array Normalization (SWAN), a new method that substantially improves the results from this platform by reducing technical variation within and between arrays. SWAN is available in the minfi Bioconductor package.}, author = {Maksimovic, Jovana and Gordon, Lavinia and Oshlack, Alicia}, doi = {10.1186/gb-2012-13-6-r44}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Maksimovic, Gordon, Oshlack - 2012 - SWAN Subset-quantile within array normalization for illumina infinium HumanMethylation450 BeadChips.pdf:pdf}, issn = {1465-6914}, journal = {Genome biology}, keywords = {CpG Islands,DNA Methylation,DNA Probes,DNA Probes: genetics,DNA, Neoplasm,DNA, Neoplasm: analysis,DNA, Neoplasm: genetics,Female,Genome, Human,Humans,MCF-7 Cells,Male,Oligonucleotide Array Sequence Analysis,Oligonucleotide Array Sequence Analysis: methods,Reproducibility of Results,Sequence Analysis, DNA,Sequence Analysis, DNA: methods,Software}, mendeley-groups = {Software}, month = {jan}, number = {6}, pages = {R44}, pmid = {22703947}, publisher = {BioMed Central Ltd}, title = {{SWAN: Subset-quantile within array normalization for illumina infinium HumanMethylation450 BeadChips.}}, url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3446316{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {13}, year = {2012} } @article{Mancuso2011, abstract = {BACKGROUND: The study of the human DNA methylome has gained particular interest in the last few years. Researchers can nowadays investigate the potential role of DNA methylation in common disorders by taking advantage of new high-throughput technologies. Among these, Illumina Infinium assays can interrogate the methylation levels of hundreds of thousands of CpG sites, offering an ideal solution for genome-wide methylation profiling. However, like for other high-throughput technologies, the main bottleneck remains at the stage of data analysis rather than data production. FINDINGS: We have developed HumMeth27QCReport, an R package devoted to researchers wanting to quickly analyse their Illumina Infinium methylation arrays. This package automates quality control steps by generating a report including sample-independent and sample-dependent quality plots, and performs primary analysis of raw methylation calls by computing data normalization, statistics, and sample similarities. This package is available at CRAN repository, and can be integrated in any Galaxy instance through the implementation of ad-hoc scripts accessible at Galaxy Tool Shed. CONCLUSIONS: Our package provides users of the Illumina Infinium Methylation assays with a simplified, automated, open-source quality control and primary analysis of their methylation data. Moreover, to enhance its use by experimental researchers, the tool is being distributed along with the scripts necessary for its implementation in the Galaxy workbench. Finally, although it was originally developed for HumanMethylation27, we proved its compatibility with data generated with the HumanMethylation450 Bead Chip.}, author = {Mancuso, Francesco M and Montfort, Magda and Carreras, Anna and Alib{\'{e}}s, Andreu and Roma, Guglielmo}, doi = {10.1186/1756-0500-4-546}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Mancuso et al. - 2011 - HumMeth27QCReport an R package for quality control and primary analysis of Illumina Infinium methylation data.pdf:pdf}, issn = {1756-0500}, journal = {BMC research notes}, keywords = {an r package for,analysis of,available soon,fully formatted,html,hummeth27qcreport,it appeared upon acceptance,pdf and full text,quality control and primary,research notes,this provisional pdf corresponds,to the article as,versions will be made}, mendeley-groups = {Software,450k Analysis}, month = {jan}, pages = {546}, pmid = {22182516}, title = {{HumMeth27QCReport: an R package for quality control and primary analysis of Illumina Infinium methylation data.}}, url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3285701{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {4}, year = {2011} } @article{Touleimat2012, abstract = {BACKGROUND: Huge progress has been made in the development of array- or sequencing-based technologies for DNA methylation analysis. The Illumina Infinium({\textregistered}) Human Methylation 450K BeadChip (Illumina Inc., CA, USA) allows the simultaneous quantitative monitoring of more than 480,000 CpG positions, enabling large-scale epigenotyping studies. However, the assay combines two different assay chemistries, which may cause a bias in the analysis if all signals are merged as a unique source of methylation measurement. MATERIALS {\&} METHODS: We confirm in three 450K data sets that Infinium I signals are more stable and cover a wider dynamic range of methylation values than Infinium II signals. We evaluated the methylation profile of Infinium I and II probes obtained with different normalization protocols and compared these results with the methylation values of a subset of CpGs analyzed by pyrosequencing. RESULTS: We developed a subset quantile normalization approach for the processing of 450K BeadChips. The Infinium I signals were used as 'anchors' to normalize Infinium II signals at the level of probe coverage categories. Our normalization approach outperformed alternative normalization or correction approaches in terms of bias correction and methylation signal estimation. We further implemented a complete preprocessing protocol that solves most of the issues currently raised by 450K array users. CONCLUSION: We developed a complete preprocessing pipeline for 450K BeadChip data using an original subset quantile normalization approach that performs both sample normalization and efficient Infinium I/II shift correction. The scripts, being freely available from the authors, will allow researchers to concentrate on the biological analysis of data, such as the identification of DNA methylation signatures.