@article{Chevrier2017,
abstract = {Mass cytometry enables simultaneous analysis of over 40 proteins and their modifications in single cells through use of metal-tagged antibodies. Compared to fluorescent dyes, the use of pure metal isotopes strongly reduces spectral overlap among measurement channels. Crosstalk still exists, however, caused by isotopic impurity, oxide formation, and mass cytometer properties. Spillover effects can be minimized, but not avoided, by following a set of constraining rules when designing an antibody panel. Generation of such low crosstalk panels requires considerable expert knowledge, knowledge of the abundance of each marker and substantial experimental effort. Here we describe a novel bead-based compensation workflow that includes R-based software and a web tool, which enables correction for interference between channels. We demonstrate utility in suspension mass cytometry and show how this approach can be applied to imaging mass cytometry. Our approach greatly simplifies the development of new antibody panels, increases flexibility for antibody-metal pairing, improves overall data quality, thereby reducing the risk of reporting cell phenotype and function artifacts, and greatly facilitates analysis of complex samples for which antigen abundances are unknown.},
author = {Chevrier, Stephane and Crowell, Helena and Zanotelli, Vito Riccardo Tomaso and Engler, Stefanie and Robinson, Mark D and Bodenmiller, Bernd},
doi = {10.1101/185744},
file = {:Users/gosia/Documents/Mendeley Desktop/Chevrier et al/Chevrier et al. - 2017 - Channel crosstalk correction in suspension and imaging mass cytometry.pdf:pdf},
journal = {bioRxiv},
keywords = {CATALYST},
mendeley-groups = {Single cell/Compensation,.cytofWorkflow},
mendeley-tags = {CATALYST},
publisher = {Cold Spring Harbor Laboratory},
title = {{Channel crosstalk correction in suspension and imaging mass cytometry}},
url = {http://www.biorxiv.org/content/early/2017/09/07/185744},
year = {2017}
}


  @Manual{Finak2011,
    title = {flowWorkspace: Infrastructure for representing and interacting with the gated
cytometry},
    author = {Greg Finak and Mike Jiang},
    year = {2011},
    note = {R package version 3.24.4},
  }

@article{Finak2014b,
author = {Finak, Greg and Frelinger, Jacob and Jiang, Wenxin and Newell, Evan W EW and Ramey, John and Davis, Mark MM and Kalams, SA Spyros a and {De Rosa}, SC Stephen C and Gottardo, Raphael},
doi = {10.1371/journal.pcbi.1003806},
isbn = {1210190109},
issn = {1553-7358},
journal = {PLoS Computational Biology},
keywords = {an open source infrastructure,and,corresponding author,for scalable,opencyto,pcompbiol-d-14-00539r2,reproducible,robust},
mendeley-groups = {.cytofWorkflow},
number = {8},
pages = {e1003806},
title = {{OpenCyto: An Open Source Infrastructure for Scalable, Robust, Reproducible, and Automated, End-to-End Flow Cytometry Data Analysis}},
volume = {10},
year = {2014}
}


@article{Lin2015b,
abstract = {Advances in flow cytometry and other single-cell technologies have enabled high-dimensional, high-throughput measurements of individual cells as well as the interrogation of cell population heterogeneity. However, in many instances, computational tools to analyze the wealth of data generated by these technologies are lacking. Here, we present a computational framework for unbiased combinatorial polyfunctionality analysis of antigen-specific T-cell subsets (COMPASS). COMPASS uses a Bayesian hierarchical framework to model all observed cell subsets and select those most likely to have antigen-specific responses. Cell-subset responses are quantified by posterior probabilities, and human subject-level responses are quantified by two summary statistics that describe the quality of an individual's polyfunctional response and can be correlated directly with clinical outcome. Using three clinical data sets of cytokine production, we demonstrate how COMPASS improves characterization of antigen-specific T cells and reveals cellular 'correlates of protection/immunity' in the RV144 HIV vaccine efficacy trial that are missed by other methods. COMPASS is available as open-source software.},
author = {Lin, Lin and Finak, Greg and Ushey, Kevin and Seshadri, Chetan and Hawn, Thomas R and Frahm, Nicole and Scriba, Thomas J and Mahomed, Hassan and Hanekom, Willem and Bart, Pierre-Alexandre and Pantaleo, Giuseppe and Tomaras, Georgia D and Rerks-Ngarm, Supachai and Kaewkungwal, Jaranit and Nitayaphan, Sorachai and Pitisuttithum, Punnee and Michael, Nelson L and Kim, Jerome H and Robb, Merlin L and O'Connell, Robert J and Karasavvas, Nicos and Gilbert, Peter and {C De Rosa}, Stephen and McElrath, M Juliana and Gottardo, Raphael},
file = {:Users/gosia/Documents/Mendeley Desktop/Lin et al/Lin et al. - 2015 - COMPASS identifies T-cell subsets correlated with clinical outcomes.pdf:pdf},
issn = {1087-0156},
journal = {Nat Biotech},
mendeley-groups = {.cytofWorkflow},
month = {jun},
number = {6},
pages = {610--616},
publisher = {Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.},
title = {{COMPASS identifies T-cell subsets correlated with clinical outcomes}},
url = {http://dx.doi.org/10.1038/nbt.3187 http://10.0.4.14/nbt.3187 http://www.nature.com/nbt/journal/v33/n6/abs/nbt.3187.html{\#}supplementary-information},
volume = {33},
year = {2015}
}


@article{Finak2014,
author = {Finak, Greg and McDavid, Andrew and Chattopadhyay, Pratip and Dominguez, Maria and {De Rosa}, Steve and Roederer, Mario and Gottardo, Raphael},
doi = {10.1093/biostatistics/kxt024},
file = {:Users/gosia/Documents/Mendeley Desktop/Finak et al/Finak et al. - 2014 - Mixture models for single-cell assays with applications to vaccine studies(2).pdf:pdf},
journal = {Biostatistics},
mendeley-groups = {.cytofWorkflow,Single cell/Differential analysis},
number = {1},
pages = {87--101},
title = {{Mixture models for single-cell assays with applications to vaccine studies}},
url = {+ http://dx.doi.org/10.1093/biostatistics/kxt024},
volume = {15},
year = {2014}
}


@article{Lin2015a,
abstract = {An important aspect of immune monitoring for vaccine development, clinical trials, and research is the detection, measurement, and comparison of antigen-specific T-cells from subject samples under different conditions. Antigen-specific T-cells compose a very small fraction of total T-cells. Developments in cytometry technology over the past five years have enabled the measurement of single-cells in a multivariate and high-throughput manner. This growth in both dimensionality and quantity of data continues to pose a challenge for effective identification and visualization of rare cell subsets, such as antigen-specific T-cells. Dimension reduction and feature extraction play pivotal role in both identifying and visualizing cell populations of interest in large, multi-dimensional cytometry datasets. However, the automated identification and visualization of rare, high-dimensional cell subsets remains challenging. Here we demonstrate how a systematic and integrated approach combining targeted feature extraction with dimension reduction can be used to identify and visualize biological differences in rare, antigen-specific cell populations. By using OpenCyto to perform semi-automated gating and features extraction of flow cytometry data, followed by dimensionality reduction with t-SNE we are able to identify polyfunctional subpopulations of antigen-specific T-cells and visualize treatment-specific differences between them. {\textcopyright} 2015 The Authors. Published by Wiley Periodicals, Inc.},
author = {Lin, Lin and Frelinger, Jacob and Jiang, Wenxin and Finak, Greg and Seshadri, Chetan and Bart, Pierre-Alexandre and Pantaleo, Giuseppe and McElrath, Julie and DeRosa, Steve and Gottardo, Raphael},
doi = {10.1002/cyto.a.22623},
file = {:Users/gosia/Documents/Mendeley Desktop/Lin et al/Lin et al. - 2015 - Identification and visualization of multidimensional antigen-specific T-cell populations in polychromatic cytometry.pdf:pdf},
issn = {1552-4930},
journal = {Cytometry Part A},
keywords = {antigen-specific T cells,automated gating,dimension reduction,intracellular cytokine staining,polyfunctionality,visualization},
mendeley-groups = {.cytofWorkflow},
number = {7},
pages = {675--682},
title = {{Identification and visualization of multidimensional antigen-specific T-cell populations in polychromatic cytometry data}},
url = {http://dx.doi.org/10.1002/cyto.a.22623},
volume = {87},
year = {2015}
}

@article{Tang2016,
author = {Tang, Jian and Liu, Jingzhou and Zhang, Ming and Mei, Qiaozhu},
journal = {CoRR},
mendeley-groups = {Single cell/Dimention reduction},
title = {{Visualization Large-scale and High-dimensional Data}},
url = {http://arxiv.org/abs/1602.00370},
volume = {abs/1602.00370},
year = {2016}
}


@article{Hahne2009,
abstract = {Recent advances in automation technologies have enabled the use of flow cytometry for high throughput screening, generating large complex data sets often in clinical trials or drug discovery settings. However, data management and data analysis methods have not advanced sufficiently far from the initial small-scale studies to support modeling in the presence of multiple covariates.},
