From 66bdbdf2db3d75fd1b33d45553908257e26d5ec0 Mon Sep 17 00:00:00 2001 From: Brock Date: Mon, 13 May 2019 14:40:59 -0400 Subject: [PATCH 01/31] First few edits --- content/04.study.md | 11 +++++++++++ content/citation-tags.tsv | 1 + 2 files changed, 12 insertions(+) diff --git a/content/04.study.md b/content/04.study.md index 05c5054f..89b68900 100644 --- a/content/04.study.md +++ b/content/04.study.md @@ -47,6 +47,17 @@ Deep learning applied to gene expression data is still in its infancy, but the f Many previously untestable hypotheses can now be interrogated as deep learning enables analysis of increasing amounts of data generated by new technologies. For example, the effects of cellular heterogeneity on basic biology and disease etiology can now be explored by single-cell RNA-seq and high-throughput fluorescence-based imaging, techniques we discuss below that will benefit immensely from deep learning approaches. +### DNA Methylation + +#### Introduction + +DNA Methylation (DNAm), is the process of adding a methyl group to a cytosine in the context of a CpG dinucleotide. +This DNA-level epigenetic modification regulates gene transcription, is critical in development, and alterations to DNA methylation are well-established as contributing to pathophysiology of many diseases including cancers. Studies of DNA methylation have also shed light on the processes involving initial differentiation of stem cells, aging and pathogenesis in response to environmental exposures. + +Traditional analytic approaches to DNA methylation data often focus on estimating differential DNA methylation between groups or related with an outcome using linear mixed effects models. In addition, a growing application of DNA methylation measures is to infer cellular or subject phenotypes from samples and either examine the relation of these phenotypes with outcomes or disease states directly, and/or include them in models as covariates. For example, inference of subject age using DNA methylation clock approaches are well established (Horvath 2012 genome biology, Bell CG et al genome biology in press), and are starting to be applied to test the relation of biological age with disease risk and outcomes [@tag:Kresovich2019]. Importantly, reference DNA methylation profiles of leukocytes are available to infer immune cell type proportions with measures of DNA methylation in peripheral blood DNA [CITE (Houseman 2012, SALAS 2018 genome biology)], a novel approach to immunophenotyping that only requires. Cell type inference is important for adjusting for cell-type composition in epigenome-wide association studies [https://www.ncbi.nlm.nih.gov/pubmed/28517979 ]. While utilizing reference-based libraries demonstrates strong predictive value for immune cell type estimation, these methods severely restrict the amount of underlying biology that can be understood and correlated with disease manifestations and phenotypes. When a referenced-based library is not available for use, unsupervised methods are able to estimate these immune profiles [https://www.ncbi.nlm.nih.gov/pubmed/28977446 ]. Methods that do not rely on these reference libraries [https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4928286/] are limited by being unable to fully capture the nonlinearity of the methylation data. + +There are many promising deep learning approaches that serve to expand the number of CpG sites whose DNA methylation state can be studied by capturing the complex interactions between different regions of DNA and extract the complete set of informative biologically relevant features. The main approaches focus on: 1) estimating regions of methylation status and imputing missing methylation values, 2) performing classification and regression tasks, and 3) understanding latent embeddings of methylation states from which to extract biologically meaningful features, infer interpolated disease states, and uncover relevant CpG sites for the above prediction tasks. + ### Splicing Pre-mRNA transcripts can be spliced into different isoforms by retaining or skipping subsets of exons or including parts of introns, creating enormous spatiotemporal flexibility to generate multiple distinct proteins from a single gene. diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index 9da21983..6efc7d48 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -122,6 +122,7 @@ Koh2017_understanding arxiv:1703.04730 Kooi2016_mamm_lesions doi:10.1016/j.media.2016.07.007 Kooi2017_mamm_tl doi:10.1002/mp.12110 Kraus2017_deeploc doi:10.15252/msb.20177551 +Kresovich2019 doi:10.1093/jnci/djz020 Krizhevsky2013_nips_cnn url:https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf Krizhevsky2014_weird_trick arxiv:1404.5997 Lacey2016_dl_fpga arxiv:1602.04283 From a58570278c4d8c262ca7a35dbd67a7cad05ceec4 Mon Sep 17 00:00:00 2001 From: Brock Date: Mon, 13 May 2019 16:13:10 -0400 Subject: [PATCH 02/31] final draft --- content/04.study.md | 18 +++++++++++++----- content/citation-tags.tsv | 6 ++++++ 2 files changed, 19 insertions(+), 5 deletions(-) diff --git a/content/04.study.md b/content/04.study.md index 89b68900..5e6c8a78 100644 --- a/content/04.study.md +++ b/content/04.study.md @@ -52,11 +52,19 @@ For example, the effects of cellular heterogeneity on basic biology and disease #### Introduction DNA Methylation (DNAm), is the process of adding a methyl group to a cytosine in the context of a CpG dinucleotide. -This DNA-level epigenetic modification regulates gene transcription, is critical in development, and alterations to DNA methylation are well-established as contributing to pathophysiology of many diseases including cancers. Studies of DNA methylation have also shed light on the processes involving initial differentiation of stem cells, aging and pathogenesis in response to environmental exposures. - -Traditional analytic approaches to DNA methylation data often focus on estimating differential DNA methylation between groups or related with an outcome using linear mixed effects models. In addition, a growing application of DNA methylation measures is to infer cellular or subject phenotypes from samples and either examine the relation of these phenotypes with outcomes or disease states directly, and/or include them in models as covariates. For example, inference of subject age using DNA methylation clock approaches are well established (Horvath 2012 genome biology, Bell CG et al genome biology in press), and are starting to be applied to test the relation of biological age with disease risk and outcomes [@tag:Kresovich2019]. Importantly, reference DNA methylation profiles of leukocytes are available to infer immune cell type proportions with measures of DNA methylation in peripheral blood DNA [CITE (Houseman 2012, SALAS 2018 genome biology)], a novel approach to immunophenotyping that only requires. Cell type inference is important for adjusting for cell-type composition in epigenome-wide association studies [https://www.ncbi.nlm.nih.gov/pubmed/28517979 ]. While utilizing reference-based libraries demonstrates strong predictive value for immune cell type estimation, these methods severely restrict the amount of underlying biology that can be understood and correlated with disease manifestations and phenotypes. When a