<!DOCTYPE html> <html xmlns="http://www.w3.org/1999/xhtml"> <head> <meta charset="utf-8" /> <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> <meta name="generator" content="pandoc" /> <meta name="author" content="Po-Yuan Tung" /> <meta name="date" content="2018-01-31" /> <title>PCA vs Technical Variables</title> <script src="site_libs/jquery-1.11.3/jquery.min.js"></script> <meta name="viewport" content="width=device-width, initial-scale=1" /> <link href="site_libs/bootstrap-3.3.5/css/cosmo.min.css" rel="stylesheet" /> <script src="site_libs/bootstrap-3.3.5/js/bootstrap.min.js"></script> <script src="site_libs/bootstrap-3.3.5/shim/html5shiv.min.js"></script> <script src="site_libs/bootstrap-3.3.5/shim/respond.min.js"></script> <script src="site_libs/jqueryui-1.11.4/jquery-ui.min.js"></script> <link href="site_libs/tocify-1.9.1/jquery.tocify.css" rel="stylesheet" /> <script src="site_libs/tocify-1.9.1/jquery.tocify.js"></script> <script src="site_libs/navigation-1.1/tabsets.js"></script> <link href="site_libs/highlightjs-1.1/textmate.css" rel="stylesheet" /> <script src="site_libs/highlightjs-1.1/highlight.js"></script> <link href="site_libs/font-awesome-4.5.0/css/font-awesome.min.css" rel="stylesheet" /> <style type="text/css">code{white-space: pre;}</style> <style type="text/css"> pre:not([class]) { background-color: white; } </style> <script type="text/javascript"> if (window.hljs && document.readyState && document.readyState === "complete") { window.setTimeout(function() { hljs.initHighlighting(); }, 0); } </script> <style type="text/css"> h1 { font-size: 34px; } h1.title { font-size: 38px; } h2 { font-size: 30px; } h3 { font-size: 24px; } h4 { font-size: 18px; } h5 { font-size: 16px; } h6 { font-size: 12px; } .table th:not([align]) { text-align: left; } </style> </head> <body> <style type = "text/css"> .main-container { max-width: 940px; margin-left: auto; margin-right: auto; } code { color: inherit; background-color: rgba(0, 0, 0, 0.04); } img { max-width:100%; height: auto; } .tabbed-pane { padding-top: 12px; } button.code-folding-btn:focus { outline: none; } </style> <style type="text/css"> /* padding for bootstrap navbar */ body { padding-top: 51px; padding-bottom: 40px; } /* offset scroll position for anchor links (for fixed navbar) */ .section h1 { padding-top: 56px; margin-top: -56px; } .section h2 { padding-top: 56px; margin-top: -56px; } .section h3 { padding-top: 56px; margin-top: -56px; } .section h4 { padding-top: 56px; margin-top: -56px; } .section h5 { padding-top: 56px; margin-top: -56px; } .section h6 { padding-top: 56px; margin-top: -56px; } </style> <script> // manage active state of menu based on current page $(document).ready(function () { // active menu anchor href = window.location.pathname href = href.substr(href.lastIndexOf('/') + 1) if (href === "") href = "index.html"; var menuAnchor = $('a[href="' + href + '"]'); // mark it active menuAnchor.parent().addClass('active'); // if it's got a parent navbar menu mark it active as well menuAnchor.closest('li.dropdown').addClass('active'); }); </script> <div class="container-fluid main-container"> <!-- tabsets --> <script> $(document).ready(function () { window.buildTabsets("TOC"); }); </script> <!-- code folding --> <script> $(document).ready(function () { // move toc-ignore selectors from section div to header $('div.section.toc-ignore') .removeClass('toc-ignore') .children('h1,h2,h3,h4,h5').addClass('toc-ignore'); // establish options var options = { selectors: "h1,h2,h3", theme: "bootstrap3", context: '.toc-content', hashGenerator: function (text) { return text.replace(/[.\\/?&!#<>]/g, '').replace(/\s/g, '_').toLowerCase(); }, ignoreSelector: ".toc-ignore", scrollTo: 0 }; options.showAndHide = true; options.smoothScroll = true; // tocify var toc = $("#TOC").tocify(options).data("toc-tocify"); }); </script> <style type="text/css"> #TOC { margin: 25px 0px 20px 0px; } @media (max-width: 768px) { #TOC { position: relative; width: 100%; } } .toc-content { padding-left: 30px; padding-right: 40px; } div.main-container { max-width: 1200px; } div.tocify { width: 20%; max-width: 260px; max-height: 85%; } @media (min-width: 768px) and (max-width: 991px) { div.tocify { width: 25%; } } @media (max-width: 767px) { div.tocify { width: 100%; max-width: none; } } .tocify ul, .tocify li { line-height: 20px; } .tocify-subheader .tocify-item { font-size: 0.90em; padding-left: 25px; text-indent: 0; } .tocify .list-group-item { border-radius: 0px; } </style> <!