author = {Hahne, Florian and LeMeur, Nolwenn and Brinkman, Ryan R and Ellis, Byron and Haaland, Perry and Sarkar, Deepayan and Spidlen, Josef and Strain, Errol and Gentleman, Robert},
doi = {10.1186/1471-2105-10-106},
issn = {1471-2105},
journal = {BMC Bioinformatics},
keywords = {flowCore},
mendeley-groups = {.cytofWorkflow},
mendeley-tags = {flowCore},
month = {apr},
number = {1},
pages = {106},
title = {{flowCore: a Bioconductor package for high throughput flow cytometry}},
url = {https://doi.org/10.1186/1471-2105-10-106},
volume = {10},
year = {2009}
}


@article{Lun2017,
author = {Lun, Aaron T L and Richard, Arianne C and Marioni, John C},
issn = {1548-7091},
journal = {Nat Meth},
keywords = {cydar},
mendeley-groups = {.cytofWorkflow},
mendeley-tags = {cydar},
month = {jul},
number = {7},
pages = {707--709},
publisher = {Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.},
title = {{Testing for differential abundance in mass cytometry data}},
url = {http://dx.doi.org/10.1038/nmeth.4295 http://10.0.4.14/nmeth.4295 http://www.nature.com/nmeth/journal/v14/n7/abs/nmeth.4295.html{\#}supplementary-information},
volume = {14},
year = {2017}
}



@article{Angerer2016,
abstract = {Summary: Diffusion maps are a spectral method for non-linear dimension reduction and have recently been adapted for the visualization of single-cell expression data. Here we present destiny, an efficient R implementation of the diffusion map algorithm. Our package includes a single-cell specific noise model allowing for missing and censored values. In contrast to previous implementations, we further present an efficient nearest-neighbour approximation that allows for the processing of hundreds of thousands of cells and a functionality for projecting new data on existing diffusion maps. We exemplarily apply destiny to a recent time-resolved mass cytometry dataset of cellular reprogramming.Availability and implementation: destiny is an open-source R/Bioconductor package “bioconductor.org/packages/destiny” also available at www.helmholtz-muenchen.de/icb/destiny. A detailed vignette describing functions and workflows is provided with the package.Contact: carsten.marr@helmholtz-muenchen.de or f.buettner@helmholtz-muenchen.deSupplementary information: Supplementary data are available at Bioinformatics online.},
annote = {10.1093/bioinformatics/btv715},
author = {Angerer, Philipp and Haghverdi, Laleh and B{\"{u}}ttner, Maren and Theis, Fabian J and Marr, Carsten and Buettner, Florian},
doi = {10.1093/bioinformatics/btv715},
file = {:Users/gosia/Documents/Mendeley Desktop/Angerer et al/Angerer et al. - 2016 - destiny diffusion maps for large-scale single-cell data in R.pdf:pdf;:Users/gosia/Documents/Mendeley Desktop/Angerer et al/Angerer et al. - 2016 - destiny diffusion maps for large-scale single-cell data in R(2).pdf:pdf},
journal = {Bioinformatics},
keywords = {destiny},
mendeley-groups = {Single cell/Diffusion maps,Single cell,.cytofWorkflow},
mendeley-tags = {destiny},
month = {apr},
number = {8},
pages = {1241--1243},
title = {{destiny: diffusion maps for large-scale single-cell data in R}},
url = {http://bioinformatics.oxfordjournals.org/content/32/8/1241.abstract},
volume = {32},
year = {2016}
}
@article{Haghverdi2015,
abstract = {MOTIVATION: Single-cell technologies have recently gained popularity in cellular differentiation studies regarding their ability to resolve potential heterogeneities in cell populations. Analysing such high-dimensional single-cell data has its own statistical and computational challenges. Popular multivariate approaches are based on data normalisation, followed by dimension reduction and clustering to identify subgroups. However, in the case of cellular differentiation, we would not expect clear clusters to be present but instead expect the cells to follow continuous branching lineages. RESULTS: Here we propose the use of diffusion maps to deal with the problem of defining differentiation trajectories. We adapt this method to single-cell data by adequate choice of kernel width and inclusion of uncertainties or missing measurement values, which enables the establishment of a pseudo-temporal ordering of single cells in a high-dimensional gene expression space. We expect this output to reflect cell differentiation trajectories, where the data originates from intrinsic diffusion-like dynamics. Starting from a pluripotent stage, cells move smoothly within the transcriptional landscape towards more differentiated states with some stochasticity along their path. We demonstrate the robustness of our method with respect to extrinsic noise (e.g. measurement noise) and sampling density heterogeneities on simulated toy data as well as two single-cell quantitative polymerase chain reaction (qPCR) data sets (i.e. mouse haematopoietic stem cells and mouse embryonic stem cells) and an RNA-Seq data of human pre-implantation embryos. We show that diffusion maps perform considerably better than Principal Component Analysis (PCA) and are advantageous over other techniques for non-linear dimension reduction such as t-distributed Stochastic Neighbour Embedding (t-SNE) for preserving the global structures and pseudotemporal ordering of cells. AVAILABILITY: The Matlab implementation of diffusion maps for single-cell data is available at https://www.helmholtz-muenchen.de/icb/single-cell-diffusion-map. CONTACT: fbuettner.phys@gmail.com, fabian.theis@helmholtz-muenchen.de.},
author = {Haghverdi, L. and Buettner, F. and Theis, F. J.},
doi = {10.1093/bioinformatics/btv325},
file = {:Users/gosia/Documents/Mendeley Desktop/Haghverdi, Buettner, Theis/Haghverdi, Buettner, Theis - 2015 - Diffusion maps for high-dimensional single-cell analysis of differentiation data.pdf:pdf},
issn = {1367-4803},
journal = {Bioinformatics},
keywords = {destiny},
mendeley-groups = {Single cell/Diffusion maps,.cytofWorkflow},
mendeley-tags = {destiny},
number = {May},
pages = {2989--2998},
pmid = {26002886},
title = {{Diffusion maps for high-dimensional single-cell analysis of differentiation data}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/26002886},
volume = {31},
year = {2015}
}


@article{Aghaeepour2013,
annote = {10.1038/nmeth.2365},
author = {Aghaeepour, Nima and Finak, Greg and Hoos, Holger and Mosmann, Tim R and Brinkman, Ryan and Gottardo, Raphael and Scheuermann, Richard H},
issn = {1548-7091},
journal = {Nat Meth},
keywords = {FlowCAP I,FlowCAP II},
mendeley-groups = {.cytofWorkflow},
mendeley-tags = {FlowCAP I,FlowCAP II},
month = {mar},
number = {3},
pages = {228--238},
publisher = {Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.},
title = {{Critical assessment of automated flow cytometry data analysis techniques}},
url = {http://dx.doi.org/10.1038/nmeth.2365 http://www.nature.com/nmeth/journal/v10/n3/abs/nmeth.2365.html{\#}supplementary-information},
volume = {10},
year = {2013}
}

@article{Arvaniti2016,
author = {Arvaniti, Eirini and Claassen, Manfred},
journal = {Nature Communications},
keywords = {CellCnn},
mendeley-groups = {.cytofWorkflow},
mendeley-tags = {CellCnn},
month = {apr},
pages = {14825},
publisher = {The Author(s)},
title = {{Sensitive detection of rare disease-associated cell subsets via representation learning}},
url = {http://dx.doi.org/10.1038/ncomms14825 http://10.0.4.14/ncomms14825 https://www.nature.com/articles/ncomms14825{\#}supplementary-information},
volume = {8},
year = {2017}
}



@article{Bandura2009,
annote = {doi: 10.1021/ac901049w},
author = {Bandura, Dmitry R and Baranov, Vladimir I and Ornatsky, Olga I and Antonov, Alexei and Kinach, Robert and Lou, Xudong and Pavlov, Serguei and Vorobiev, Sergey and Dick, John E and Tanner, Scott D},
doi = {10.1021/ac901049w},
issn = {0003-2700},
journal = {Analytical Chemistry},
mendeley-groups = {.cytofWorkflow},
month = {aug},
number = {16},
pages = {6813--6822},
publisher = {American Chemical Society},
title = {{Mass Cytometry: Technique for Real Time Single Cell Multitarget Immunoassay Based on Inductively Coupled Plasma Time-of-Flight Mass Spectrometry}},
url = {http://dx.doi.org/10.1021/ac901049w},
volume = {81},
year = {2009}
}
@article{Bendall2014,
abstract = {Tissue regeneration is an orchestrated progression of cells from an immature state to a mature one, conventionally represented as distinctive cell subsets. A continuum of transitional cell states exists between these discrete stages. We combine the depth of single-cell mass cytometry and an algorithm developed to leverage this continuum by aligning single cells of a given lineage onto a unified trajectory that accurately predicts the developmental path de novo. Applied to human B cell lymphopoiesis, the algorithm (termed Wanderlust) constructed trajectories spanning from hematopoietic stem cells through to naive B cells. This trajectory revealed nascent fractions of B cell progenitors and aligned them with developmentally cued regulatory signaling including IL-7/STAT5 and cellular events such as immunoglobulin rearrangement, highlighting checkpoints across which regulatory signals are rewired paralleling changes in cellular state. This study provides a comprehensive analysis of human B lymphopoiesis, laying a foundation to apply this approach to other tissues and "corrupted" developmental processes including cancer.},