referenced-based library is not available for use, unsupervised methods are able to estimate these immune profiles [https://www.ncbi.nlm.nih.gov/pubmed/28977446 ]. Methods that do not rely on these reference libraries [https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4928286/] are limited by being unable to fully capture the nonlinearity of the methylation data. - -There are many promising deep learning approaches that serve to expand the number of CpG sites whose DNA methylation state can be studied by capturing the complex interactions between different regions of DNA and extract the complete set of informative biologically relevant features. The main approaches focus on: 1) estimating regions of methylation status and imputing missing methylation values, 2) performing classification and regression tasks, and 3) understanding latent embeddings of methylation states from which to extract biologically meaningful features, infer interpolated disease states, and uncover relevant CpG sites for the above prediction tasks. +This DNA-level epigenetic modification regulates gene transcription, is critical in development, and alterations to DNA methylation are well-established as contributing to pathophysiology of many diseases including cancers. +Studies of DNA methylation have also shed light on the processes involving initial differentiation of stem cells, aging and pathogenesis in response to environmental exposures. + +Traditional analytic approaches to DNA methylation data often focus on estimating differential DNA methylation between groups or related with an outcome using linear mixed effects models. +In addition, a growing application of DNA methylation measures is to infer cellular or subject phenotypes from samples and either examine the relation of these phenotypes with outcomes or disease states directly, and/or include them in models as covariates. +For example, inference of subject age using DNA methylation clock approaches are established [@tag:Horvath2013], and are starting to be applied to test the relation of biological age with disease risk and outcomes [@tag:Kresovich2019]. +Importantly, reference DNA methylation profiles of leukocytes are available to infer immune cell type proportions with measures of DNA methylation in peripheral blood DNA [@tag:Houseman2012],[@tag:Salas2018], a novel approach to immunophenotyping that only requires. +Cell type inference is important for adjusting for cell-type composition in epigenome-wide association studies [@tag:Teschendorff2017]. +While utilizing reference-based libraries demonstrates strong predictive value for immune cell type estimation, these methods severely restrict the amount of underlying biology that can be understood and correlated with disease manifestations and phenotypes. When a referenced-based library is not available for use, unsupervised methods are able to estimate these immune profiles [@tag:Titus2017]. +Methods that do not rely on these reference libraries [@tag:Houseman2016], are limited by being unable to fully capture the nonlinearity of the methylation data. + +There are many promising deep learning approaches that serve to expand the number of CpG sites whose DNA methylation state can be studied by capturing the complex interactions between different regions of DNA and extract the complete set of informative biologically relevant features. +The main approaches focus on: 1) estimating regions of methylation status and imputing missing methylation values, 2) performing classification and regression tasks, and 3) understanding latent embeddings of methylation states from which to extract biologically meaningful features, infer interpolated disease states, and uncover relevant CpG sites for the above prediction tasks. ### Splicing diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index 6efc7d48..f5af9dcc 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -96,6 +96,9 @@ Hinton2015_dk arxiv:1503.02531v1 Hochreiter doi:10.1093/bioinformatics/btm247 Hoff doi:10.1093/nar/gkp327 Horton1992_assessment doi:10.1093/nar/20.16.4331 +Horvath2013 doi:10.1186/gb-2013-14-10-r115 +Houseman2012 doi:10.1186/1471-2105-13-86 +Houseman2016 doi:10.1186/s12859-016-1140-4 Hubara2016_qnn arxiv:1609.07061 Huddar2016_predicting doi:10.1109/ACCESS.2016.2618775 Hughes2016_macromol_react doi:10.1021/acscentsci.6b00162 @@ -205,6 +208,7 @@ Romero2017_diet url:https://openreview.net/pdf?id=Sk-oDY9ge Rosenberg2015_synthetic_seqs doi:10.1016/j.cell.2015.09.054 Russakovsky2015_imagenet doi:10.1007/s11263-015-0816-y Sa2015_buckwild pmcid:PMC4907892 +Salas2018 doi:10.1186/s13059-018-1448-7 Salzberg doi:10.1186/1471-2105-11-544 Schatz2010_dna_cloud doi:10.1038/nbt0710-691 Schmidhuber2014_dnn_overview doi:10.1016/j.neunet.2014.09.003 @@ -247,6 +251,8 @@ Tan2015_adage doi:10.1128/mSystems.00025-15 Tan2016_eadage doi:10.1101/078659 TAC-ELM doi:10.1142/S0219720012500151 TensorFlow arxiv:1603.04467 +Teschendorff2017 doi:10.2217/epi-2016-0153 +Titus2017 doi:10.1093/hmg/ddx275 Torracinta2016_deep_snp doi:10.1101/097469 Torracinta2016_sim doi:10.1101/079087 Tu1996_anns doi:10.1016/S0895-4356(96)00002-9 From db7e3a7ca34e9dc59fa5ebacf3a1b4cca24d1038 Mon Sep 17 00:00:00 2001 From: Brock Date: Tue, 25 Jun 2019 09:33:23 -0400 Subject: [PATCH 03/31] Update citation-tags.tsv --- content/citation-tags.tsv | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index f5af9dcc..9f726e7d 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -97,7 +97,7 @@ Hochreiter doi:10.1093/bioinformatics/btm247 Hoff doi:10.1093/nar/gkp327 Horton1992_assessment doi:10.1093/nar/20.16.4331 Horvath2013 doi:10.1186/gb-2013-14-10-r115 -Houseman2012 doi:10.1186/1471-2105-13-86 +Houseman2012 doi:10.1186/1471-2105-13-86 Houseman2016 doi:10.1186/s12859-016-1140-4 Hubara2016_qnn arxiv:1609.07061 Huddar2016_predicting doi:10.1109/ACCESS.2016.2618775 From 5bf698f3301d32dac32319fa7915afc3032367b2 Mon Sep 17 00:00:00 2001 From: brockclarke Date: Fri, 26 Jul 2019 09:23:51 -0600 Subject: [PATCH 04/31] Update content/04.study.md Co-Authored-By: Casey Greene --- content/04.study.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/content/04.study.md b/content/04.study.md index 5e6c8a78..90c53d95 100644 --- a/content/04.study.md +++ b/content/04.study.md @@ -58,7 +58,8 @@ Studies of DNA methylation have also shed light on the processes involving initi Traditional analytic approaches to DNA methylation data often focus on estimating differential DNA methylation between groups or related with an outcome using linear mixed effects models. In addition, a growing application of DNA methylation measures is to infer cellular or subject phenotypes from samples and either examine the relation of these phenotypes with outcomes or disease states directly, and/or include them in models as covariates. For example, inference of subject age using DNA methylation clock approaches are established [@tag:Horvath2013], and are starting to be applied to test the relation of biological age with disease risk and outcomes [@tag:Kresovich2019]. -Importantly, reference DNA methylation profiles of leukocytes are available to infer immune cell type proportions with measures of DNA methylation in peripheral blood DNA [@tag:Houseman2012],[@tag:Salas2018], a novel approach