}, author = {Touleimat, Nizar and Tost, J{\"{o}}rg}, doi = {10.2217/epi.12.21}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Touleimat, Tost - 2012 - Complete pipeline for Infinium{\textregistered} Human Methylation 450K BeadChip data processing using subset quantile normaliza.pdf:pdf}, issn = {1750-192X}, journal = {Epigenomics}, keywords = {450k beadchip data processing,chnology r eport,com,complete pipeline for infinium,for reprint orders,futuremedicine,human methylation,please contact,reprints,using subset quantile}, mendeley-groups = {450k Analysis}, month = {jun}, number = {3}, pages = {325--341}, pmid = {22690668}, title = {{Complete pipeline for Infinium{\textregistered} Human Methylation 450K BeadChip data processing using subset quantile normalization for accurate DNA methylation estimation}}, url = {http://www.futuremedicine.com/doi/abs/10.2217/epi.12.21}, volume = {4}, year = {2012} } @article{Teschendorff2013, abstract = {MOTIVATION: The Illumina Infinium 450 k DNA Methylation Beadchip is a prime candidate technology for Epigenome-Wide Association Studies (EWAS). However, a difficulty associated with these beadarrays is that probes come in two different designs, characterized by widely different DNA methylation distributions and dynamic range, which may bias downstream analyses. A key statistical issue is therefore how best to adjust for the two different probe designs. RESULTS: Here we propose a novel model-based intra-array normalization strategy for 450 k data, called BMIQ (Beta MIxture Quantile dilation), to adjust the beta-values of type2 design probes into a statistical distribution characteristic of type1 probes. The strategy involves application of a three-state beta-mixture model to assign probes to methylation states, subsequent transformation of probabilities into quantiles and finally a methylation-dependent dilation transformation to preserve the monotonicity and continuity of the data. We validate our method on cell-line data, fresh frozen and paraffin-embedded tumour tissue samples and demonstrate that BMIQ compares favourably with two competing methods. Specifically, we show that BMIQ improves the robustness of the normalization procedure, reduces the technical variation and bias of type2 probe values and successfully eliminates the type1 enrichment bias caused by the lower dynamic range of type2 probes. BMIQ will be useful as a preprocessing step for any study using the Illumina Infinium 450 k platform. AVAILABILITY: BMIQ is freely available from http://code.google.com/p/bmiq/. CONTACT: a.teschendorff@ucl.ac.uk SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.}, author = {Teschendorff, Andrew E and Marabita, Francesco and Lechner, Matthias and Bartlett, Thomas and Tegner, Jesper and Gomez-Cabrero, David and Beck, Stephan}, doi = {10.1093/bioinformatics/bts680}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Teschendorff et al. - 2013 - A beta-mixture quantile normalization method for correcting probe design bias in Illumina Infinium 450 k DN.pdf:pdf}, issn = {1367-4811}, journal = {Bioinformatics (Oxford, England)}, keywords = {Algorithms,DNA Methylation,Neoplasms,Neoplasms: genetics,Normal Distribution,Nucleic Acid Probes,Nucleic Acid Probes: chemistry,Oligonucleotide Array Sequence Analysis,Oligonucleotide Array Sequence Analysis: methods}, mendeley-groups = {450k Analysis}, month = {jan}, number = {2}, pages = {189--96}, pmid = {23175756}, title = {{A beta-mixture quantile normalization method for correcting probe design bias in Illumina Infinium 450 k DNA methylation data.}}, url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3546795{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {29}, year = {2013} } @article{Triche2013, abstract = {We propose a novel approach to background correction for Infinium HumanMethylation data to account for technical variation in background fluorescence signal. Our approach capitalizes on a new use for the Infinium I design bead types to measure non-specific fluorescence in the colour channel opposite of their design (Cy3/Cy5). This provides tens of thousands of features for measuring background instead of the much smaller number of negative control probes on the platforms (n = 32 for HumanMethylation27 and n = 614 for HumanMethylation450, respectively). We compare the performance of our methods with existing approaches, using technical replicates of both mixture samples and biological samples, and demonstrate that within- and between-platform artefacts can be substantially reduced, with concomitant improvement in sensitivity, by the proposed methods.}, author = {Triche, Timothy J and Weisenberger, Daniel J and {Van Den Berg}, David and Laird, Peter W and Siegmund, Kimberly D}, doi = {10.1093/nar/gkt090}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Triche et al. - 2013 - Low-level processing of Illumina Infinium DNA Methylation BeadArrays.pdf:pdf}, issn = {1362-4962}, journal = {Nucleic acids research}, keywords = {DNA Methylation,Fluorescent Dyes,HapMap Project,Humans,Oligonucleotide Array Sequence Analysis,Oligonucleotide Array Sequence Analysis: methods}, mendeley-groups = {450k Analysis}, month = {apr}, number = {7}, pages = {e90}, pmid = {23476028}, title = {{Low-level processing of Illumina Infinium DNA Methylation BeadArrays.}}, url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3627582{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {41}, year = {2013} } @article{Chen2013, abstract = {DNA methylation, an important type of epigenetic modification in humans, participates in crucial cellular processes, such as embryonic development, X-inactivation, genomic imprinting and chromosome stability. Several platforms have been developed to study genome-wide DNA methylation. Many investigators in the field have chosen the Illumina Infinium HumanMethylation microarray for its ability to reliably assess DNA methylation following sodium bisulfite conversion. Here, we analyzed methylation profiles of 489 adult males and 357 adult females generated by the Infinium HumanMethylation450 microarray. Among the autosomal CpG sites that displayed significant methylation differences between the two sexes, we observed a significant enrichment of cross-reactive probes co-hybridizing to the sex chromosomes with more than 94{\%} sequence identity. This could lead investigators to mistakenly infer the existence of significant autosomal sex-associated methylation. Using sequence identity cutoffs derived from the sex methylation analysis, we concluded that 6{\%} of the array probes can potentially generate spurious signals because of co-hybridization to alternate genomic sequences highly homologous to the intended targets. Additionally, we discovered probes targeting polymorphic CpGs that overlapped SNPs. The methylation levels detected by these probes are simply the reflection of underlying genetic polymorphisms but could be misinterpreted as true signals. The existence of probes that are cross-reactive or of target polymorphic CpGs in the Illumina HumanMethylation microarrays can confound data obtained from such microarrays. Therefore, investigators should exercise caution when significant biological associations are found using these array platforms. A list of all cross-reactive probes and polymorphic CpGs identified by us are annotated in this paper.