author = {Bendall, Sean C and Davis, Kara L and Amir, El-Ad David and Tadmor, Michelle D and Simonds, Erin F and Chen, Tiffany J and Shenfeld, Daniel K and Nolan, Garry P and Pe'er, Dana},
doi = {10.1016/j.cell.2014.04.005},
file = {:Users/gosia/Documents/Mendeley Desktop/Bendall et al/Bendall et al. - 2014 - Single-cell trajectory detection uncovers progression and regulatory coordination in human B cell development.pdf:pdf;:Users/gosia/Documents/Mendeley Desktop/Bendall et al/Bendall et al. - 2014 - Single-cell trajectory detection uncovers progression and regulatory coordination in human B cell development(2).pdf:pdf},
issn = {1097-4172},
journal = {Cell},
keywords = {Algorithms,B-Lymphocytes,B-Lymphocytes: cytology,B-Lymphoid,B-Lymphoid: cytology,Humans,Interleukin-7,Interleukin-7: metabolism,Lymphopoiesis,Precursor Cells,STAT5 Transcription Factor,STAT5 Transcription Factor: metabolism,V(D)J Recombination,Wanderlust},
language = {English},
mendeley-groups = {Single cell,Single cell/Pseudotime/trajectories,.cytofWorkflow},
mendeley-tags = {Wanderlust},
month = {apr},
number = {3},
pages = {714--25},
pmid = {24766814},
publisher = {Elsevier},
title = {{Single-cell trajectory detection uncovers progression and regulatory coordination in human B cell development.}},
url = {http://www.cell.com/article/S0092867414004711/fulltext},
volume = {157},
year = {2014}
}
@article{Bendall687,
abstract = {Flow cytometry is an essential tool for dissecting the functional complexity of hematopoiesis. We used single-cell {\{}$\backslash$textquotedblleft{\}}mass cytometry{\{}$\backslash$textquotedblright{\}} to examine healthy human bone marrow, measuring 34 parameters simultaneously in single cells (binding of 31 antibodies, viability, DNA content, and relative cell size). The signaling behavior of cell subsets spanning a defined hematopoietic hierarchy was monitored with 18 simultaneous markers of functional signaling states perturbed by a set of ex vivo stimuli and inhibitors. The data set allowed for an algorithmically driven assembly of related cell types defined by surface antigen expression, providing a superimposable map of cell signaling responses in combination with drug inhibition. Visualized in this manner, the analysis revealed previously unappreciated instances of both precise signaling responses that were bounded within conventionally defined cell subsets and more continuous phosphorylation responses that crossed cell population boundaries in unexpected manners yet tracked closely with cellular phenotype. Collectively, such single-cell analyses provide system-wide views of immune signaling in healthy human hematopoiesis, against which drug action and disease can be compared for mechanistic studies and pharmacologic intervention.},
author = {Bendall, Sean C and Simonds, Erin F and Qiu, Peng and Amir, El-ad D and Krutzik, Peter O and Finck, Rachel and Bruggner, Robert V and Melamed, Rachel and Trejo, Angelica and Ornatsky, Olga I and Balderas, Robert S and Plevritis, Sylvia K and Sachs, Karen and Pe$\backslash$textquoterighter, Dana and Tanner, Scott D and Nolan, Garry P},
doi = {10.1126/science.1198704},
issn = {0036-8075},
journal = {Science},
mendeley-groups = {CyTOF {\&} flow cytometry,.cytofWorkflow},
number = {6030},
pages = {687--696},
publisher = {American Association for the Advancement of Science},
title = {{Single-Cell Mass Cytometry of Differential Immune and Drug Responses Across a Human Hematopoietic Continuum}},
url = {http://science.sciencemag.org/content/332/6030/687},
volume = {332},
year = {2011}
}
@article{Bodenmiller2012,
author = {Bodenmiller, Bernd and Zunder, Eli R and Finck, Rachel and Chen, Tiffany J and Savig, Erica S and Bruggner, Robert V and Simonds, Erin F and Bendall, Sean C and Sachs, Karen and Krutzik, Peter O and Nolan, Garry P},
doi = {10.1038/nbt.2317},
file = {:Users/gosia/Documents/Mendeley Desktop/Bodenmiller et al/Bodenmiller et al. - 2012 - Multiplexed mass cytometry profiling of cellular states perturbed by small-molecule regulators.pdf:pdf;:Users/gosia/Documents/Mendeley Desktop/Bodenmiller et al/Bodenmiller et al. - 2012 - Multiplexed mass cytometry profiling of cellular states perturbed by small-molecule regulators(2).pdf:pdf},
isbn = {1855387298},
issn = {1087-0156},
journal = {Nature Biotechnology},
mendeley-groups = {Single cell,CyTOF {\&} flow cytometry/Data,.cytofWorkflow},
number = {9},
pages = {858--867},
pmid = {22902532},
publisher = {Nature Publishing Group},
title = {{Multiplexed mass cytometry profiling of cellular states perturbed by small-molecule regulators}},
url = {http://dx.doi.org/10.1038/nbt.2317},
volume = {30},
year = {2012}
}
@article{Bruggner2014,
abstract = {Elucidation and examination of cellular subpopulations that display condition-specific behavior can play a critical contributory role in understanding disease mechanism, as well as provide a focal point for development of diagnostic criteria linking such a mechanism to clinical prognosis. Despite recent advancements in single-cell measurement technologies, the identification of relevant cell subsets through manual efforts remains standard practice. As new technologies such as mass cytometry increase the parameterization of single-cell measurements, the scalability and subjectivity inherent in manual analyses slows both analysis and progress. We therefore developed Citrus (cluster identification, characterization, and regression), a data-driven approach for the identification of stratifying subpopulations in multidimensional cytometry datasets. The methodology of Citrus is demonstrated through the identification of known and unexpected pathway responses in a dataset of stimulated peripheral blood mononuclear cells measured by mass cytometry. Additionally, the performance of Citrus is compared with that of existing methods through the analysis of several publicly available datasets. As the complexity of flow cytometry datasets continues to increase, methods such as Citrus will be needed to aid investigators in the performance of unbiased--and potentially more thorough--correlation-based mining and inspection of cell subsets nested within high-dimensional datasets.},
author = {Bruggner, Robert V and Bodenmiller, Bernd and Dill, David L and Tibshirani, Robert J and Nolan, Garry P},
doi = {10.1073/pnas.1408792111},
file = {:Users/gosia/Documents/Mendeley Desktop/Bruggner et al/Bruggner et al. - 2014 - Automated identification of stratifying signatures in cellular subpopulations.pdf:pdf},
issn = {1091-6490},
journal = {Proceedings of the National Academy of Sciences of the United States of America},
keywords = {Algorithms,Blood Cells,Blood Cells: cytology,Cells,Cells: classification,Cells: cytology,Citrus,Computational Biology,Computational Biology: methods,Flow Cytometry,Flow Cytometry: methods,Humans,Software,T-Lymphocyte Subsets,T-Lymphocyte Subsets: cytology},
mendeley-groups = {Single cell,Single cell/Clustering,CyTOF {\&} flow cytometry/Differential analysis,.cytofWorkflow},
mendeley-tags = {Citrus},
month = {jul},
number = {26},
pages = {E2770--7},
pmid = {24979804},
title = {{Automated identification of stratifying signatures in cellular subpopulations.}},
url = {http://www.pnas.org/cgi/content/long/111/26/E2770},
volume = {111},
year = {2014}
}
@article{Chen2016,
abstract = {Single-cell mass cytometry significantly increases the dimensionality of cytometry analysis as compared to fluorescence flow cytometry, providing unprecedented resolution of cellular diversity in tissues. However, analysis and interpretation of these high-dimensional data poses a significant technical challenge. Here, we present cytofkit, a new Bioconductor package, which integrates both state-of-the-art bioinformatics methods and in-house novel algorithms to offer a comprehensive toolset for mass cytometry data analysis. Cytofkit provides functions for data pre-processing, data visualization through linear or non-linear dimensionality reduction, automatic identification of cell subsets, and inference of the relatedness between cell subsets. This pipeline also provides a graphical user interface (GUI) for ease of use, as well as a shiny application (APP) for interactive visualization of cell subpopulations and progression profiles of key markers. Applied to a CD14−CD19− PBMCs dataset, cytofkit accurately identified different subsets of lymphocytes; applied to a human CD4+ T cell dataset, cytofkit uncovered multiple subtypes of TFH cells spanning blood and tonsils. Cytofkit is implemented in R, licensed under the Artistic license 2.0, and freely available from the Bioconductor website, https://bioconductor.org/packages/cytofkit/. Cytofkit is also applicable for flow cytometry data analysis.},
author = {Chen, Hao and Lau, Mai Chan and Wong, Michael Thomas and Newell, Evan W and Poidinger, Michael and Chen, Jinmiao},
doi = {10.1371/journal.pcbi.1005112},
journal = {PLOS Computational Biology},
mendeley-groups = {.cytofWorkflow},
number = {9},
pages = {1--17},
publisher = {Public Library of Science},
title = {{Cytofkit: A Bioconductor Package for an Integrated Mass Cytometry Data Analysis Pipeline}},