to immunophenotyping that only requires. +Different cell types have different DNA methylation profiles. +Reference DNA methylation profiles of leukocytes are available, which makes it feasible to infer immune cell type proportions with measures of DNA methylation in peripheral blood DNA [@tag:Houseman2012],[@tag:Salas2018], a novel approach to immunophenotyping that only requires. Cell type inference is important for adjusting for cell-type composition in epigenome-wide association studies [@tag:Teschendorff2017]. While utilizing reference-based libraries demonstrates strong predictive value for immune cell type estimation, these methods severely restrict the amount of underlying biology that can be understood and correlated with disease manifestations and phenotypes. When a referenced-based library is not available for use, unsupervised methods are able to estimate these immune profiles [@tag:Titus2017]. Methods that do not rely on these reference libraries [@tag:Houseman2016], are limited by being unable to fully capture the nonlinearity of the methylation data. From 8ad26dd6298e7f3a0320c107e21681035986ec7d Mon Sep 17 00:00:00 2001 From: brockclarke Date: Fri, 26 Jul 2019 11:24:05 -0400 Subject: [PATCH 05/31] Update content/04.study.md Co-Authored-By: Casey Greene --- content/04.study.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/04.study.md b/content/04.study.md index 90c53d95..61a3e608 100644 --- a/content/04.study.md +++ b/content/04.study.md @@ -51,7 +51,7 @@ For example, the effects of cellular heterogeneity on basic biology and disease #### Introduction -DNA Methylation (DNAm), is the process of adding a methyl group to a cytosine in the context of a CpG dinucleotide. +DNA methylation, is the process of adding a methyl group to a cytosine in the context of a CpG dinucleotide. This DNA-level epigenetic modification regulates gene transcription, is critical in development, and alterations to DNA methylation are well-established as contributing to pathophysiology of many diseases including cancers. Studies of DNA methylation have also shed light on the processes involving initial differentiation of stem cells, aging and pathogenesis in response to environmental exposures. From 99c19afd7cdf222bf14988e6089d9971774a643f Mon Sep 17 00:00:00 2001 From: brockclarke Date: Fri, 26 Jul 2019 11:24:26 -0400 Subject: [PATCH 06/31] Update content/04.study.md Co-Authored-By: Casey Greene --- content/04.study.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/content/04.study.md b/content/04.study.md index 61a3e608..4aa0d599 100644 --- a/content/04.study.md +++ b/content/04.study.md @@ -61,7 +61,8 @@ For example, inference of subject age using DNA methylation clock approaches are Different cell types have different DNA methylation profiles. Reference DNA methylation profiles of leukocytes are available, which makes it feasible to infer immune cell type proportions with measures of DNA methylation in peripheral blood DNA [@tag:Houseman2012],[@tag:Salas2018], a novel approach to immunophenotyping that only requires. Cell type inference is important for adjusting for cell-type composition in epigenome-wide association studies [@tag:Teschendorff2017]. -While utilizing reference-based libraries demonstrates strong predictive value for immune cell type estimation, these methods severely restrict the amount of underlying biology that can be understood and correlated with disease manifestations and phenotypes. When a referenced-based library is not available for use, unsupervised methods are able to estimate these immune profiles [@tag:Titus2017]. +While utilizing reference-based libraries demonstrates strong predictive value for immune cell type estimation, these methods severely restrict the amount of underlying biology that can be understood and correlated with disease manifestations and phenotypes. +When a referenced-based library is not available for use, unsupervised methods are able to estimate these immune profiles [@tag:Titus2017]. Methods that do not rely on these reference libraries [@tag:Houseman2016], are limited by being unable to fully capture the nonlinearity of the methylation data. There are many promising deep learning approaches that serve to expand the number of CpG sites whose DNA methylation state can be studied by capturing the complex interactions between different regions of DNA and extract the complete set of informative biologically relevant features. From 2860a1630e5b081936309477f9b16979a936afb0 Mon Sep 17 00:00:00 2001 From: brockclarke Date: Fri, 26 Jul 2019 11:27:30 -0400 Subject: [PATCH 07/31] Update content/04.study.md Co-Authored-By: Casey Greene --- content/04.study.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/content/04.study.md b/content/04.study.md index 4aa0d599..966b1eef 100644 --- a/content/04.study.md +++ b/content/04.study.md @@ -65,7 +65,8 @@ While utilizing reference-based libraries demonstrates strong predictive value f When a referenced-based library is not available for use, unsupervised methods are able to estimate these immune profiles [@tag:Titus2017]. Methods that do not rely on these reference libraries [@tag:Houseman2016], are limited by being unable to fully capture the nonlinearity of the methylation data. -There are many promising deep learning approaches that serve to expand the number of CpG sites whose DNA methylation state can be studied by capturing the complex interactions between different regions of DNA and extract the complete set of informative biologically relevant features. +Deep learning approaches have numerous potential applications for DNA methylation data. +Imputation methods that capture complex interactions between different regions of DNA can expand the number of CpG sites whose DNA methylation state can be studied, and ideally these methods can derive their own informative, biologically-relevant features. The main approaches focus on: 1) estimating regions of methylation status and imputing missing methylation values, 2) performing classification and regression tasks, and 3) understanding latent embeddings of methylation states from which to extract biologically meaningful features, infer interpolated disease states, and uncover relevant CpG sites for the above prediction tasks. ### Splicing From a84c4a1b8134d7633529283a9e04be6b42b29896 Mon Sep 17 00:00:00 2001 From: brockclarke Date: Fri, 26 Jul 2019 11:27:57 -0400 Subject: [PATCH 08/31] Update content/04.study.md Co-Authored-By: Casey Greene --- content/04.study.