}, author = {Chen, Yi-an and Lemire, Mathieu and Choufani, Sanaa and Butcher, Darci T and Grafodatskaya, Daria and Zanke, Brent W and Gallinger, Steven and Hudson, Thomas J and Weksberg, Rosanna}, doi = {10.4161/epi.23470}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Chen et al. - 2013 - Discovery of cross-reactive probes and polymorphic CpGs in the Illumina Infinium HumanMethylation450 microarray.pdf:pdf}, issn = {1559-2308}, journal = {Epigenetics : official journal of the DNA Methylation Society}, keywords = {Adult,Chromosomes,CpG Islands,DNA Methylation,DNA Probes,Female,Genome,Human,Humans,Male,Oligonucleotide Array Sequence Analysis,Oligonucleotide Array Sequence Analysis: methods,Polymorphism,Single Nucleotide,X,Y}, mendeley-groups = {450k Analysis}, month = {feb}, number = {2}, pages = {203--9}, pmid = {23314698}, publisher = {Landes Bioscience}, title = {{Discovery of cross-reactive probes and polymorphic CpGs in the Illumina Infinium HumanMethylation450 microarray.}}, url = {https://www.landesbioscience.com/journals/epigenetics/article/23470/?nocache=1557519926 http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3592906{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {8}, year = {2013} } @article{Peters2015, abstract = {BACKGROUND: The identification and characterisation of differentially methylated regions (DMRs) between phenotypes in the human genome is of prime interest in epigenetics. We present a novel method, DMRcate, that fits replicated methylation measurements from the Illumina HM450K BeadChip (or 450K array) spatially across the genome using a Gaussian kernel. DMRcate identifies and ranks the most differentially methylated regions across the genome based on tunable kernel smoothing of the differential methylation (DM) signal. The method is agnostic to both genomic annotation and local change in the direction of the DM signal, removes the bias incurred from irregularly spaced methylation sites, and assigns significance to each DMR called via comparison to a null model. RESULTS: We show that, for both simulated and real data, the predictive performance of DMRcate is superior to those of Bumphunter and Probe Lasso, and commensurate with that of comb-p. For the real data, we validate all array-derived DMRs from the candidate methods on a suite of DMRs derived from whole-genome bisulfite sequencing called from the same DNA samples, using two separate phenotype comparisons. CONCLUSIONS: The agglomeration of genomically localised individual methylation sites into discrete DMRs is currently best served by a combination of DM-signal smoothing and subsequent threshold specification. The findings also suggest the design of the 450K array shows preference for CpG sites that are more likely to be differentially methylated, but its overall coverage does not adequately reflect the depth and complexity of methylation signatures afforded by sequencing. For the convenience of the research community we have created a user-friendly R software package called DMRcate, downloadable from Bioconductor and compatible with existing preprocessing packages, which allows others to apply the same DMR-finding method on 450K array data.}, author = {Peters, Timothy J and Buckley, Michael J and Statham, Aaron L and Pidsley, Ruth and Samaras, Katherine and {V Lord}, Reginald and Clark, Susan J and Molloy, Peter L}, doi = {10.1186/1756-8935-8-6}, issn = {1756-8935}, journal = {Epigenetics {\&} chromatin}, keywords = {Animal Genetics and Genomics,Cell Biology,Human Genetics,Plant Genetics {\&} Genomics}, language = {En}, month = {jan}, number = {1}, pages = {6}, pmid = {25972926}, publisher = {BioMed Central}, title = {{De novo identification of differentially methylated regions in the human genome.}}, url = {http://epigeneticsandchromatin.biomedcentral.com/articles/10.1186/1756-8935-8-6}, volume = {8}, year = {2015} } @article{Jaffe2012, abstract = {BACKGROUND: During the past 5 years, high-throughput technologies have been successfully used by epidemiology studies, but almost all have focused on sequence variation through genome-wide association studies (GWAS). Today, the study of other genomic events is becoming more common in large-scale epidemiological studies. Many of these, unlike the single-nucleotide polymorphism studied in GWAS, are continuous measures. In this context, the exercise of searching for regions of interest for disease is akin to the problems described in the statistical 'bump hunting' literature. METHODS: New statistical challenges arise when the measurements are continuous rather than categorical, when they are measured with uncertainty, and when both biological signal, and measurement errors are characterized by spatial correlation along the genome. Perhaps the most challenging complication is that continuous genomic data from large studies are measured throughout long periods, making them susceptible to 'batch effects'. An example that combines all three characteristics is genome-wide DNA methylation measurements. Here, we present a data analysis pipeline that effectively models measurement error, removes batch effects, detects regions of interest and attaches statistical uncertainty to identified regions. RESULTS: We illustrate the usefulness of our approach by detecting genomic regions of DNA methylation associated with a continuous trait in a well-characterized population of newborns. Additionally, we show that addressing unexplained heterogeneity like batch effects reduces the number of false-positive regions. CONCLUSIONS: Our framework offers a comprehensive yet flexible approach for identifying genomic regions of biological interest in large epidemiological studies using quantitative high-throughput methods.