url = {https://doi.org/10.1371/journal.pcbi.1005112},
volume = {12},
year = {2016}
}
@article{Diggins2017,
author = {Diggins, Kirsten E and Greenplate, Allison R and Leelatian, Nalin and Wogsland, Cara E and Irish, Jonathan M},
file = {:Users/gosia/Documents/Mendeley Desktop/Diggins et al/Diggins et al. - 2017 - Characterizing cell subsets using marker enrichment modeling.pdf:pdf},
issn = {1548-7091},
journal = {Nat Meth},
keywords = {MEM},
mendeley-groups = {.cytofWorkflow},
mendeley-tags = {MEM},
month = {mar},
number = {3},
pages = {275--278},
publisher = {Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.},
title = {{Characterizing cell subsets using marker enrichment modeling}},
url = {http://dx.doi.org/10.1038/nmeth.4149 http://10.0.4.14/nmeth.4149 http://www.nature.com/nmeth/journal/v14/n3/abs/nmeth.4149.html{\#}supplementary-information},
volume = {14},
year = {2017}
}
@article{Finck2013,
abstract = {Mass cytometry uses atomic mass spectrometry combined with isotopically pure reporter elements to currently measure as many as 40 parameters per single cell. As with any quantitative technology, there is a fundamental need for quality assurance and normalization protocols. In the case of mass cytometry, the signal variation over time due to changes in instrument performance combined with intervals between scheduled maintenance must be accounted for and then normalized. Here, samples were mixed with polystyrene beads embedded with metal lanthanides, allowing monitoring of mass cytometry instrument performance over multiple days of data acquisition. The protocol described here includes simultaneous measurements of beads and cells on the mass cytometer, subsequent extraction of the bead-based signature, and the application of an algorithm enabling correction of both short- and long-term signal fluctuations. The variation in the intensity of the beads that remains after normalization may also be used to determine data quality. Application of the algorithm to a one-month longitudinal analysis of a human peripheral blood sample reduced the range of median signal fluctuation from 4.9-fold to 1.3-fold.},
author = {Finck, Rachel and Simonds, Erin F and Jager, Astraea and Krishnaswamy, Smita and Sachs, Karen and Fantl, Wendy and Pe'er, Dana and Nolan, Garry P and Bendall, Sean C},
doi = {10.1002/cyto.a.22271},
file = {:Users/gosia/Documents/Mendeley Desktop/Finck et al/Finck et al. - 2013 - Normalization of mass cytometry data with bead standards.pdf:pdf},
issn = {15524922},
journal = {Cytometry Part A},
keywords = {Blood,CyTOF,Flow cytometry,Internal standards,Mass cytometry,Normalization,PBMC,Phenotype},
mendeley-groups = {.cytofWorkflow,CyTOF {\&} flow cytometry/Normalization},
pages = {483--494},
pmid = {23512433},
title = {{Normalization of mass cytometry data with bead standards}},
volume = {83A},
year = {2013}
}
@article{Harrison2015,
abstract = {Overdispersion is a common feature of models of biological data, but researchers often fail to model the excess variation driving the overdispersion, resulting in biased parameter estimates and standard errors. Quantifying and modeling overdispersion when it is present is therefore critical for robust biological inference. One means to account for overdispersion is to add an observation-level random effect (OLRE) to a model, where each data point receives a unique level of a random effect that can absorb the extra-parametric variation in the data. Although some studies have investigated the utility of OLRE to model overdispersion in Poisson count data, studies doing so for Binomial proportion data are scarce. Here I use a simulation approach to investigate the ability of both OLRE models and Beta-Binomial models to recover unbiased parameter estimates in mixed effects models of Binomial data under various degrees of overdispersion. In addition, as ecologists often fit random intercept terms to models when the random effect sample size is low ({\textless}5 levels), I investigate the performance of both model types under a range of random effect sample sizes when overdispersion is present. Simulation results revealed that the efficacy of OLRE depends on the process that generated the overdispersion; OLRE failed to cope with overdispersion generated from a Beta-Binomial mixture model, leading to biased slope and intercept estimates, but performed well for overdispersion generated by adding random noise to the linear predictor. Comparison of parameter estimates from an OLRE model with those from its corresponding Beta-Binomial model readily identified when OLRE were performing poorly due to disagreement between effect sizes, and this strategy should be employed whenever OLRE are used for Binomial data to assess their reliability. Beta-Binomial models performed well across all contexts, but showed a tendency to underestimate effect sizes when modelling non-Beta-Binomial data. Finally, both OLRE and Beta-Binomial models performed poorly when models contained {\textless}5 levels of the random intercept term, especially for estimating variance components, and this effect appeared independent of total sample size. These results suggest that OLRE are a useful tool for modelling overdispersion in Binomial data, but that they do not perform well in all circumstances and researchers should take care to verify the robustness of parameter estimates of OLRE models.},
author = {Harrison, Xavier A},
doi = {10.7717/peerj.1114},
file = {:Users/gosia/Documents/Mendeley Desktop/Harrison/Harrison - 2015 - A comparison of observation-level random effect and Beta-Binomial models for modelling overdispersion in Binomial data.pdf:pdf},
issn = {2167-8359},
journal = {PeerJ},
keywords = {Bayesian Hierarchical model,Beta-Binomial model,Ecological modelling,Effect size,Mixed effect model,Overdispersion,Random intercept,Variance component,observation-level random effect},
mendeley-groups = {Statistics/Mixed models,.cytofWorkflow},
mendeley-tags = {observation-level random effect},
month = {jul},
pages = {e1114},
title = {{A comparison of observation-level random effect and Beta-Binomial models for modelling overdispersion in Binomial data in ecology {\&} evolution}},
url = {https://doi.org/10.7717/peerj.1114},
volume = {3},
year = {2015}
}
@article{Harrison2014,
abstract = {Overdispersion is common in models of count data in ecology and evolutionary biology, and can occur due to missing covariates, non-independent (aggregated) data, or an excess frequency of zeroes (zero-inflation). Accounting for overdispersion in such models is vital, as failing to do so can lead to biased parameter estimates, and false conclusions regarding hypotheses of interest. Observation-level random effects (OLRE), where each data point receives a unique level of a random effect that models the extra-Poisson variation present in the data, are commonly employed to cope with overdispersion in count data. However studies investigating the efficacy of observation-level random effects as a means to deal with overdispersion are scarce. Here I use simulations to show that in cases where overdispersion is caused by random extra-Poisson noise, or aggregation in the count data, observation-level random effects yield more accurate parameter estimates compared to when overdispersion is simply ignored. Conversely, OLRE fail to reduce bias in zero-inflated data, and in some cases increase bias at high levels of overdispersion. There was a positive relationship between the magnitude of overdispersion and the degree of bias in parameter estimates. Critically, the simulations reveal that failing to account for overdispersion in mixed models can erroneously inflate measures of explained variance ($\backslash$textit{\{}r{\}}$\backslash$textsuperscript{\{}2{\}}), which may lead to researchers overestimating the predictive power of variables of interest. This work suggests use of observation-level random effects provides a simple and robust means to account for overdispersion in count data, but also that their ability to minimise bias is not uniform across all types of overdispersion and must be applied judiciously.},
author = {Harrison, Xavier A},
doi = {10.7717/peerj.616},
file = {:Users/gosia/Documents/Mendeley Desktop/Harrison/Harrison - 2014 - Using observation-level random effects to model overdispersion in count data in ecology and evolution.pdf:pdf},
issn = {2167-8359},
journal = {PeerJ},
keywords = {Explained variance,Generalized linear mixed models,Observation-level random effect,Poisson-lognormal models,Quasi-Poisson,observation-level random effect,r-squared},
mendeley-groups = {Statistics/Mixed models,.cytofWorkflow},
mendeley-tags = {observation-level random effect},
month = {oct},
pages = {e616},
title = {{Using observation-level random effects to model overdispersion in count data in ecology and evolution}},
url = {https://doi.org/10.7717/peerj.616},
volume = {2},
year = {2014}
}
@article{Hartmann2016,