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/04.study.md b/content/04.study.md index 966b1eef..214e6e99 100644 --- a/content/04.study.md +++ b/content/04.study.md @@ -67,7 +67,7 @@ Methods that do not rely on these reference libraries [@tag:Houseman2016], are l Deep learning approaches have numerous potential applications for DNA methylation data. Imputation methods that capture complex interactions between different regions of DNA can expand the number of CpG sites whose DNA methylation state can be studied, and ideally these methods can derive their own informative, biologically-relevant features. -The main approaches focus on: 1) estimating regions of methylation status and imputing missing methylation values, 2) performing classification and regression tasks, and 3) understanding latent embeddings of methylation states from which to extract biologically meaningful features, infer interpolated disease states, and uncover relevant CpG sites for the above prediction tasks. +The primary deep learning methods developed to date focus on: 1) estimating regions of methylation status and imputing missing methylation values, 2) performing classification and regression tasks, and 3) using the latent embeddings of methylation states to derive biologically meaningful features, infer interpolated disease states, and uncover CpG sites that aid the above prediction tasks. ### Splicing From a0bc01e8de64f1259a772de392e77808fb2aa382 Mon Sep 17 00:00:00 2001 From: Brock Date: Wed, 31 Jul 2019 09:53:50 -0400 Subject: [PATCH 09/31] changes in response to review here added refs and revised some language --- content/.Rhistory | 0 content/04.study.md | 17 +++++++++-------- content/citation-tags.tsv | 15 +++++++++++++++ webpage/images | 1 - webpage/index.html | 1 - webpage/manuscript.pdf | 1 - 6 files changed, 24 insertions(+), 11 deletions(-) create mode 100644 content/.Rhistory delete mode 120000 webpage/images delete mode 120000 webpage/index.html delete mode 120000 webpage/manuscript.pdf diff --git a/content/.Rhistory b/content/.Rhistory new file mode 100644 index 00000000..e69de29b diff --git a/content/04.study.md b/content/04.study.md index 214e6e99..60647497 100644 --- a/content/04.study.md +++ b/content/04.study.md @@ -52,18 +52,19 @@ For example, the effects of cellular heterogeneity on basic biology and disease #### Introduction DNA methylation, is the process of adding a methyl group to a cytosine in the context of a CpG dinucleotide. -This DNA-level epigenetic modification regulates gene transcription, is critical in development, and alterations to DNA methylation are well-established as contributing to pathophysiology of many diseases including cancers. -Studies of DNA methylation have also shed light on the processes involving initial differentiation of stem cells, aging and pathogenesis in response to environmental exposures. +This DNA-level epigenetic modification regulates gene transcription, is critical in development, and alterations to DNA methylation are well-established as contributing to pathophysiology of many diseases including cancers [@tag:Roberston2005],[@tag:Feinberg2018]. +Studies of DNA methylation have demonstrated the fundamental role of DNA methylation in cell lineage specification starting with stem cell differentiation [@tag:Meissner2008], [@tag:Nazor2012], as well as a strong relationship of DNA methylation with aging phenotypes [@tag:Kwabi-Addo2007], [@tag:Fraga2005], and pathogenesis in response to environmental exposures [@tag:Christensen2009], [@tag:Relton2010]. -Traditional analytic approaches to DNA methylation data often focus on estimating differential DNA methylation between groups or related with an outcome using linear mixed effects models. -In addition, a growing application of DNA methylation measures is to infer cellular or subject phenotypes from samples and either examine the relation of these phenotypes with outcomes or disease states directly, and/or include them in models as covariates. +Traditional analytic approaches to DNA methylation data often focus on estimating differential DNA methylation between groups or related with an outcome using linear mixed effects models, so-called epigenome-wide association studies (EWAS) [@tag:Laird2010], [@tag:Wilhelm-Benartzi2013], [@tag:Liu2013], [@tag:Teschendorff2017]. +In addition, a growing application of DNA methylation measures is to infer cellular or subject phenotypes from samples and either examine the relation of these phenotypes with outcomes or disease states directly, and/or include them in models as covariates [@tag:Titus2017], [@tag:Salas2018_GR], [@tag:Zhang2019], [@tag:Horvath2014], [@tag:Quach2017]. For example, inference of subject age using DNA methylation clock approaches are established [@tag:Horvath2013], and are starting to be applied to test the relation of biological age with disease risk and outcomes [@tag:Kresovich2019]. Different cell types have different DNA methylation profiles. -Reference DNA methylation profiles of leukocytes are available, which makes it feasible to infer immune cell type proportions with measures of DNA methylation in peripheral blood DNA [@tag:Houseman2012],[@tag:Salas2018], a novel approach to immunophenotyping that only requires. +Reference DNA methylation profiles of leukocytes are available, which makes it feasible to infer immune cell type proportions with measures of DNA methylation in peripheral blood DNA [@tag:Houseman2012],[@tag:Salas2018], a novel approach to immunophenotyping that only requires DNA. Cell type inference is important for adjusting for cell-type composition in epigenome-wide association studies [@tag:Teschendorff2017]. -While utilizing reference-based libraries demonstrates strong predictive value for immune cell type estimation, these methods severely restrict the amount of underlying biology that can be understood and correlated with disease manifestations and phenotypes. -When a referenced-based library is not available for use, unsupervised methods are able to estimate these immune profiles [@tag:Titus2017]. -Methods that do not rely on these reference libraries [@tag:Houseman2016], are limited by being unable to fully capture the nonlinearity of the methylation data. +While utilizing reference-based libraries demonstrates strong predictive value for immune cell type estimation and has broad utiltiy, cell composition mixtures per se, and methods to incorporate estimates of mixures pose important considerations on the interpretation of underlying biology associated with disease manifestations and phenotypes. +When a referenced-based library is not available for use, methods that do not rely on these reference libraries, so called reference-free deconvolution [@tag:Houseman2016], are available to decompose singal purported to be contributed by cell types. +However, using reference-free cell type proportion estimates as potential confounders in adjusted models can be overly conservative as as outcome-associated variation in DNA methylation may be decomposed into putative cell type estimates. +Additional validated reference-based libraries for other tissue types, advancements in reference-free deconvolution methods, and application of deep learning methods are expected to provide new opportunities to understand and interpret DNA methylation in human health and disease. Deep learning approaches have numerous potential applications for DNA methylation data. Imputation methods that capture complex interactions between different regions of DNA can expand the number of CpG sites whose DNA methylation state can be studied, and ideally these methods can derive their own informative, biologically-relevant features. diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index 9f726e7d..24807ead 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -39,6 +39,7 @@ Chen2015_trans_species doi:10.1093/bioinformatics/btv315 Choi2016_retain arxiv:1608.05745 Choi2016_gram arxiv:1611.07012 Chollet2016_xception arxiv:1610.02357 +Christensen2009 