}, author = {Jaffe, Andrew E and Murakami, Peter and Lee, Hwajin and Leek, Jeffrey T and Fallin, M Daniele and Feinberg, Andrew P and Irizarry, Rafael a}, doi = {10.1093/ije/dyr238}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Jaffe et al. - 2012 - Bump hunting to identify differentially methylated regions in epigenetic epidemiology studies.pdf:pdf}, issn = {1464-3685}, journal = {International journal of epidemiology}, keywords = {DNA Methylation,DNA Methylation: genetics,Epigenesis,Genetic,Genome-Wide Association Study,Genome-Wide Association Study: methods,Humans,Models,Statistical}, mendeley-groups = {450k Analysis}, month = {feb}, number = {1}, pages = {200--9}, pmid = {22422453}, title = {{Bump hunting to identify differentially methylated regions in epigenetic epidemiology studies.}}, url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3304533{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {41}, year = {2012} } @article{Wu2010, abstract = {The DNA of most vertebrates is depleted in CpG dinucleotide: a C followed by a G in the 5' to 3' direction. CpGs are the target for DNA methylation, a chemical modification of cytosine (C) heritable during cell division and the most well-characterized epigenetic mechanism. The remaining CpGs tend to cluster in regions referred to as CpG islands (CGI). Knowing CGI locations is important because they mark functionally relevant epigenetic loci in development and disease. For various mammals, including human, a readily available and widely used list of CGI is available from the UCSC Genome Browser. This list was derived using algorithms that search for regions satisfying a definition of CGI proposed by Gardiner-Garden and Frommer more than 20 years ago. Recent findings, enabled by advances in technology that permit direct measurement of epigenetic endpoints at a whole-genome scale, motivate the need to adapt the current CGI definition. In this paper, we propose a procedure, guided by hidden Markov models, that permits an extensible approach to detecting CGI. The main advantage of our approach over others is that it summarizes the evidence for CGI status as probability scores. This provides flexibility in the definition of a CGI and facilitates the creation of CGI lists for other species. The utility of this approach is demonstrated by generating the first CGI lists for invertebrates, and the fact that we can create CGI lists that substantially increases overlap with recently discovered epigenetic marks. A CGI list and the probability scores, as a function of genome location, for each species are available at http://www.rafalab.org.}, author = {Wu, Hao and Caffo, Brian and Jaffee, Harris A and Irizarry, Rafael A and Feinberg, Andrew P}, doi = {10.1093/biostatistics/kxq005}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Wu et al. - 2010 - Redefining CpG islands using hidden Markov models.pdf:pdf}, issn = {1468-4357}, journal = {Biostatistics (Oxford, England)}, keywords = {CpG Islands,CpG Islands: genetics,Epigenesis, Genetic,Epigenesis, Genetic: genetics,Genome, Human,Genome, Human: genetics,Humans,Markov Chains,Models, Genetic,Models, Statistical}, month = {jul}, number = {3}, pages = {499--514}, pmid = {20212320}, title = {{Redefining CpG islands using hidden Markov models.}}, url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=2883304{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {11}, year = {2010} } @article{Phipson2014, abstract = {Methylation of DNA is known to be essential to development and dramatically altered in cancers. The Illumina HumanMethylation450 BeadChip has been used extensively as a cost-effective way to profile nearly half a million CpG sites across the human genome. Here we present DiffVar, a novel method to test for differential variability between sample groups. DiffVar employs an empirical Bayes model framework that can take into account any experimental design and is robust to outliers. We applied DiffVar to several datasets from The Cancer Genome Atlas, as well as an aging dataset. DiffVar is available in the missMethyl Bioconductor R package.}, author = {Phipson, Belinda and Oshlack, Alicia}, doi = {10.1186/s13059-014-0465-4}, issn = {1474-760X}, journal = {Genome biology}, keywords = {Aging,Aging: genetics,Bayes Theorem,Computer Simulation,CpG Islands,DNA Methylation,Genetic Variation,Genome, Human,Humans,Models, Genetic,Neoplasms,Neoplasms: genetics,Sequence Analysis, DNA,Software}, language = {En}, month = {jan}, number = {9}, pages = {465}, pmid = {25245051}, publisher = {BioMed Central}, title = {{DiffVar: a new method for detecting differential variability with application to methylation in cancer and aging.}}, url = {http://genomebiology.biomedcentral.com/articles/10.1186/s13059-014-0465-4}, volume = {15}, year = {2014} } @article{Heyn2012, abstract = {Human aging cannot be fully understood in terms of the con- strained genetic setting. Epigenetic drift is an alternative means of explaining age-associated alterations. To address this issue, we performed whole-genome bisulfite sequencing (WGBS) of new- born and centenarian genomes. The centenarian DNA had a lower DNA methylation content and a reduced correlation in the methyl- ation status of neighboring cytosine—phosphate—guanine (CpGs) throughout the genome in comparison with the more homoge- neously methylated newborn DNA. The more hypomethylated CpGs observed in the centenarian DNA compared with the neonate covered all genomic compartments, such as promoters, exonic, intronic, and intergenic regions. For regulatory regions, the most hypomethylated sequences in the centenarian DNA were present mainly at CpG-poor promoters and in tissue-specific genes, whereas a greater level of DNA methylation was observed in CpG island promoters. We extended the study to a larger cohort of newborn and nonagenarian samples using a 450,000 CpG-site DNA methylation microarray that reinforced the observation of more hypomethylated DNA sequences in the advanced age group. WGBS and 450,000 analyses of middle-age individuals demon- strated DNA methylomes in the crossroad between the newborn and the nonagenarian/centenarian groups. Our study constitutes a unique DNA methylation analysis of the extreme points of human life at a single-nucleotide resolution level.