abstract = {Narcolepsy type 1 is a devastating neurological sleep disorder resulting from the destruction of orexin-producing neurons in the central nervous system (CNS). Despite its striking association with the HLA-DQB1*06:02 allele, the autoimmune etiology of narcolepsy has remained largely hypothetical. Here, we compared peripheral mononucleated cells from narcolepsy patients with HLA-DQB1*06:02-matched healthy controls using high-dimensional mass cytometry in combination with algorithm-guided data analysis. Narcolepsy patients displayed multifaceted immune activation in CD4+ and CD8+ T cells dominated by elevated levels of B cell{\{}$\backslash$textendash{\}}supporting cytokines. Additionally, T cells from narcolepsy patients showed increased production of the proinflammatory cytokines IL-2 and TNF. Although it remains to be established whether these changes are primary to an autoimmune process in narcolepsy or secondary to orexin deficiency, these findings are indicative of inflammatory processes in the pathogenesis of this enigmatic disease.},
author = {Hartmann, Felix J and Bernard-Valnet, Rapha{\"{e}}l and Qu{\'{e}}riault, Cl{\'{e}}mence and Mrdjen, Dunja and Weber, Lukas M and Galli, Edoardo and Krieg, Carsten and Robinson, Mark D and Nguyen, Xuan-Hung and Dauvilliers, Yves and Liblau, Roland S and Becher, Burkhard},
doi = {10.1084/jem.20160897},
file = {:Users/gosia/Documents/Mendeley Desktop/Hartmann et al/Hartmann et al. - 2016 - High-dimensional single-cell analysis reveals the immune signature of narcolepsy.pdf:pdf},
issn = {0022-1007},
journal = {Journal of Experimental Medicine},
mendeley-groups = {CyTOF {\&} flow cytometry/Differential analysis,.cytofWorkflow},
number = {12},
pages = {2621--2633},
publisher = {Rockefeller University Press},
title = {{High-dimensional single-cell analysis reveals the immune signature of narcolepsy}},
url = {http://jem.rupress.org/content/213/12/2621},
volume = {213},
year = {2016}
}
@article{Jia2014,
author = {Jia, Cheng and Hu, Yu and Liu, Yichuan and Li, Mingyao},
doi = {10.4137/CIN.S13971.Received},
file = {:Users/gosia/Documents/Mendeley Desktop/Jia et al/Jia et al. - 2014 - Mapping Splicing Quantitative Trait Loci in RNA-Seq.pdf:pdf},
journal = {Cancer Informatics},
mendeley-groups = {sQTL analysis,sQTL analysis/Methods,.DRIMSeq paper,.cytofWorkflow},
pages = {35--43},
title = {{Mapping Splicing Quantitative Trait Loci in RNA-Seq}},
volume = {13},
year = {2014}
}
@incollection{Kotecha2001,
abstract = {Cytobank is a Web-based application for storage, analysis, and sharing of flow cytometry experiments. Researchers use a Web browser to log in and use a wide range of tools developed for basic and advanced flow cytometry. In addition to providing access to standard cytometry tools from any computer, Cytobank creates a platform and community for developing new analysis and publication tools. Figure layouts created on Cytobank are designed to allow transparent access to the underlying experiment annotation and data processing steps. Since all flow cytometry files and analysis data are stored on a central server, experiments and figures can be viewed or edited by anyone with the proper permission, from any computer with Internet access. Once a primary researcher has performed the initial analysis of the data, collaborators can engage in experiment analysis and make their own figure layouts using the gated, compensated experiment files. Cytobank is available to the scientific community at http://www.cytobank.org. Curr. Protoc. Cytom. 53:10.17.1-10.17.24. {\textcopyright} 2010 by John Wiley {\&} Sons, Inc.},
author = {Kotecha, Nikesh and Krutzik, Peter O and Irish, Jonathan M},
booktitle = {Current Protocols in Cytometry},
doi = {10.1002/0471142956.cy1017s53},
isbn = {9780471142959},
keywords = {Cytobank,analysis,database,flow cytometry,storage platform},
mendeley-groups = {.cytofWorkflow},
mendeley-tags = {Cytobank},
publisher = {John Wiley {\&} Sons, Inc.},
title = {{Web-Based Analysis and Publication of Flow Cytometry Experiments}},
url = {http://dx.doi.org/10.1002/0471142956.cy1017s53},
year = {2001}
}
@article{Leipold2015,
author = {Leipold, Michael D},
doi = {10.1002/cyto.a.22661},
issn = {1552-4930},
journal = {Cytometry Part A},
mendeley-groups = {CyTOF {\&} flow cytometry/Compensation,.cytofWorkflow},
number = {5},
pages = {380--382},
title = {{Another step on the path to mass cytometry standardization}},
url = {http://dx.doi.org/10.1002/cyto.a.22661},
volume = {87},
year = {2015}
}
@article{Levine2015,
abstract = {Acute myeloid leukemia (AML) manifests as phenotypically and functionally diverse cells, often within the same patient. Intratumor phenotypic and functional heterogeneity have been linked primarily by physical sorting experiments, which assume that functionally distinct subpopulations can be prospectively isolated by surface phenotypes. This assumption has proven problematic, and we therefore developed a data-driven approach. Using mass cytometry, we profiled surface and intracellular signaling proteins simultaneously in millions of healthy and leukemic cells. We developed PhenoGraph, which algorithmically defines phenotypes in high-dimensional single-cell data. PhenoGraph revealed that the surface phenotypes of leukemic blasts do not necessarily reflect their intracellular state. Using hematopoietic progenitors, we defined a signaling-based measure of cellular phenotype, which led to isolation of a gene expression signature that was predictive of survival in independent cohorts. This study presents new methods for large-scale analysis of single-cell heterogeneity and demonstrates their utility, yielding insights into AML pathophysiology.},
annote = {NULL},
author = {Levine, Jacob H. and Simonds, Erin F. and Bendall, Sean C. and Davis, Kara L. and Amir, El-ad D. and Tadmor, Michelle D. and Litvin, Oren and Fienberg, Harris G. and Jager, Astraea and Zunder, Eli R. and Finck, Rachel and Gedman, Amanda L. and Radtke, Ina and Downing, James R. and Pe'er, Dana and Nolan, Garry P.},
doi = {10.1016/j.cell.2015.05.047},
file = {:Users/gosia/Documents/Mendeley Desktop/Levine et al/Levine et al. - 2015 - Data-Driven Phenotypic Dissection of AML Reveals Progenitor-like Cells that Correlate with Prognosis.pdf:pdf;:Users/gosia/Documents/Mendeley Desktop/Levine et al/Levine et al. - 2015 - Data-Driven Phenotypic Dissection of AML Reveals Progenitor-like Cells that Correlate with Prognosis(2).pdf:pdf},
issn = {00928674},
journal = {Cell},
keywords = {Acute,Acute: diagnosis,Acute: genetics,Acute: pathology,Acute: physiopathology,Bone Marrow,Bone Marrow: pathology,Child,Cohort Studies,Computational Biology,Computational Biology: methods,Genetic Heterogeneity,Humans,Leukemia,Myeloid,Neoplastic Stem Cells,Neoplastic Stem Cells: pathology,PCA score,PhenoGraph,Single-Cell Analysis,Single-Cell Analysis: methods,Transcriptome},
language = {English},
mendeley-groups = {Single cell,.cytofWorkflow,Single cell - Carsten project},
mendeley-tags = {PCA score,PhenoGraph},
month = {jun},
number = {1},
pages = {184--97},
pmid = {26095251},
publisher = {Elsevier},
title = {{Data-Driven Phenotypic Dissection of AML Reveals Progenitor-like Cells that Correlate with Prognosis}},
url = {http://www.cell.com/article/S0092867415006376/fulltext},
volume = {162},
year = {2015}
}
@article{Love2014,
abstract = {In comparative high-throughput sequencing assays, a fundamental task is the analysis of count data, such as read counts per gene in RNA-seq, for evidence of systematic changes across experimental conditions. Small replicate numbers, discreteness, large dynamic range and the presence of outliers require a suitable statistical approach. We present DESeq2, a method for differential analysis of count data, using shrinkage estimation for dispersions and fold changes to improve stability and interpretability of estimates. This enables a more quantitative analysis focused on the strength rather than the mere presence of differential expression. The DESeq2 package is available at http://www.bioconductor.org/packages/release/bioc/html/DESeq2.html webcite.},
author = {Love, Michael I and Huber, Wolfgang and Anders, Simon},
journal = {Genome biology},
keywords = {Algorithms,Computational Biology,Computational Biology: methods,DESeq2,Genetic,High-Throughput Nucleotide Sequencing,Models,RNA,RNA: analysis,Sequence Analysis,Software,rlog},
mendeley-groups = {RNA-seq DE/Gene DE,.cytofWorkflow},
mendeley-tags = {DESeq2,rlog},
number = {12},
pages = {550},
publisher = {BioMed Central},
title = {{Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2.}},
url = {http://genomebiology.biomedcentral.com/articles/10.1186/s13059-014-0550-8},
volume = {15},
year = {2014}
}
@article{Mahnke2007,
abstract = {Flow cytometry-based immunophenotyping assays have become increasingly multiparametric, concomitantly analyzing multiple cellular parameters. To maximize the quality of the information obtained, antibody conjugate panels need to be developed with care, including requisite controls at every step. Such an optimization procedure for multicolor immunophenotyping assays is time consuming, but the value of having a reliable antibody conjugate panel that provides for sensitive detection of all molecules of interest justifies this time investment. This article outlines important considerations and procedures to undertake for the successful design and development of multicolor flow cytometry panels.},