doi:10.1371/journal.pgen.1000602 Chryssolouris1996_confidence doi:10.1109/72.478409 Ciresan2013_mitosis doi:10.1007/978-3-642-40763-5_51 Coates2013_cots_hpc url:http://www.jmlr.org/proceedings/papers/v28/coates13.html @@ -68,8 +69,10 @@ Esfahani2016_melanoma doi:10.1109/EMBC.2016.7590963 Essinger2010_taxonomic doi:10.1109/IJCNN.2010.5596644 Esteva2017_skin_cancer_nature doi:10.1038/nature21056 Faruqi url:http://alifar76.github.io/sklearn-metrics/ +Feinberg2018 doi:10.1056/NEJMra1402513 Finnegan2017_maximum doi:10.1101/105957 Fong2017_perturb doi:10.1109/ICCV.2017.371 +Fraga2005 doi:doi.org/10.1073/pnas.0500398102 Gal2015_dropout arxiv:1506.02142 Gaublomme2015_th17 doi:10.1016/j.cell.2015.11.009 Gargeya2017_dr doi:10.1016/j.ophtha.2017.02.008 @@ -97,6 +100,7 @@ Hochreiter doi:10.1093/bioinformatics/btm247 Hoff doi:10.1093/nar/gkp327 Horton1992_assessment doi:10.1093/nar/20.16.4331 Horvath2013 doi:10.1186/gb-2013-14-10-r115 +Horvath2014 doi:10.1073/pnas.1412759111 Houseman2012 doi:10.1186/1471-2105-13-86 Houseman2016 doi:10.1186/s12859-016-1140-4 Hubara2016_qnn arxiv:1609.07061 @@ -128,7 +132,9 @@ Kraus2017_deeploc doi:10.15252/msb.20177551 Kresovich2019 doi:10.1093/jnci/djz020 Krizhevsky2013_nips_cnn url:https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf Krizhevsky2014_weird_trick arxiv:1404.5997 +Kwabi-Addo2007 doi:10.1158/1078-0432.CCR-07-0085 Lacey2016_dl_fpga arxiv:1602.04283 +Laird2010 doi:10.1038/nrg2732 Lakhani2017_radiography doi:10.1148/radiol.2017162326 Lanchantin2016_motif arxiv:1608.03644 Lee2016_deeptarget arxiv:1603.09123v2 @@ -144,6 +150,7 @@ Lipton2015_lstm arxiv:1510.07641 Litjens2016_histopath_survey doi:10.1038/srep26286 Litjens2017_medimage_survey doi:10.1016/j.media.2017.07.005 Lisboa2006_review doi:10.1016/j.neunet.2005.10.007 +Liu2013 doi:10.1038/nbt.2487 Liu doi:10.1371/journal.pone.0053253 Liu2016_towards arxiv:1604.07043 Liu2016_sc_transcriptome doi:10.12688/f1000research.7223.1 @@ -163,6 +170,7 @@ Mapreduce doi:10.1145/1327452.1327492 Mayr2016_deep_tox doi:10.3389/fenvs.2015.00080 McHardy doi:10.1038/nmeth976 McHardy2 doi:10.7717/peerj.1603 +Meissner2008 doi:10.1038/nature07107 Metaphlan doi:10.1038/nmeth.2066 Meng2016_mllib arxiv:1505.06807 Min2016_deepenhancer doi:10.1109/BIBM.2016.7822593 @@ -172,6 +180,7 @@ Mrzelj url:https://repozitorij.uni-lj.si/IzpisGradiva.php?id=85515 matis doi:10.1016/S0097-8485(96)80015-5 nbc doi:10.1093/bioinformatics/btq619 Murdoch2017_automatic arxiv:1702.02540 +Nazor2012 doi:10.1016/j.stem.2012.02.013 Nemati2016_rl doi:10.1109/EMBC.2016.7591355 Nguyen2014_adversarial arxiv:1412.1897v4 Ngiam2011 url:https://ai.stanford.edu/~ang/papers/icml11-MultimodalDeepLearning.pdf @@ -190,6 +199,7 @@ PerezSianes2016_screening doi:10.1007/978-3-319-40126-3_2 Phymm doi:10.1038/nmeth.1358 Poplin2016_deepvariant doi:10.1101/092890 Pratt2016_dr doi:10.1016/j.procs.2016.07.014 +Quach2017 doi:10.18632/aging.101168 Quang2017_factor doi:10.1101/151274 Qin2017_onehot doi:10.1371/journal.pcbi.1005403 Qiu2017_graph_embedding doi:10.1101/110668 @@ -201,13 +211,16 @@ Rakhlin2018_histology doi:10.1101/259911 Ramsundar2015_multitask_drug arxiv:1502.02072 Ranganath2016_deep arxiv:1608.02158 Raina2009_gpu doi:10.1145/1553374.1553486 +Relton2010 doi:10.1371/journal.pmed.1000356 Ribeiro2016_lime arxiv:1602.04938 +Robertson2005 doi:10.1038/nrg1655 Rogers2010_fingerprints doi:10.1021/ci100050t Roth2015_view_agg_cad doi:10.1109/TMI.2015.2482920 Romero2017_diet url:https://openreview.net/pdf?id=Sk-oDY9ge Rosenberg2015_synthetic_seqs doi:10.1016/j.cell.2015.09.054 Russakovsky2015_imagenet doi:10.1007/s11263-015-0816-y Sa2015_buckwild pmcid:PMC4907892 +Salas2018_GR doi:10.1101/gr.233213.117 Salas2018 doi:10.1186/s13059-018-1448-7 Salzberg doi:10.1186/1471-2105-11-544 Schatz2010_dna_cloud doi:10.1038/nbt0710-691 @@ -266,6 +279,7 @@ Wang2016_protein_contact doi:10.1371/journal.pcbi.1005324 Wasson1985_clinical doi:10.1056/NEJM198509263131306 WayGreene2017_eval arxiv:1711.04828 WayGreene2017_tybalt doi:10.1101/174474 +Wilhelm-Benartzi2013 doi:10.1038/bjc.2013.496 Word2Vec arxiv:1301.3781 wgsquikr doi:10.1371/journal.pone.0091784 Wu2017_molecule_net doi:10.1039/C7SC02664A @@ -284,6 +298,7 @@ Zeng2015 doi:10.1186/s12859-015-0553-9 Zeng2016_convolutional doi:10.1093/bioinformatics/btw255 Zhang2015_multitask_tl doi:10.1145/2783258.2783304 Zhang2017_generalization arxiv:1611.03530v2 +Zhang2019 doi:10.1186/s12885-019-5932-6 Zhou2015_deep_sea doi:10.1038/nmeth.3547 Zhu2016_advers_mamm doi:10.1101/095786 Zhu2016_mult_inst_mamm doi:10.1101/095794 diff --git a/webpage/images b/webpage/images deleted file mode 120000 index 2b55bac8..00000000 --- a/webpage/images +++ /dev/null @@ -1 +0,0 @@ -v/latest/images \ No newline at end of file diff --git a/webpage/index.html b/webpage/index.html deleted file mode 120000 index 2f982aca..00000000 --- a/webpage/index.html +++ /dev/null @@ -1 +0,0 @@ -v/latest/index.html \ No newline at end of file diff --git a/webpage/manuscript.pdf b/webpage/manuscript.pdf deleted file mode 120000 index b8867276..00000000 --- a/webpage/manuscript.pdf +++ /dev/null @@ -1 +0,0 @@ -v/latest/manuscript.pdf \ No newline at end of file From 00ed16d971291c5ab5deea2206bcf344d664c662 Mon Sep 17 00:00:00 2001 From: brockclarke Date: Wed, 31 Jul 2019 16:08:11 -0400 Subject: [PATCH 10/31] Update content/04.study.md Co-Authored-By: Casey Greene --- content/04.study.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/content/04.study.md b/content/04.study.md index d61665f8..5e4941ef 100644 --- a/content/04.study.md +++ b/content/04.study.md @@ -57,7 +57,8 @@ Traditional analytic approaches to DNA methylation data often focus on estimatin In addition, a growing application of DNA methylation measures is to infer cellular or subject phenotypes from samples and either examine the relation of these phenotypes with outcomes or disease states directly, and/or include them in models as covariates [@tag:Titus2017], [@tag:Salas2018_GR], [@tag:Zhang2019], [@tag:Horvath2014], [@tag:Quach2017]. For example, inference of subject age using DNA methylation clock approaches are established [@tag:Horvath2013], and are starting to be applied to test the relation of biological age with disease risk and outcomes [@tag:Kresovich2019]. Different cell types have different DNA methylation profiles. -Reference DNA methylation profiles of leukocytes are available, which makes it feasible to infer immune cell type proportions with measures of DNA methylation in peripheral blood DNA [@tag:Houseman2012],[@tag:Salas2018], a novel approach to immunophenotyping that only requires DNA. +A novel approach to immunophenotyping combines measurements with Reference DNA methylation profiles of leukocytes, which are available, to infer immune cell type proportions [@tag:Houseman2012],[@tag:Salas2018]. +This strategy is particularly helpful when only DNA is available from a sample. Cell type inference is important for adjusting for cell-type composition in epigenome-wide association studies [@tag:Teschendorff2017]. While utilizing reference-based libraries demonstrates strong predictive value for immune cell type estimation and has broad utiltiy, cell composition mixtures per se, and methods to incorporate estimates of mixures pose important considerations on the interpretation of underlying biology associated with disease manifestations and phenotypes. When a referenced-based library is not available for use, methods that do not rely on these reference libraries, so called reference-free deconvolution [@tag:Houseman2016], are available to decompose singal purported to be contributed by cell types. From 07fdc0390d112deec0aa9425eb4383a438149936 Mon Sep 17 00:00:00 2001 From: brockclarke Date: Wed, 31 Jul 2019 16:08:54 -0400 Subject: [PATCH 11/31] Update content/04.study.md Co-Authored-By: Casey Greene --- content/04.study.