}, author = {Heyn, Holger and Li, Ning and Ferreira, HJ Humberto J and Moran, Sebastian and Pisano, David G and Gomez, Antonio and Diez, Javier}, doi = {10.1073/pnas.1120658109/-/DCSupplemental.www.pnas.org/cgi/doi/10.1073/pnas.1120658109}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Heyn et al. - 2012 - Distinct DNA methylomes of newborns and centenarians.pdf:pdf}, journal = {Proceedings of the National Academy of Sciences of the United States of America}, keywords = {newborns,tinct dna methylomes of}, mendeley-groups = {Methylation/EWAS}, number = {26}, pages = {10522--10527}, title = {{Distinct DNA methylomes of newborns and centenarians}}, url = {http://www.pnas.org/content/109/26/10522.short}, volume = {109}, year = {2012} } @article{Jaffe2014, abstract = {BACKGROUND: Epigenome-wide association studies of human disease and other quantitative traits are becoming increasingly common. A series of papers reporting age-related changes in DNA methylation profiles in peripheral blood have already been published. However, blood is a heterogeneous collection of different cell types, each with a very different DNA methylation profile. RESULTS: Using a statistical method that permits estimating the relative proportion of cell types from DNA methylation profiles, we examine data from five previously published studies, and find strong evidence of cell composition change across age in blood. We also demonstrate that, in these studies, cellular composition explains much of the observed variability in DNA methylation. Furthermore, we find high levels of confounding between age-related variability and cellular composition at the CpG level. CONCLUSIONS: Our findings underscore the importance of considering cell composition variability in epigenetic studies based on whole blood and other heterogeneous tissue sources. We also provide software for estimating and exploring this composition confounding for the Illumina 450k microarray.}, author = {Jaffe, Andrew E and Irizarry, Rafael a}, doi = {10.1186/gb-2014-15-2-r31}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Jaffe, Irizarry - 2014 - Accounting for cellular heterogeneity is critical in epigenome-wide association studies.pdf:pdf}, issn = {1465-6914}, journal = {Genome biology}, keywords = {accounting for cellular heterogeneity,association,available soon,copyedited and,full text,fully formatted pdf and,html,is critical in epigenome-wide,it appeared upon acceptance,ome biology,this provisional pdf corresponds,to the article as,versions will be made}, mendeley-groups = {450k Analysis}, month = {feb}, number = {2}, pages = {R31}, pmid = {24495553}, title = {{Accounting for cellular heterogeneity is critical in epigenome-wide association studies.}}, url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=4053810{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {15}, year = {2014} } @article{Houseman2012, abstract = {BACKGROUND: There has been a long-standing need in biomedical research for a method that quantifies the normally mixed composition of leukocytes beyond what is possible by simple histological or flow cytometric assessments. The latter is restricted by the labile nature of protein epitopes, requirements for cell processing, and timely cell analysis. In a diverse array of diseases and following numerous immune-toxic exposures, leukocyte composition will critically inform the underlying immuno-biology to most chronic medical conditions. Emerging research demonstrates that DNA methylation is responsible for cellular differentiation, and when measured in whole peripheral blood, serves to distinguish cancer cases from controls. RESULTS: Here we present a method, similar to regression calibration, for inferring changes in the distribution of white blood cells between different subpopulations (e.g. cases and controls) using DNA methylation signatures, in combination with a previously obtained external validation set consisting of signatures from purified leukocyte samples. We validate the fundamental idea in a cell mixture reconstruction experiment, then demonstrate our method on DNA methylation data sets from several studies, including data from a Head and Neck Squamous Cell Carcinoma (HNSCC) study and an ovarian cancer study. Our method produces results consistent with prior biological findings, thereby validating the approach. CONCLUSIONS: Our method, in combination with an appropriate external validation set, promises new opportunities for large-scale immunological studies of both disease states and noxious exposures.}, author = {Houseman, Eugene Andres and Accomando, William P and Koestler, Devin C and Christensen, Brock C and Marsit, Carmen J and Nelson, Heather H and Wiencke, John K and Kelsey, Karl T}, doi = {10.1186/1471-2105-13-86}, issn = {1471-2105}, journal = {BMC bioinformatics}, month = {jan}, number = {1}, pages = {86}, pmid = {22568884}, title = {{DNA methylation arrays as surrogate measures of cell mixture distribution.}}, volume = {13}, year = {2012} } @article{Fortin2015, abstract = {Analysis of Hi-C data has shown that the genome can be divided into twocompartments called A/B compartments. These compartments are cell-type specific and are associated with open and closed chromatin. We show that A/B compartments can reliably be estimated using epigenetic data from several different platforms: the Illumina 450k DNA methylation microarray, DNase hypersensitivity sequencing, single-cell ATAC sequencing and single-cell whole-genome bisulfite sequencing. We do this by exploiting that the structure of long-range correlations differs between open and closed compartments. This work makes A/B compartment assignment readily available in a wide variety of cell types, including many human cancers.}, author = {Fortin, JP and Hansen, KD}, doi = {10.1186/s13059-015-0741-y}, file = {::}, issn = {1474-760X}, journal = {Genome biology}, keywords = {Animal Genetics and Genomics,Bioinformatics,Evolutionary Biology,Human Genetics,Microbial Genetics and Genomics,Plant Genetics {\&} Genomics}, language = {En}, month = {aug}, number = {1}, pages = {180}, pmid = {26316348}, publisher = {BioMed Central}, title = {{Reconstructing A/B compartments as revealed by Hi-C using long-range correlations in epigenetic data.