annote = {Flow Cytometry},
author = {Mahnke, Yolanda D and Roederer, Mario},
doi = {http://doi.org/10.1016/j.cll.2007.05.002},
issn = {0272-2712},
journal = {Clinics in Laboratory Medicine},
mendeley-groups = {.cytofWorkflow},
number = {3},
pages = {469--485},
title = {{Optimizing a Multicolor Immunophenotyping Assay}},
url = {http://www.sciencedirect.com/science/article/pii/S0272271207000479},
volume = {27},
year = {2007}
}
@article{McCarthy2012,
abstract = {A flexible statistical framework is developed for the analysis of read counts from RNA-Seq gene expression studies. It provides the ability to analyse complex experiments involving multiple treatment conditions and blocking variables while still taking full account of biological variation. Biological variation between RNA samples is estimated separately from the technical variation associated with sequencing technologies. Novel empirical Bayes methods allow each gene to have its own specific variability, even when there are relatively few biological replicates from which to estimate such variability. The pipeline is implemented in the edgeR package of the Bioconductor project. A case study analysis of carcinoma data demonstrates the ability of generalized linear model methods (GLMs) to detect differential expression in a paired design, and even to detect tumour-specific expression changes. The case study demonstrates the need to allow for gene-specific variability, rather than assuming a common dispersion across genes or a fixed relationship between abundance and variability. Genewise dispersions de-prioritize genes with inconsistent results and allow the main analysis to focus on changes that are consistent between biological replicates. Parallel computational approaches are developed to make non-linear model fitting faster and more reliable, making the application of GLMs to genomic data more convenient and practical. Simulations demonstrate the ability of adjusted profile likelihood estimators to return accurate estimators of biological variability in complex situations. When variation is gene-specific, empirical Bayes estimators provide an advantageous compromise between the extremes of assuming common dispersion or separate genewise dispersion. The methods developed here can also be applied to count data arising from DNA-Seq applications, including ChIP-Seq for epigenetic marks and DNA methylation analyses.},
author = {McCarthy, Davis J. and Chen, Yunshun and Smyth, Gordon K.},
file = {:Users/gosia/Documents/Mendeley Desktop/McCarthy, Chen, Smyth/McCarthy, Chen, Smyth - 2012 - Differential expression analysis of multifactor RNA-Seq experiments with respect to biological variation.pdf:pdf},
journal = {Nucleic Acids Research},
keywords = {edgeR},
mendeley-groups = {RNA-seq DE/Gene DE/edgeR,Project DM/edgeR,.DRIMSeq paper,.CM2 PhD report,.cytofWorkflow},
mendeley-tags = {edgeR},
number = {10},
pages = {4288--4297},
pmid = {22287627},
title = {{Differential expression analysis of multifactor RNA-Seq experiments with respect to biological variation}},
volume = {40},
year = {2012}
}
@article{Monti2003,
abstract = {In this paper we present a new methodology of class discovery and clustering validation tailored to the task of analyzing gene expression data. The method can best be thought of as an analysis approach, to guide and assist in the use of any of a wide range of available clustering algorithms. We call the new methodology consensus clustering, and in conjunction with resampling techniques, it provides for a method to represent the consensus across multiple runs of a clustering algorithm and to assess the stability of the discovered clusters. The method can also be used to represent the consensus over multiple runs of a clustering algorithm with random restart (such as K-means, model-based Bayesian clustering, SOM, etc.), so as to account for its sensitivity to the initial conditions. Finally, it provides for a visualization tool to inspect cluster number, membership, and boundaries. We present the results of our experiments on both simulated data and real gene expression data aimed at evaluating the effectiveness of the methodology in discovering biologically meaningful clusters.},
author = {Monti, Stefano and Tamayo, Pablo and Mesirov, Jill and Golub, Todd},
doi = {10.1023/A:1023949509487},
file = {:Users/gosia/Documents/Mendeley Desktop/Monti et al/Monti et al. - 2003 - Consensus Clustering A Resampling-Based Method for Class Discovery and Visualization of Gene Expression Microarray.pdf:pdf},
issn = {1573-0565},
journal = {Machine Learning},
mendeley-groups = {.cytofWorkflow},
number = {1},
pages = {91--118},
title = {{Consensus Clustering: A Resampling-Based Method for Class Discovery and Visualization of Gene Expression Microarray Data}},
url = {http://dx.doi.org/10.1023/A:1023949509487},
volume = {52},
year = {2003}
}
@article{Pejoski4814,
abstract = {Broadening our understanding of the abundance and phenotype of B cell subsets that are induced or perturbed by exogenous Ags will improve the vaccine evaluation process. Mass cytometry (CyTOF) is being used to increase the number of markers that can be investigated in single cells, and therefore characterize cell phenotype at an unprecedented level. We designed a panel of CyTOF Abs to compare the B cell response in cynomolgus macaques at baseline, and 8 and 28 d after the second homologous immunization with modified vaccinia virus Ankara. The spanning-tree progression analysis of density-normalized events (SPADE) algorithm was used to identify clusters of CD20+ B cells. Our data revealed the phenotypic complexity and diversity of circulating B cells at steady-state and significant vaccine-induced changes in the proportions of some B cell clusters. All SPADE clusters, including those altered quantitatively by vaccination, were characterized phenotypically and compared using double hierarchical clustering. Vaccine-altered clusters composed of previously described subsets including CD27hiCD21lo activated memory and CD27+CD21+ resting memory B cells, and subphenotypes with novel patterns of marker coexpression. The expansion, followed by the contraction, of a single memory B cell SPADE cluster was positively correlated with serum anti-vaccine Ab titers. Similar results were generated by a different algorithm, automatic classification of cellular expression by nonlinear stochastic embedding. In conclusion, we present an in-depth characterization of B cell subphenotypes and proportions, before and after vaccination, using a two-step clustering analysis of CyTOF data, which is suitable for longitudinal studies and B cell subsets and biomarkers discovery.},
author = {Pejoski, David and Tchitchek, Nicolas and {Rodriguez Pozo}, Andr{\'{e}} and Elhmouzi-Younes, Jamila and Yousfi-Bogniaho, Rahima and Rogez-Kreuz, Christine and Clayette, Pascal and Dereuddre-Bosquet, Nathalie and L{\'{e}}vy, Yves and Cosma, Antonio and {Le Grand}, Roger and Beignon, Anne-Sophie},
doi = {10.4049/jimmunol.1502005},
issn = {0022-1767},
journal = {The Journal of Immunology},
mendeley-groups = {.cytofWorkflow},
number = {11},
pages = {4814--4831},
publisher = {American Association of Immunologists},
title = {{Identification of Vaccine-Altered Circulating B Cell Phenotypes Using Mass Cytometry and a Two-Step Clustering Analysis}},
url = {http://www.jimmunol.org/content/196/11/4814},
volume = {196},
year = {2016}
}
@article{Pyne2009,
abstract = {Flow cytometric analysis allows rapid single cell interrogation of surface and intracellular determinants by measuring fluorescence intensity of fluorophore-conjugated reagents. The availability of new platforms, allowing detection of increasing numbers of cell surface markers, has challenged the traditional technique of identifying cell populations by manual gating and resulted in a growing need for the development of automated, high-dimensional analytical methods. We present a direct multivariate finite mixture modeling approach, using skew and heavy-tailed distributions, to address the complexities of flow cytometric analysis and to deal with high-dimensional cytometric data without the need for projection or transformation. We demonstrate its ability to detect rare populations, to model robustly in the presence of outliers and skew, and to perform the critical task of matching cell populations across samples that enables downstream analysis. This advance will facilitate the application of flow cytometry to new, complex biological and clinical problems.},
author = {Pyne, Saumyadipta and Hu, Xinli and Wang, Kui and Rossin, Elizabeth and Lin, Tsung-I and Maier, Lisa M and Baecher-Allan, Clare and McLachlan, Geoffrey J and Tamayo, Pablo and Hafler, David A and {De Jager}, Philip L and Mesirov, Jill P},
doi = {10.1073/pnas.0903028106},
file = {:Users/gosia/Documents/Mendeley Desktop/Pyne et al/Pyne et al. - 2009 - Automated high-dimensional flow cytometric data analysis.pdf:pdf},
journal = {Proceedings of the National Academy of Sciences},
mendeley-groups = {CyTOF {\&} flow cytometry/Cluster mapping,.cytofWorkflow},
number = {21},
pages = {8519--8524},
title = {{Automated high-dimensional flow cytometric data analysis}},