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/04.study.md b/content/04.study.md index 5e4941ef..ba4574c5 100644 --- a/content/04.study.md +++ b/content/04.study.md @@ -61,7 +61,7 @@ A novel approach to immunophenotyping combines measurements with Reference DNA m This strategy is particularly helpful when only DNA is available from a sample. Cell type inference is important for adjusting for cell-type composition in epigenome-wide association studies [@tag:Teschendorff2017]. While utilizing reference-based libraries demonstrates strong predictive value for immune cell type estimation and has broad utiltiy, cell composition mixtures per se, and methods to incorporate estimates of mixures pose important considerations on the interpretation of underlying biology associated with disease manifestations and phenotypes. -When a referenced-based library is not available for use, methods that do not rely on these reference libraries, so called reference-free deconvolution [@tag:Houseman2016], are available to decompose singal purported to be contributed by cell types. +When a referenced library is not available for use, methods that do not rely on these reference libraries, so called reference-free deconvolution [@tag:Houseman2016], are available to decompose signal purported to be contributed by cell types. However, using reference-free cell type proportion estimates as potential confounders in adjusted models can be overly conservative as as outcome-associated variation in DNA methylation may be decomposed into putative cell type estimates. Additional validated reference-based libraries for other tissue types, advancements in reference-free deconvolution methods, and application of deep learning methods are expected to provide new opportunities to understand and interpret DNA methylation in human health and disease. From dc6134263e7c78f0ee3099bb5d656248a18963c3 Mon Sep 17 00:00:00 2001 From: brockclarke Date: Wed, 31 Jul 2019 16:10:20 -0400 Subject: [PATCH 12/31] Update content/04.study.md Co-Authored-By: Casey Greene --- content/04.study.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/04.study.md b/content/04.study.md index ba4574c5..dfb5fe89 100644 --- a/content/04.study.md +++ b/content/04.study.md @@ -60,7 +60,7 @@ Different cell types have different DNA methylation profiles. A novel approach to immunophenotyping combines measurements with Reference DNA methylation profiles of leukocytes, which are available, to infer immune cell type proportions [@tag:Houseman2012],[@tag:Salas2018]. This strategy is particularly helpful when only DNA is available from a sample. Cell type inference is important for adjusting for cell-type composition in epigenome-wide association studies [@tag:Teschendorff2017]. -While utilizing reference-based libraries demonstrates strong predictive value for immune cell type estimation and has broad utiltiy, cell composition mixtures per se, and methods to incorporate estimates of mixures pose important considerations on the interpretation of underlying biology associated with disease manifestations and phenotypes. +While reference-based libraries have strong predictive value for immune cell type estimation and has broad utility, cell composition mixtures per se, and methods to incorporate estimates of mixtures pose important considerations on the interpretation of underlying biology associated with disease manifestations and phenotypes. When a referenced library is not available for use, methods that do not rely on these reference libraries, so called reference-free deconvolution [@tag:Houseman2016], are available to decompose signal purported to be contributed by cell types. However, using reference-free cell type proportion estimates as potential confounders in adjusted models can be overly conservative as as outcome-associated variation in DNA methylation may be decomposed into putative cell type estimates. Additional validated reference-based libraries for other tissue types, advancements in reference-free deconvolution methods, and application of deep learning methods are expected to provide new opportunities to understand and interpret DNA methylation in human health and disease. From 84236c58b53067522ac5eb36d694d7d55d497e88 Mon Sep 17 00:00:00 2001 From: Brock Date: Wed, 31 Jul 2019 16:12:22 -0400 Subject: [PATCH 13/31] Update 04.study.md --- content/04.study.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/04.study.md b/content/04.study.md index dfb5fe89..aefa2a3c 100644 --- a/content/04.study.md +++ b/content/04.study.md @@ -61,7 +61,7 @@ A novel approach to immunophenotyping combines measurements with Reference DNA m This strategy is particularly helpful when only DNA is available from a sample. Cell type inference is important for adjusting for cell-type composition in epigenome-wide association studies [@tag:Teschendorff2017]. While reference-based libraries have strong predictive value for immune cell type estimation and has broad utility, cell composition mixtures per se, and methods to incorporate estimates of mixtures pose important considerations on the interpretation of underlying biology associated with disease manifestations and phenotypes. -When a referenced library is not available for use, methods that do not rely on these reference libraries, so called reference-free deconvolution [@tag:Houseman2016], are available to decompose signal purported to be contributed by cell types. +When a reference library is not available for use, methods that do not rely on these reference libraries, so called reference-free deconvolution [@tag:Houseman2016], are available to decompose signal purported to be contributed by cell types. However, using reference-free cell type proportion estimates as potential confounders in adjusted models can be overly conservative as as outcome-associated variation in DNA methylation may be decomposed into putative cell type estimates. Additional validated reference-based libraries for other tissue types, advancements in reference-free deconvolution methods, and application of deep learning methods are expected to provide new opportunities to understand and interpret DNA methylation in human health and disease. From 6f641bc29aaa8f318e7339fda166c10f6c3d04fa Mon Sep 17 00:00:00 2001 From: brockclarke Date: Wed, 31 Jul 2019 16:15:50 -0400 Subject: [PATCH 14/31] Update content/citation-tags.tsv Co-Authored-By: Casey Greene --- content/citation-tags.tsv | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index 0662a56e..ca55b545 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -135,7 +135,7 @@ Krizhevsky2013_nips_cnn url:https://papers.nips.cc/paper/4824-imagenet-classific Krizhevsky2014_weird_trick