}}, url = {http://genomebiology.biomedcentral.com/articles/10.1186/s13059-015-0741-y}, volume = {16}, year = {2015} } @article{Hansen2011, abstract = {Tumor heterogeneity is a major barrier to effective cancer diagnosis and treatment. We recently identified cancer-specific differentially DNA-methylated regions (cDMRs) in colon cancer, which also distinguish normal tissue types from each other, suggesting that these cDMRs might be generalized across cancer types. Here we show stochastic methylation variation of the same cDMRs, distinguishing cancer from normal tissue, in colon, lung, breast, thyroid and Wilms' tumors, with intermediate variation in adenomas. Whole-genome bisulfite sequencing shows these variable cDMRs are related to loss of sharply delimited methylation boundaries at CpG islands. Furthermore, we find hypomethylation of discrete blocks encompassing half the genome, with extreme gene expression variability. Genes associated with the cDMRs and large blocks are involved in mitosis and matrix remodeling, respectively. We suggest a model for cancer involving loss of epigenetic stability of well-defined genomic domains that underlies increased methylation variability in cancer that may contribute to tumor heterogeneity.}, author = {Hansen, Kasper Daniel and Timp, Winston and Bravo, H{\'{e}}ctor Corrada and Sabunciyan, Sarven and Langmead, Benjamin and McDonald, Oliver G and Wen, Bo and Wu, Hao and Liu, Yun and Diep, Dinh and Briem, Eirikur and Zhang, Kun and Irizarry, Rafael A and Feinberg, Andrew P}, doi = {10.1038/ng.865}, file = {::}, issn = {1546-1718}, journal = {Nature genetics}, keywords = {CpG Islands,CpG Islands: genetics,DNA Methylation,DNA, Neoplasm,DNA, Neoplasm: genetics,Epigenomics,Gene Expression Profiling,Gene Expression Regulation, Neoplastic,Genetic Variation,Genetic Variation: genetics,Humans,Neoplasms,Neoplasms: classification,Neoplasms: genetics,Oligonucleotide Array Sequence Analysis,Promoter Regions, Genetic,Sulfites,Tumor Markers, Biological,Tumor Markers, Biological: genetics}, month = {aug}, number = {8}, pages = {768--75}, pmid = {21706001}, title = {{Increased methylation variation in epigenetic domains across cancer types.}}, url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3145050{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {43}, year = {2011} } @article{Maksimovic2015, abstract = {Due to their relatively low-cost per sample and broad, gene-centric coverage of CpGs across the human genome, Illumina's 450k arrays are widely used in large scale differential methylation studies. However, by their very nature, large studies are particularly susceptible to the effects of unwanted variation. The effects of unwanted variation have been extensively documented in gene expression array studies and numerous methods have been developed to mitigate these effects. However, there has been much less research focused on the appropriate methodology to use for accounting for unwanted variation in methylation array studies. Here we present a novel 2-stage approach using RUV-inverse in a differential methylation analysis of 450k data and show that it outperforms existing methods.}, author = {Maksimovic, Jovana and Gagnon-Bartsch, Johann A and Speed, Terence P and Oshlack, Alicia}, doi = {10.1093/nar/gkv526}, issn = {1362-4962}, journal = {Nucleic acids research}, month = {may}, pages = {gkv526--}, pmid = {25990733}, title = {{Removing unwanted variation in a differential methylation analysis of Illumina HumanMethylation450 array data.}}, url = {http://nar.oxfordjournals.org/content/early/2015/05/18/nar.gkv526.abstract}, year = {2015} } @article{Leek2012, abstract = {Heterogeneity and latent variables are now widely recognized as major sources of bias and variability in high-throughput experiments. The most well-known source of latent variation in genomic experiments are batch effects-when samples are processed on different days, in different groups or by different people. However, there are also a large number of other variables that may have a major impact on high-throughput measurements. Here we describe the sva package for identifying, estimating and removing unwanted sources of variation in high-throughput experiments. The sva package supports surrogate variable estimation with the sva function, direct adjustment for known batch effects with the ComBat function and adjustment for batch and latent variables in prediction problems with the fsva function.}, author = {Leek, Jeffrey T and Johnson, W Evan and Parker, Hilary S and Jaffe, Andrew E and Storey, John D}, doi = {10.1093/bioinformatics/bts034}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Leek et al. - 2012 - The sva package for removing batch effects and other unwanted variation in high-throughput experiments.pdf:pdf}, issn = {1367-4811}, journal = {Bioinformatics (Oxford, England)}, keywords = {Gene Expression Profiling,Genomics,High-Throughput Nucleotide Sequencing,Humans,Regression Analysis,Software,Urinary Bladder Neoplasms,Urinary Bladder Neoplasms: genetics}, month = {mar}, number = {6}, pages = {882--3}, pmid = {22257669}, title = {{The sva package for removing batch effects and other unwanted variation in high-throughput experiments.}}, url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3307112{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {28}, year = {2012} } @article{Teschendorff2011, abstract = {MOTIVATION: A common difficulty in large-scale microarray studies is the presence of confounding factors, which may significantly skew estimates of statistical significance, cause unreliable feature selection and high false negative rates. To deal with these difficulties, an algorithmic framework known as Surrogate Variable Analysis (SVA) was recently proposed. RESULTS: Based on the notion that data can be viewed as an interference pattern, reflecting the superposition of independent effects and random noise, we present a modified SVA, called Independent Surrogate Variable Analysis (ISVA), to identify features correlating with a phenotype of interest in the presence of potential confounding factors. Using simulated data, we show that ISVA performs well in identifying confounders as well as outperforming methods which do not adjust for confounding. Using four large-scale Illumina Infinium DNA methylation datasets subject to low signal to noise ratios and substantial confounding by beadchip effects and variable bisulfite conversion efficiency, we show that ISVA improves the identifiability of confounders and that this enables a framework for feature selection that is more robust to model misspecification and heterogeneous phenotypes. Finally, we demonstrate similar improvements of ISVA across four mRNA expression datasets. Thus, ISVA should be useful as a feature selection tool in studies that are subject to confounding. AVAILABILITY: An R-package isva is available from www.cran.r-project.org.