url = {http://www.pnas.org/content/106/21/8519.abstract},
volume = {106},
year = {2009}
}
@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, 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},
keywords = {limma},
mendeley-groups = {.DRIMSeq paper,RNA-seq DE,RNA-seq DE/Gene DE,Microarrays,.PhDthesis,.cytofWorkflow},
mendeley-tags = {limma},
number = {7},
pages = {e47},
publisher = {Oxford University Press},
title = {{Limma powers differential expression analyses for RNA-sequencing and microarray studies}},
volume = {43},
year = {2015}
}
@article{Robinson2007,
abstract = {MOTIVATION: Digital gene expression (DGE) technologies measure gene expression by counting sequence tags. They are sensitive technologies for measuring gene expression on a genomic scale, without the need for prior knowledge of the genome sequence. As the cost of sequencing DNA decreases, the number of DGE datasets is expected to grow dramatically. Various tests of differential expression have been proposed for replicated DGE data using binomial, Poisson, negative binomial or pseudo-likelihood (PL) models for the counts, but none of the these are usable when the number of replicates is very small. RESULTS: We develop tests using the negative binomial distribution to model overdispersion relative to the Poisson, and use conditional weighted likelihood to moderate the level of overdispersion across genes. Not only is our strategy applicable even with the smallest number of libraries, but it also proves to be more powerful than previous strategies when more libraries are available. The methodology is equally applicable to other counting technologies, such as proteomic spectral counts. AVAILABILITY: An R package can be accessed from http://bioinf.wehi.edu.au/resources/},
author = {Robinson, Mark D. and Smyth, Gordon K.},
file = {:Users/gosia/Documents/Mendeley Desktop/Robinson, Smyth/Robinson, Smyth - 2007 - Moderated statistical tests for assessing differences in tag abundance.pdf:pdf},
journal = {Bioinformatics},
keywords = {edgeR},
mendeley-groups = {RNA-seq DE/Gene DE/edgeR,Project DM/edgeR,.DRIMSeq paper,RNA-seq DE/Gene DE,.CM2 PhD report,.cytofWorkflow},
mendeley-tags = {edgeR},
number = {21},
pages = {2881--2887},
pmid = {17881408},
title = {{Moderated statistical tests for assessing differences in tag abundance}},
volume = {23},
year = {2007}
}
@article{Roederer2001,
abstract = {BackgroundIn multicolor flow cytometric analysis, compensation for spectral overlap is nearly always necessary. For the most part, such compensation has been relatively simple, producing the desired rectilinear distributions. However, in the realm of multicolor analysis, visualization of compensated often results in unexpected distributions, principally the appearance of a large number of events on the axis, and even more disconcerting, an inability to bring the extent of compensated data down to “autofluorescence” levels.Materials and MethodsA mathematical model of detector measurements with variable photon intensities, spillover parameters, measurement errors, and data storage characteristics was used to illustrate sources of apparent error in compensated data. Immunofluorescently stained cells were collected under conditions of limiting light collection and high spillover between detectors to confirm aspects of the model.ResultsPhoton-counting statistics contribute a nonlinear error to compensated parameters. Measurement errors and log-scale binning error contribute linear errors to compensated parameters. These errors are most apparent with the use of red or far-red fluorochromes (where the emitted light is at low intensity) and with large spillover between detectors. Such errors can lead to data visualization artifacts that can easily lead to incorrect conclusions about data, and account for the apparent “undercompensation” previously described for multicolor staining.ConclusionsThere are inescapable errors arising from imperfect measurements, photon-counting statistics, and even data storage methods that contribute both linearly and nonlinearly to a “spreading” of a properly compensated autofluorescence distribution. This phenomenon precludes the use of “quadrant” statistics or gates to analyze affected data; it also precludes visual adjustment of compensation. Most importantly, it is impossible to properly compensate data using standard visual graphical interfaces (histograms or dot plots). Computer-assisted compensation is required, as well as careful gating and experimental design to determine the distinction between positive and negative events. Finally, the use of special staining controls that employ all reagents except for the one of interest (termed fluorescence minus one, or “FMO” controls) becomes necessary to accurately identify expressing cells in the fully stained sample. Cytometry 45:194–205, 2001. {\textcopyright} 2001 Wiley-Liss, Inc.},
author = {Roederer, Mario},
doi = {10.1002/1097-0320(20011101)45:3<194::AID-CYTO1163>3.0.CO;2-C},
issn = {1097-0320},
journal = {Cytometry},
keywords = {compensation,data analysis,flow cytometry,multicolor immunophenotyping},
mendeley-groups = {CyTOF {\&} flow cytometry/Compensation,.cytofWorkflow},
number = {3},
pages = {194--205},
publisher = {John Wiley {\&} Sons, Inc.},
title = {{Spectral compensation for flow cytometry: Visualization artifacts, limitations, and caveats}},
url = {http://dx.doi.org/10.1002/1097-0320(20011101)45:3{\%}3C194::AID-CYTO1163{\%}3E3.0.CO;2-C},
volume = {45},
year = {2001}
}
@article{Saeys2016,
abstract = {Recent advances in flow cytometry allow scientists to measure an increasing number of parameters per cell, generating huge and high-dimensional datasets. To analyse, visualize and interpret these data, newly available computational techniques should be adopted, evaluated and improved upon by the immunological community. Computational flow cytometry is emerging as an important new field at the intersection of immunology and computational biology; it allows new biological knowledge to be extracted from high-throughput single-cell data. This Review provides non-experts with a broad and practical overview of the many recent developments in computational flow cytometry.},
author = {Saeys, Yvan and Gassen, Sofie Van and Lambrecht, Bart N},
file = {:Users/gosia/Documents/Mendeley Desktop/Saeys, Gassen, Lambrecht/Saeys, Gassen, Lambrecht - 2016 - Computational flow cytometry helping to make sense of high-dimensional immunology data(2).pdf:pdf},
issn = {1474-1733},
journal = {Nat Rev Immunol},
mendeley-groups = {Single cell/Reviews,.cytofWorkflow},
month = {jul},
number = {7},
pages = {449--462},
publisher = {Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.},
title = {{Computational flow cytometry: helping to make sense of high-dimensional immunology data}},
url = {http://dx.doi.org/10.1038/nri.2016.56 http://10.0.4.14/nri.2016.56},
volume = {16},
year = {2016}
}
@article{VanDerMaaten2008,
abstract = {KNAW Narcis. Back to search results. Publication - - (2008). Pagina-navigatie: Main. Title, - - . Published in, Journal of Machine Learning Research, Vol. 9, No. nov, p.2579-2605.},
archivePrefix = {arXiv},
arxivId = {1307.1662},
author = {{Van Der Maaten}, L J P and Hinton, G E},
doi = {10.1007/s10479-011-0841-3},
eprint = {1307.1662},
isbn = {1532-4435},
issn = {1532-4435},
journal = {Journal of Machine Learning Research},
keywords = {dimensionality reduction,embedding algorithms,manifold learning,multidimensional scaling,visualization},
mendeley-groups = {.cytofWorkflow,Single cell/Dimention reduction},
pmid = {20652508},
title = {{Visualizing high-dimensional data using t-sne}},
year = {2008}
}
@article{VanGassen2015,
abstract = {The number of markers measured in both flow and mass cytometry keeps increasing steadily. Although this provides a wealth of information, it becomes infeasible to analyze these datasets manually. When using 2D scatter plots, the number of possible plots increases exponentially with the number of markers and therefore, relevant information that is present in the data might be missed. In this article, we introduce a new visualization technique, called FlowSOM, which analyzes Flow or mass cytometry data using a Self-Organizing Map. Using a two-level clustering and star charts, our algorithm helps to obtain a clear overview of how all markers are behaving on all cells, and to detect subsets that might be missed otherwise. R code is available at https://github.com/SofieVG/FlowSOM and will be made available at Bioconductor.},
author = {{Van Gassen}, Sofie and Callebaut, Britt and {Van Helden}, Mary J and Lambrecht, Bart N and Demeester, Piet and Dhaene, Tom and Saeys, Yvan},
doi = {10.1002/cyto.a.22625},
file = {:Users/gosia/Documents/Mendeley Desktop/Van Gassen et al/Van Gassen et al. - 2015 - FlowSOM Using self-organizing maps for visualization and interpretation of cytometry data.pdf:pdf},
issn = {1552-4930},
journal = {Cytometry. Part A : the journal of the International Society for Analytical Cytology},
keywords = {FlowSOM},
mendeley-groups = {Single cell,Single cell/Clustering,.cytofWorkflow},
mendeley-tags = {FlowSOM},
number = {7},
pages = {636--45},