arxiv:1404.5997 Kwabi-Addo2007 doi:10.1158/1078-0432.CCR-07-0085 Khwaja2017 doi:10.1109/BIOCAS.2017.8325078 -Khwaja2018 doi:1810.01243 +Khwaja2018 arxiv:1810.01243 Lacey2016_dl_fpga arxiv:1602.04283 Laird2010 doi:10.1038/nrg2732 Lakhani2017_radiography doi:10.1148/radiol.2017162326 From eb540d7595e7d873b9516eb4240badee508cf184 Mon Sep 17 00:00:00 2001 From: brockclarke Date: Wed, 31 Jul 2019 20:23:04 -0400 Subject: [PATCH 15/31] Update content/citation-tags.tsv Co-Authored-By: Anthony Gitter --- content/citation-tags.tsv | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index ca55b545..75dde652 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -72,7 +72,7 @@ Faruqi url:http://alifar76.github.io/sklearn-metrics/ Feinberg2018 doi:10.1056/NEJMra1402513 Finnegan2017_maximum doi:10.1101/105957 Fong2017_perturb doi:10.1109/ICCV.2017.371 -Fraga2005 doi:doi.org/10.1073/pnas.0500398102 +Fraga2005 doi:10.1073/pnas.0500398102 Fu2019 doi:10.1109/TCBB.2019.2909237 Gal2015_dropout arxiv:1506.02142 Gaublomme2015_th17 doi:10.1016/j.cell.2015.11.009 From edf269daaa33b33e942b65e22e0afc34ad860d03 Mon Sep 17 00:00:00 2001 From: Casey Greene Date: Wed, 31 Jul 2019 20:51:50 -0400 Subject: [PATCH 16/31] delete Rhistory --- content/.Rhistory | 0 1 file changed, 0 insertions(+), 0 deletions(-) delete mode 100644 content/.Rhistory diff --git a/content/.Rhistory b/content/.Rhistory deleted file mode 100644 index e69de29b..00000000 From 6968452ebc26f7d32cd6726150986fa9fe4185f8 Mon Sep 17 00:00:00 2001 From: brockclarke Date: Wed, 31 Jul 2019 21:01:18 -0400 Subject: [PATCH 17/31] Update content/citation-tags.tsv Co-Authored-By: Casey Greene --- content/citation-tags.tsv | 1 + 1 file changed, 1 insertion(+) diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index 75dde652..02f681f3 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -10,6 +10,7 @@ Asgari doi:10.1371/journal.pone.0141287 blast doi:10.1016/S0022-2836(05)80360-2 Angermueller2016_dl_review doi:10.15252/msb.20156651 Angermueller2016_single_methyl doi:10.1186/s13059-017-1189-z +Angermueller2017 doi:10.1186/s13059-017-1189-z Artemov2016_clinical doi:10.1101/095653 Arvaniti2016_rare_subsets doi:10.1101/046508 Bach2015_on doi:10.1371/journal.pone.0130140 From 2327af5d938607edb03d1a5e307ca83c392befe4 Mon Sep 17 00:00:00 2001 From: brockclarke Date: Wed, 31 Jul 2019 21:01:32 -0400 Subject: [PATCH 18/31] Update content/citation-tags.tsv Co-Authored-By: Casey Greene --- content/citation-tags.tsv | 1 + 1 file changed, 1 insertion(+) diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index 02f681f3..42fe5ab0 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -28,6 +28,7 @@ Bracken2016_mirna doi:10.1038/nrg.2016.134 Boza doi:10.1371/journal.pone.0178751 Buggenthin2017_imaged_lineage doi:10.1038/nmeth.4182 Burlina2016_amd doi:10.1109/ISBI.2016.7493240 +Chatterjee2018 arxiv:1807.09617 Caruana2014_need arxiv:1312.6184 Caruana2015_intelligible url:https://dl.acm.org/citation.cfm?id=2788613 Chaudhary2017_multiom_liver_cancer doi:10.1101/114892 From 978e2dd45699e8931beda6a5559d74a6a19b56bb Mon Sep 17 00:00:00 2001 From: brockclarke Date: Wed, 31 Jul 2019 21:01:41 -0400 Subject: [PATCH 19/31] Update content/citation-tags.tsv Co-Authored-By: Casey Greene --- content/citation-tags.tsv | 1 + 1 file changed, 1 insertion(+) diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index 42fe5ab0..8379f395 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -49,6 +49,7 @@ Codella2016_ensemble_melanoma arxiv:1610.04662 Consortium2012_encode doi:10.1038/nature11247 CudNN arxiv:1410.0759 Dahl2014_multi_qsar arxiv:1406.1231 +Darst2018 doi:10.1186/s12863-018-0646-3 Dean2012_nips_downpour url:http://research.google.com/archive/large_deep_networks_nips2012.html DeepChem url:https://github.com/deepchem/deepchem Deming2016_genetic arxiv:1605.07156 From 3796879ae3584ce204ea5ed07c023f6993878419 Mon Sep 17 00:00:00 2001 From: brockclarke Date: Wed, 31 Jul 2019 21:02:13 -0400 Subject: [PATCH 20/31] Update content/citation-tags.tsv Co-Authored-By: Casey Greene --- content/citation-tags.tsv | 1 + 1 file changed, 1 insertion(+) diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index 8379f395..43a2677b 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -111,6 +111,7 @@ Hubara2016_qnn arxiv:1609.07061 Huddar2016_predicting doi:10.1109/ACCESS.2016.2618775 Hughes2016_macromol_react doi:10.1021/acscentsci.6b00162 Iglovikov2017_baa doi:10.1101/234120 +Islam2018 doi:10.1186/s12919-018-0121-1 Ithapu2015_efficient doi:10.1016/j.jalz.2015.01.010 Jafari2016_skin_lesions doi:10.1007/s11548-017-1567-8 Jha2017_integrative_models doi:10.1101/104869 From 30ef4867d1178b19678358d3632f092e8a9d53c3 Mon Sep 17 00:00:00 2001 From: brockclarke Date: Wed, 31 Jul 2019 21:02:22 -0400 Subject: [PATCH 21/31] Update content/citation-tags.tsv Co-Authored-By: Casey Greene --- content/citation-tags.tsv | 1 + 1 file changed, 1 insertion(+) diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index 43a2677b..09cd71e4 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -133,6 +133,7 @@ Koh2016_denoising doi:10.1101/052118 Koh2017_understanding arxiv:1703.04730 Kooi2016_mamm_lesions doi:10.1016/j.media.2016.07.007 Kooi2017_mamm_tl doi:10.1002/mp.12110 +Korfiatis2017 doi:10.1007/s10278-017-0009-z Kraus2017_deeploc doi:10.15252/msb.20177551 Kresovich2019 doi:10.1093/jnci/djz020 Krizhevsky2013_nips_cnn url:https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf From b75d297b0a4af7c22e1eb6c6c81e96181f3cba56 Mon Sep 17 00:00:00 2001 From: brockclarke Date: Wed, 31 Jul 2019 21:02:32 -0400 Subject: [PATCH 22/31] Update content/citation-tags.tsv Co-Authored-By: Casey Greene --- content/citation-tags.tsv | 1 + 1 file changed, 1 insertion(+) diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index 09cd71e4..8aa5ec29 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -201,6 +201,7 @@ onecodex url:https://www.onecodex.com/ Papernot2017_pate url:https://openreview.net/forum?id=HkwoSDPgg Park2016_deepmirgene arxiv:1605.00017 Parnamaa2017 doi:10.1534/g3.116.033654 +Pan2018 doi:10.1101/438218 Pawlowski2016 doi:10.1101/085118 Pereira2016_docking doi:10.1021/acs.jcim.6b00355 PerezSianes2016_screening doi:10.1007/978-3-319-40126-3_2 From 41a5a358812e6a761d9cee77bb26ee3ab8a2d15c Mon Sep 17 00:00:00 2001 From: brockclarke Date: Wed, 31 Jul 2019 21:02:44 -0400 Subject: [PATCH 23/31] Update content/citation-tags.tsv Co-Authored-By: Casey Greene --- content/citation-tags.tsv | 1 + 1 file changed, 1 insertion(+) diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index 8aa5ec29..41b1bc8f 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -203,6 +203,7 @@ Park2016_deepmirgene arxiv:1605.00017 Parnamaa2017 doi:10.1534/g3.116.033654 Pan2018 doi:10.1101/438218 Pawlowski2016 doi:10.1101/085118 +Peng2019 doi:10.1101/527044 Pereira2016_docking doi:10.1021/acs.jcim.6b00355 PerezSianes2016_screening doi:10.1007/978-3-319-40126-3_2 Phymm doi:10.1038/nmeth.1358 From 0a88697db6666337f825305420fc27208bd93642 Mon Sep 17 00:00:00 2001 From: brockclarke Date: Wed, 31 Jul 2019 21:02:52 -0400 Subject: [PATCH 24/31] Update content/citation-tags.tsv Co-Authored-By: Casey Greene --- content/citation-tags.tsv | 1 + 1 file changed, 1 insertion(+) diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index 