}, author = {Teschendorff, Andrew E and Zhuang, Joanna and Widschwendter, Martin}, doi = {10.1093/bioinformatics/btr171}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Teschendorff, Zhuang, Widschwendter - 2011 - Independent surrogate variable analysis to deconvolve confounding factors in large-scale mi.pdf:pdf}, issn = {1367-4811}, journal = {Bioinformatics (Oxford, England)}, keywords = {Algorithms,Breast Neoplasms,Breast Neoplasms: genetics,Breast Neoplasms: metabolism,DNA Methylation,Female,Gene Expression Profiling,Gene Expression Profiling: methods,Humans,Male,Oligonucleotide Array Sequence Analysis,Oligonucleotide Array Sequence Analysis: methods,RNA, Messenger,RNA, Messenger: metabolism}, mendeley-groups = {Microarray analysis}, month = {jun}, number = {11}, pages = {1496--505}, pmid = {21471010}, title = {{Independent surrogate variable analysis to deconvolve confounding factors in large-scale microarray profiling studies.}}, url = {http://www.ncbi.nlm.nih.gov/pubmed/21471010}, volume = {27}, year = {2011} } @article{Bibikova2009, abstract = {AIMS: Bisulfite sequence analysis of individual CpG sites within genomic DNA is a powerful approach for methylation analysis in the genome. The major limitation of bisulfite-based methods is parallelization. Both array and next-generation sequencing technology are capable of addressing this bottleneck. In this report, we describe the application of Infinium{\textregistered} genotyping technology to analyze bisulfite-converted DNA to simultaneously query the methylation state of over 27,000 CpG sites from promoters of consensus coding sequences (CCDS) genes. MATERIALS {\&} METHODS: We adapted the Infinium genotyping assay to readout an array of over 27,000 pairs of CpG methylation-specific query probes complementary to bisulfite-converted DNA. Two probes were designed to each CpG site: a 'methylated' and an 'unmethylated' query probe. The probe design assumed that all underlying CpG sites were 'in phase' with the queried CpG site due to their close proximity. Bisulfite conversion was performed with a modified version of the Zymo EZ DNA Methylation™ kit. RESULTS: We applied this technology to measuring methylation levels across a panel of 14 different human tissues, four Coriell cell lines and six cancer cell lines. We observed that CpG sites within CpG islands (CGIs) were largely unmethylated across all tissues ({\~{}}80{\%} sites unmethylated, $\beta$ {\textless} 0.2), whereas CpG sites in non-CGIs were moderately to highly methylated (only {\~{}}12{\%} sites unmethylated, $\beta$ {\textless} 0.2). Within CGIs, only approximately 3-6{\%} of the loci were highly methylated; in contrast, outside of CGIs approximately 25-40{\%} of loci were highly methylated. Moreover, tissue-specific methylation (variation in methylation across tissues) was much more prevalent in non-CGIs than within CGIs. CONCLUSION: Our results demonstrate a genome-wide scalable array-based methylation readout platform that is both highly reproducible and quantitative. In the near future, this platform should enable the analysis of hundreds of thousands to millions of CpG sites per sample.}, author = {Bibikova, Marina and Le, Jennie and Barnes, Bret and Saedinia-Melnyk, Shadi and Zhou, Lixin and Shen, Richard and Gunderson, Kevin L}, doi = {10.2217/epi.09.14}, issn = {1750-192X}, journal = {Epigenomics}, keywords = {Cell Line, Tumor,Consensus Sequence,CpG Islands,DNA,DNA Methylation,DNA: chemistry,DNA: metabolism,Epigenomics,Epigenomics: methods,Genome, Human,HeLa Cells,Humans,Jurkat Cells,K562 Cells,Oligonucleotide Array Sequence Analysis,Promoter Regions, Genetic,Sequence Analysis, DNA,Sulfites,Sulfites: chemistry}, language = {EN}, month = {oct}, number = {1}, pages = {177--200}, pmid = {22122642}, publisher = {Future Medicine Ltd London, UK}, title = {{Genome-wide DNA methylation profiling using Infinium{\textregistered} assay.}}, url = {http://www.futuremedicine.com/doi/abs/10.2217/epi.09.14?url{\_}ver=Z39.88-2003{\&}rfr{\_}id=ori{\%}3Arid{\%}3Acrossref.org{\&}rfr{\_}dat=cr{\_}pub{\%}3Dwww.ncbi.nlm.nih.gov{\&}}, volume = {1}, year = {2009} } @article{Bibikova2011, abstract = {We have developed a new generation of genome-wide DNA methylation BeadChip which allows high-throughput methylation profiling of the human genome. The new high density BeadChip can assay over 480K CpG sites and analyze twelve samples in parallel. The innovative content includes coverage of 99{\%} of RefSeq genes with multiple probes per gene, 96{\%} of CpG islands from the UCSC database, CpG island shores and additional content selected from whole-genome bisulfite sequencing data and input from DNA methylation experts. The well-characterized Infinium{\textregistered} Assay is used for analysis of CpG methylation using bisulfite-converted genomic DNA. We applied this technology to analyze DNA methylation in normal and tumor DNA samples and compared results with whole-genome bisulfite sequencing (WGBS) data obtained for the same samples. Highly comparable DNA methylation profiles were generated by the array and sequencing methods (average R2 of 0.95). The ability to determine genome-wide methylation patterns will rapidly advance methylation research.}, author = {Bibikova, Marina and Barnes, Bret and Tsan, Chan and Ho, Vincent and Klotzle, Brandy and Le, Jennie M and Delano, David and Zhang, Lu and Schroth, Gary P and Gunderson, Kevin L and Fan, Jian-Bing and Shen, Richard}, doi = {10.1016/j.ygeno.2011.07.007}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Bibikova et al. - 2011 - High density DNA methylation array with single CpG site resolution.pdf:pdf}, issn = {1089-8646}, journal = {Genomics}, keywords = {CpG Islands,CpG Islands: genetics,DNA,DNA Methylation,DNA: methods,Epigenomics,Gene Expression Profiling,Genome,Human,Humans,Oligonucleotide Array Sequence Analysis,Oligonucleotide Array Sequence Analysis: methods,Sequence Analysis,Sulfites,Sulfites: chemistry}, mendeley-groups = {450k Analysis}, month = {oct}, number = {4}, pages = {288--95}, pmid = {21839163}, publisher = {Elsevier Inc.