pmid = {25573116},
title = {{FlowSOM: Using self-organizing maps for visualization and interpretation of cytometry data.}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/25573116},
volume = {87},
year = {2015}
}
@article{vanUnen20161227,
abstract = {Summary Inflammatory intestinal diseases are characterized by abnormal immune responses and affect distinct locations of the gastrointestinal tract. Although the role of several immune subsets in driving intestinal pathology has been studied, a system-wide approach that simultaneously interrogates all major lineages on a single-cell basis is lacking. We used high-dimensional mass cytometry to generate a system-wide view of the human mucosal immune system in health and disease. We distinguished 142 immune subsets and through computational applications found distinct immune subsets in peripheral blood mononuclear cells and intestinal biopsies that distinguished patients from controls. In addition, mucosal lymphoid malignancies were readily detected as well as precursors from which these likely derived. These findings indicate that an integrated high-dimensional analysis of the entire immune system can identify immune subsets associated with the pathogenesis of complex intestinal disorders. This might have implications for diagnostic procedures, immune-monitoring, and treatment of intestinal diseases and mucosal malignancies.},
author = {van Unen, Vincent and Li, Na and Molendijk, Ilse and Temurhan, Mine and H{\"{o}}llt, Thomas and {van der Meulen-de Jong}, Andrea E and Verspaget, Hein W and Mearin, M Luisa and Mulder, Chris J and van Bergen, Jeroen and Lelieveldt, Boudewijn P F and Koning, Frits},
doi = {http://dx.doi.org/10.1016/j.immuni.2016.04.014},
issn = {1074-7613},
journal = {Immunity},
mendeley-groups = {.cytofWorkflow},
number = {5},
pages = {1227--1239},
title = {{Mass Cytometry of the Human Mucosal Immune System Identifies Tissue- and Disease-Associated Immune Subsets}},
url = {http://www.sciencedirect.com/science/article/pii/S1074761316301431},
volume = {44},
year = {2016}
}
@article{Wang2017,
abstract = {Motivation: We here present SIMLR (Single-cell Interpretation via Multi-kernel LeaRning), an open-source tool that implements a novel framework to learn a cell-to-cell similarity measure from single-cell RNA-seq data. SIMLR can be effectively used to perform tasks such as dimen- sion reduction, clustering, and visualization of heterogeneous populations of cells. SIMLR was benchmarked against state-of-the-art methods for these three tasks on several public datasets, showing it to be scalable and capable of greatly improving clustering performance, as well as providing valuable insights by making the data more interpretable via better a visualization. Availability and Implementation: SIMLR is available on GitHub in both R and MATLAB implementations. Furthermore, it is also available as an R package on bioconductor.org. Contact: bowang87@stanford.edu or daniele.ramazzotti@stanford.edu Supplementary Information: Supplementary data are available at Bioinformatics online.},
author = {Wang, Bo and Ramazzotti, Daniele and {De Sano}, Luca and Zhu, Junjie and Pierson, Emma and Batzoglou, Serafim},
doi = {10.1101/118901},
journal = {bioRxiv},
mendeley-groups = {.cytofWorkflow},
publisher = {Cold Spring Harbor Labs Journals},
title = {{SIMLR: A Tool For Large-Scale Single-Cell Analysis By Multi-Kernel Learning}},
url = {http://biorxiv.org/content/early/2017/03/21/118901},
year = {2017}
}
@article{Wattenberg2016,
author = {Wattenberg, Martin and Vi{\'{e}}gas, Fernanda and Johnson, Ian},
doi = {10.23915/distill.00002},
journal = {Distill},
mendeley-groups = {Single cell/Dimention reduction,.cytofWorkflow},
title = {{How to Use t-SNE Effectively}},
url = {http://distill.pub/2016/misread-tsne},
year = {2016}
}
@article{Weber2016,
author = {Weber, Lukas M and Robinson, Mark D},
doi = {10.1002/cyto.a.23030},
file = {:Users/gosia/Documents/Mendeley Desktop/Weber, Robinson/Weber, Robinson - 2016 - Comparison of clustering methods for high-dimensional single-cell flow and mass cytometry data.pdf:pdf},
issn = {1552-4930},
journal = {Cytometry Part A},
keywords = {CyTOF,F1 score,bioinformatics,cell populations,clustering,flow cytometry,high-dimensional,manual gating,mass cytometry,single-cell},
mendeley-groups = {Single cell/Clustering,.cytofWorkflow},
number = {12},
pages = {1084--1096},
title = {{Comparison of clustering methods for high-dimensional single-cell flow and mass cytometry data}},
url = {http://dx.doi.org/10.1002/cyto.a.23030},
volume = {89},
year = {2016}
}
@article{Wilkerson2010,
author = {Wilkerson, Matthew D and Hayes, D Neil},
doi = {10.1093/bioinformatics/btq170},
journal = {Bioinformatics},
keywords = {ConsensusClusterPlus},
mendeley-groups = {.cytofWorkflow},
mendeley-tags = {ConsensusClusterPlus},
number = {12},
pages = {1572},
title = {{ConsensusClusterPlus: a class discovery tool with confidence assessments and item tracking}},
url = {+ http://dx.doi.org/10.1093/bioinformatics/btq170},
volume = {26},
year = {2010}
}
@article{Zhao2013,
abstract = {To characterize the genetic variation of alternative splicing, we develop GLiMMPS, a robust statistical method for detecting splicing quantitative trait loci (sQTLs) from RNA-seq data. GLiMMPS takes into account the individual variation in sequencing coverage and the noise prevalent in RNA-seq data. Analyses of simulated and real RNA-seq datasets demonstrate that GLiMMPS outperforms competing statistical models. Quantitative RT-PCR tests of 26 randomly selected GLiMMPS sQTLs yielded a validation rate of 100{\%}. As population-scale RNA-seq studies become increasingly affordable and popular, GLiMMPS provides a useful tool for elucidating the genetic variation of alternative splicing in humans and model organisms.},
author = {Zhao, Keyan and Lu, Zhi-Xiang and Park, Juw Won and Zhou, Qing and Xing, Yi},
file = {:Users/gosia/Documents/Mendeley Desktop/Zhao et al/Zhao et al. - 2013 - GLiMMPS Robust statistical model for regulatory variation of alternative splicing using RNA-seq data.pdf:pdf},
issn = {1465-6914},
journal = {Genome biology},
keywords = {GLiMMPS,alternative splicing,exon,generalized linear mixed model,rna-seq,sqtl},
mendeley-groups = {sQTL analysis,sQTL analysis/Methods,.DRIMSeq paper,.CM2 PhD report,.cytofWorkflow},
mendeley-tags = {GLiMMPS},
number = {7},
pages = {R74},
pmid = {23876401},
publisher = {BioMed Central Ltd},
title = {{GLiMMPS: Robust statistical model for regulatory variation of alternative splicing using RNA-seq data.}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/23876401},
volume = {14},
year = {2013}
}
@article{Zunder2015,
author = {Zunder, Eli R and Finck, Rachel and Behbehani, Gregory K and Amir, El-ad D and Krishnaswamy, Smita and Gonzalez, Veronica D and Lorang, Cynthia G and Bjornson, Zach and Spitzer, Matthew H and Bodenmiller, Bernd and Fantl, Wendy J and Pe'er, Dana and Nolan, Garry P},
doi = {10.1038/nprot.2015.020},
file = {:Users/gosia/Documents/Mendeley Desktop/Zunder et al/Zunder et al. - 2015 - Palladium-based mass tag cell barcoding with a doublet-filtering scheme and single-cell deconvolution algorithm.pdf:pdf},
issn = {1754-2189},
journal = {Nature Protocols},
mendeley-groups = {CyTOF {\&} flow cytometry/Debarcoding,.cytofWorkflow},
number = {2},
pages = {316--333},
publisher = {Nature Publishing Group},
title = {{Palladium-based mass tag cell barcoding with a doublet-filtering scheme and single-cell deconvolution algorithm}},
url = {http://www.nature.com/doifinder/10.1038/nprot.2015.020},
volume = {10},
year = {2015}
}
@article{Li116566,
abstract = {Mass cytometry (CyTOF) has greatly expanded the capability of cytometry. It is now easy to generate multiple CyTOF samples in a single study, with each sample containing single-cell measurement on 50 markers for more than hundreds of thousands of cells. Current methods do not adequately address the issues concerning combining multiple samples for subpopulation discovery, and these issues can be quickly and dramatically amplified with increasing number of samples. To overcome this limitation, we developed Partition-Assisted Clustering and Multiple Alignments of Networks (PAC-MAN) for the fast automatic identification of cell populations in CyTOF data closely matching that of expert manual-discovery, and for alignments between subpopulations across samples to define dataset-level cellular states. PAC-MAN is computationally efficient, allowing the management of very large CyTOF datasets, which are increasingly common in clinical studies and cancer studies that monitor various tissue samples for each subject.},
author = {Li, Ye Henry and Li, Dangna and Samusik, Nikolay and Wang, Xiaowei and Guan, Leying and Nolan, Garry P and Wong, Wing Hung},
doi = {10.1101/116566},
journal = {bioRxiv},
keywords = {PAC-MAN},
mendeley-groups = {Single cell/Clustering,.cytofWorkflow},
mendeley-tags = {PAC-MAN},
publisher = {Cold Spring Harbor Labs Journals},
title = {{Scalable Multi-Sample Single-Cell Data Analysis by Partition-Assisted Clustering and Multiple Alignments of Networks}},
url = {http://biorxiv.org/content/early/2017/03/28/116566},
year = {2017}
}