41b1bc8f..a11cd7da 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -213,6 +213,7 @@ Quach2017 doi:10.18632/aging.101168 Quang2017_factor doi:10.1101/151274 Qin2017_onehot doi:10.1371/journal.pcbi.1005403 Qiu2017_graph_embedding doi:10.1101/110668 +Qiu2018 doi:10.1101/406066 Ragoza2016_protein arxiv:1612.02751 RAD2010_view_cc doi:10.1145/1721654.1721672 Radford_dcgan arxiv:1511.06434v2 From 94815b678c96d99b92a918475f72d03419e35e42 Mon Sep 17 00:00:00 2001 From: brockclarke Date: Wed, 31 Jul 2019 21:03:01 -0400 Subject: [PATCH 25/31] Update content/citation-tags.tsv Co-Authored-By: Casey Greene --- content/citation-tags.tsv | 1 + 1 file changed, 1 insertion(+) diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index a11cd7da..d84493fd 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -276,6 +276,7 @@ Tan2016_eadage doi:10.1101/078659 TAC-ELM doi:10.1142/S0219720012500151 TensorFlow arxiv:1603.04467 Teschendorff2017 doi:10.2217/epi-2016-0153 +Tian2019 doi:10.1186/s12864-019-5488-5 Titus2017 doi:10.1093/hmg/ddx275 Torracinta2016_deep_snp doi:10.1101/097469 Torracinta2016_sim doi:10.1101/079087 From 42eac498c89273c3d6aecb380524a6bb8d14a540 Mon Sep 17 00:00:00 2001 From: brockclarke Date: Wed, 31 Jul 2019 21:03:09 -0400 Subject: [PATCH 26/31] Update content/citation-tags.tsv Co-Authored-By: Casey Greene --- content/citation-tags.tsv | 1 + 1 file changed, 1 insertion(+) diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index d84493fd..42230815 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -287,6 +287,7 @@ Vera2016_sc_analysis doi:10.1146/annurev-genet-120215-034854 Vervier doi:10.1093/bioinformatics/btv683 Wallach2015_atom_net arxiv:1510.02855 Wang2016_breast_cancer arxiv:1606.05718 +Wang2016_methyl doi:10.1038/srep19598 Wang2016_protein_contact doi:10.1371/journal.pcbi.1005324 Wasson1985_clinical doi:10.1056/NEJM198509263131306 WayGreene2017_eval arxiv:1711.04828 From 49a71511ed2746bdc757eb5fcb9aad02d1e63ceb Mon Sep 17 00:00:00 2001 From: Anthony Gitter Date: Thu, 1 Aug 2019 06:01:54 -0500 Subject: [PATCH 27/31] Restore webpage files --- webpage/images | 1 + webpage/index.html | 1 + webpage/manuscript.pdf | 1 + 3 files changed, 3 insertions(+) create mode 120000 webpage/images create mode 120000 webpage/index.html create mode 120000 webpage/manuscript.pdf diff --git a/webpage/images b/webpage/images new file mode 120000 index 00000000..2b55bac8 --- /dev/null +++ b/webpage/images @@ -0,0 +1 @@ +v/latest/images \ No newline at end of file diff --git a/webpage/index.html b/webpage/index.html new file mode 120000 index 00000000..2f982aca --- /dev/null +++ b/webpage/index.html @@ -0,0 +1 @@ +v/latest/index.html \ No newline at end of file diff --git a/webpage/manuscript.pdf b/webpage/manuscript.pdf new file mode 120000 index 00000000..b8867276 --- /dev/null +++ b/webpage/manuscript.pdf @@ -0,0 +1 @@ +v/latest/manuscript.pdf \ No newline at end of file From 50983fc955be7c963cea40d9fb674c04c31bf107 Mon Sep 17 00:00:00 2001 From: Brock Date: Thu, 1 Aug 2019 08:59:39 -0400 Subject: [PATCH 28/31] Update 04.study.md correcting spelling error for Roberston --- content/04.study.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/04.study.md b/content/04.study.md index aefa2a3c..35b5c319 100644 --- a/content/04.study.md +++ b/content/04.study.md @@ -50,7 +50,7 @@ For example, the effects of cellular heterogeneity on basic biology and disease ### DNA methylation DNA methylation, is the process of adding a methyl group to a cytosine in the context of a CpG dinucleotide. -This DNA-level epigenetic modification regulates gene transcription, is critical in development, and alterations to DNA methylation are well-established as contributing to pathophysiology of many diseases including cancers [@tag:Roberston2005],[@tag:Feinberg2018]. +This DNA-level epigenetic modification regulates gene transcription, is critical in development, and alterations to DNA methylation are well-established as contributing to pathophysiology of many diseases including cancers [@tag:Robertson2005],[@tag:Feinberg2018]. Studies of DNA methylation have demonstrated the fundamental role of DNA methylation in cell lineage specification starting with stem cell differentiation [@tag:Meissner2008], [@tag:Nazor2012], as well as a strong relationship of DNA methylation with aging phenotypes [@tag:Kwabi-Addo2007], [@tag:Fraga2005], and pathogenesis in response to environmental exposures [@tag:Christensen2009], [@tag:Relton2010]. Traditional analytic approaches to DNA methylation data often focus on estimating differential DNA methylation between groups or related with an outcome using linear mixed effects models, so-called epigenome-wide association studies (EWAS) [@tag:Laird2010], [@tag:Wilhelm-Benartzi2013], [@tag:Liu2013], [@tag:Teschendorff2017]. From 1ab5ac67ecdc8005d318f06dfa67e43cb35c73cc Mon Sep 17 00:00:00 2001 From: brockclarke Date: Thu, 1 Aug 2019 10:47:22 -0400 Subject: [PATCH 29/31] Update content/citation-tags.tsv Co-Authored-By: Casey Greene --- content/citation-tags.tsv | 2 ++ 1 file changed, 2 insertions(+) diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index 42230815..bd35080b 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -149,6 +149,8 @@ Lee2016_deeptarget arxiv:1603.09123v2 Lee2016_emr_oct_amd doi:10.1101/094276 Lei2016_rationalizing arxiv:1606.04155 Leibig2016_dr doi:10.1101/084210 +Levy2019 doi:10.1101/692665 +Levy-Jurgenson2018 doi:10.1101/491357 Li2014_minibatch doi:10.1145/2623330.2623612 Li2016_variation doi:10.1126/science.aad9417 Liang2015_exprs_cancer doi:10.1109/TCBB.2014.2377729 From bb3cc4aac34787614708241fe728fe0f8f26598e Mon Sep 17 00:00:00 2001 From: brockclarke Date: Thu, 1 Aug 2019 10:47:38 -0400 Subject: [PATCH 30/31] Update content/citation-tags.tsv Co-Authored-By: Casey Greene --- content/citation-tags.tsv | 1 + 1 file changed, 1 insertion(+) diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index bd35080b..f5f5f651 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -184,6 +184,7 @@ Meissner2008 doi:10.1038/nature07107 Metaphlan doi:10.1038/nmeth.2066 Meng2016_mllib arxiv:1505.06807 Min2016_deepenhancer doi:10.1109/BIBM.2016.7822593 +Momeni2018 doi:10.1101/438341 Moritz2015_sparknet arxiv:1511.06051 Mordvintsev2015_inceptionism url:http://googleresearch.blogspot.co.uk/2015/06/inceptionism-going-deeper-into-neural.html Mrzelj url:https://repozitorij.uni-lj.si/IzpisGradiva.php?id=85515 From 6efc3af8a415596cf83c2b3c0803b48d9ca65c56 Mon Sep 17 00:00:00 2001 From: brockclarke Date: Thu, 1 Aug 2019 10:47:56 -0400 Subject: [PATCH 31/31] Update content/citation-tags.tsv Co-Authored-By: Casey Greene --- content/citation-tags.tsv | 1 + 1 file changed, 1 insertion(+) diff --git a/content/citation-tags.tsv b/content/citation-tags.tsv index f5f5f651..e302d04b 100644 --- a/content/citation-tags.tsv +++ b/content/citation-tags.tsv @@ -193,6 +193,7 @@ nbc doi:10.1093/bioinformatics/btq619 Murdoch2017_automatic arxiv:1702.02540 Nazor2012 doi:10.1016/j.stem.2012.02.013 Nemati2016_rl doi:10.1109/EMBC.2016.7591355 +Ni2018 doi:10.1101/385849 Nguyen2014_adversarial arxiv:1412.1897v4 Ngiam2011 url:https://ai.stanford.edu/~ang/papers/icml11-MultimodalDeepLearning.pdf Nie2016_3d_survival doi:10.1007/978-3-319-46723-8_25