}, title = {{High density DNA methylation array with single CpG site resolution.}}, url = {http://www.ncbi.nlm.nih.gov/pubmed/21839163}, volume = {98}, year = {2011} } @article{Bird2002, author = {Bird, Adrian}, doi = {10.1101/gad.947102}, file = {::}, issn = {0890-9369}, journal = {Genes {\&} development}, keywords = {Animals,DNA Methylation,Embryonic and Fetal Development,Embryonic and Fetal Development: genetics,Gene Expression Regulation, Developmental,Gene Silencing,Humans,Transcription, Genetic}, month = {jan}, number = {1}, pages = {6--21}, pmid = {11782440}, title = {{DNA methylation patterns and epigenetic memory.}}, url = {http://genesdev.cshlp.org/content/16/1/6.long}, volume = {16}, year = {2002} } @article{Laird2003, abstract = {The past few years have seen an explosion of interest in the epigenetics of cancer. This has been a consequence of both the exciting coalescence of the chromatin and DNA methylation fields, and the realization that DNA methylation changes are involved in human malignancies. The ubiquity of DNA methylation changes has opened the way to a host of innovative diagnostic and therapeutic strategies. Recent advances attest to the great promise of DNA methylation markers as powerful future tools in the clinic.}, author = {Laird, Peter W}, doi = {10.1038/nrc1045}, file = {:C$\backslash$:/Users/jovana.maksimovic.MCRI/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Laird - 2003 - The power and the promise of DNA methylation markers.pdf:pdf}, issn = {1474-175X}, journal = {Nature reviews. Cancer}, keywords = {DNA Methylation,DNA, Neoplasm,DNA, Neoplasm: analysis,Genetic Markers,Humans,Neoplasms,Neoplasms: blood,Neoplasms: genetics,Sensitivity and Specificity,Tumor Markers, Biological,Tumor Markers, Biological: analysis}, mendeley-groups = {Methylation/EWAS}, month = {apr}, number = {4}, pages = {253--66}, pmid = {12671664}, title = {{The power and the promise of DNA methylation markers.}}, url = {http://www.ncbi.nlm.nih.gov/pubmed/12671664}, volume = {3}, year = {2003} } @article{Smith2013, author = {Smith, Mike L and Baggerly, Keith A. and Bengtsson, Henrik and Ritchie, Matthew E. and Hansen, Kasper D. and Smith, Mike L and Baggerly, Keith A. and Bengtsson, Henrik and Ritchie, Matthew E. and Hansen, Kasper D.}, doi = {10.12688/f1000research.2-264.v1}, issn = {2046-1402}, journal = {F1000Research}, month = {dec}, title = {{illuminaio: An open source IDAT parsing tool for Illumina microarrays}}, url = {http://f1000research.com/articles/2-264/v1}, volume = {2}, year = {2013} } @article{benjamini1995fdr, author = {Benjamini, Y and Hochberg, Y}, journal = {Journal of the Royal Statistical Society: Series B}, pages = {289--300}, title = {{Controlling the false discovery rate: a practical and powerful approach to multiple testing}}, volume = {57}, year = {1995} } @article{smyth2004ebayes, author = {Smyth, G K}, journal = {Statistical applications in genetics and molecular biology}, number = {1}, pages = {Article{\~{}}3}, publisher = {bepress}, title = {{Linear models and empirical Bayes methods for assessing differential expression in microarray experiments}}, volume = {3}, year = {2004} } @article{hicks2015quantro, title={quantro: a data-driven approach to guide the choice of an appropriate normalization method}, author={Hicks, Stephanie C and Irizarry, Rafael A}, journal={Genome biology}, volume={16}, number={1}, pages={1}, year={2015}, publisher={BioMed Central} } @article{lonnstedt2002replicated, author = {Lonnstedt, I and Speed, T}, journal = {Statistica Sinica}, pages = {31--46}, title = {{Replicated Microarray Data}}, volume = {12}, year = {2002} } @article{Hansen2011, abstract = {Tumor heterogeneity is a major barrier to effective cancer diagnosis and treatment. We recently identified cancer-specific differentially DNA-methylated regions (cDMRs) in colon cancer, which also distinguish normal tissue types from each other, suggesting that these cDMRs might be generalized across cancer types. Here we show stochastic methylation variation of the same cDMRs, distinguishing cancer from normal tissue, in colon, lung, breast, thyroid and Wilms' tumors, with intermediate variation in adenomas. Whole-genome bisulfite sequencing shows these variable cDMRs are related to loss of sharply delimited methylation boundaries at CpG islands. Furthermore, we find hypomethylation of discrete blocks encompassing half the genome, with extreme gene expression variability. Genes associated with the cDMRs and large blocks are involved in mitosis and matrix remodeling, respectively. We suggest a model for cancer involving loss of epigenetic stability of well-defined genomic domains that underlies increased methylation variability in cancer that may contribute to tumor heterogeneity.}, author = {Hansen, Kasper Daniel and Timp, Winston and Bravo, H{\'{e}}ctor Corrada and Sabunciyan, Sarven and Langmead, Benjamin and McDonald, Oliver G and Wen, Bo and Wu, Hao and Liu, Yun and Diep, Dinh and Briem, Eirikur and Zhang, Kun and Irizarry, Rafael a and Feinberg, Andrew P}, doi = {10.1038/ng.865}, file = {:D$\backslash$:/{\_}MCRI/{\_}Research projects/Differential Variability/DiffMethVarNatureGen.pdf:pdf}, issn = {1546-1718}, journal = {Nature genetics}, keywords = {CpG Islands,CpG Islands: genetics,DNA Methylation,DNA, Neoplasm,DNA, Neoplasm: genetics,Epigenomics,Gene Expression Profiling,Gene Expression Regulation, Neoplastic,Genetic Variation,Genetic Variation: genetics,Humans,Neoplasms,Neoplasms: classification,Neoplasms: genetics,Oligonucleotide Array Sequence Analysis,Promoter Regions, Genetic,Sulfites,Tumor Markers, Biological,Tumor Markers, Biological: genetics}, month = {aug}, number = {8}, pages = {768--75}, pmid = {21706001}, publisher = {Nature Publishing Group}, title = {{Increased methylation variation in epigenetic domains across cancer types.}}, url = {http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=3145050{\&}tool=pmcentrez{\&}rendertype=abstract}, volume = {43}, year = {2011} }