-- setup 3col/9col grid for toc_float and main content --> <div class="row-fluid"> <div class="col-xs-12 col-sm-4 col-md-3"> <div id="TOC" class="tocify"> </div> </div> <div class="toc-content col-xs-12 col-sm-8 col-md-9"> <div class="navbar navbar-default navbar-fixed-top" role="navigation"> <div class="container"> <div class="navbar-header"> <button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#navbar"> <span class="icon-bar"></span> <span class="icon-bar"></span> <span class="icon-bar"></span> </button> <a class="navbar-brand" href="index.html">fucci-seq</a> </div> <div id="navbar" class="navbar-collapse collapse"> <ul class="nav navbar-nav"> <li> <a href="index.html">Home</a> </li> <li> <a href="about.html">About</a> </li> <li> <a href="license.html">License</a> </li> </ul> <ul class="nav navbar-nav navbar-right"> <li> <a href="https://github.com/jdblischak/fucci-seq"> <span class="fa fa-github"></span> </a> </li> </ul> </div><!--/.nav-collapse --> </div><!--/.container --> </div><!--/.navbar --> <!-- Add a small amount of space between sections. --> <style type="text/css"> div.section { padding-top: 12px; } </style> <div class="fluid-row" id="header"> <h1 class="title toc-ignore">PCA vs Technical Variables</h1> <h4 class="author"><em>Po-Yuan Tung</em></h4> <h4 class="date"><em>2018-01-31</em></h4> </div> <!-- The file analysis/chunks.R contains chunks that define default settings shared across the workflowr files. --> <!-- Update knitr chunk options --> <!-- Insert the date the file was last updated --> <p><strong>Last updated:</strong> 2018-05-18</p> <!-- Insert the code version (Git commit SHA1) if Git repository exists and R package git2r is installed --> <p><strong>Code version:</strong> f053912</p> <hr /> <div id="setup" class="section level2"> <h2>Setup</h2> <pre class="r"><code>library("cowplot") library("dplyr") library("edgeR") library("ggplot2") library("heatmap3") library("reshape2") library("Biobase") source("../code/utility.R")</code></pre> </div> <div id="pca" class="section level2"> <h2>PCA</h2> <div id="before-fileter" class="section level3"> <h3>Before fileter</h3> <pre class="r"><code>fname <- Sys.glob("../data/eset/*.rds") eset <- Reduce(combine, Map(readRDS, fname)) ## look at human genes eset_hs <- eset[fData(eset)$source == "H. sapiens", ] head(featureNames(eset_hs))</code></pre> <pre><code>[1] "ENSG00000000003" "ENSG00000000005" "ENSG00000000419" "ENSG00000000457" [5] "ENSG00000000460" "ENSG00000000938"</code></pre> <pre class="r"><code>## remove genes of all 0s eset_hs_clean <- eset_hs[rowSums(exprs(eset_hs)) != 0, ] dim(eset_hs_clean)</code></pre> <pre><code>Features Samples 19348 1536 </code></pre> <pre class="r"><code>## convert to log2 cpm mol_hs_cpm <- cpm(exprs(eset_hs_clean), log = TRUE) mol_hs_cpm_means <- rowMeans(mol_hs_cpm) summary(mol_hs_cpm_means)</code></pre> <pre><code> Min. 1st Qu. Median Mean 3rd Qu. Max. 2.413 2.482 3.180 3.858 4.761 12.999 </code></pre> <pre class="r"><code>## keep genes with reasonable expression levels mol_hs_cpm <- mol_hs_cpm[mol_hs_cpm_means > median(mol_hs_cpm_means), ] dim(mol_hs_cpm)</code></pre> <pre><code>[1] 9674 1536</code></pre> <pre class="r"><code>## pca of genes with reasonable expression levels pca_hs <- run_pca(mol_hs_cpm) ## a function of pca vs technical factors get_r2 <- function(x, y) { stopifnot(length(x) == length(y)) model <- lm(y ~ x) stats <- summary(model) return(stats$adj.r.squared) } ## selection of technical factor covariates <- pData(eset) %>% dplyr::select(experiment, well, concentration, raw:unmapped, starts_with("detect"), chip_id, molecules) ## look at the first 6 PCs pcs <- pca_hs$PCs[, 1:6] ## generate the data r2_before <- matrix(NA, nrow = ncol(covariates), ncol = ncol(pcs), dimnames = list(colnames(covariates), colnames(pcs))) for (cov in colnames(covariates)) { for (pc in colnames(pcs)) { r2_before[cov, pc] <- get_r2(covariates[, cov], pcs[, pc]) } } ## plot heatmap3(r2_before, cexRow=1, cexCol=1, margins=c(8,8), ylab="technical factor", main = "Before filter")</code></pre> <p><img src="figure/pca-tf.Rmd/before-filter-1.png" width="672" style="display: block; margin: auto;" /></p> <pre class="r"><code>heatmap3(r2_before, cexRow=1, cexCol=1, margins=c(8,8), scale = "none", ylab="technical factor", main = "Before filter w/o scale")</code></pre> <p><img src="figure/pca-tf.Rmd/before-filter-2.png" width="672" style="display: block; margin: auto;" /></p> <pre class="r"><code>plot_pca(pca_hs$PCs, pcx = 1, pcy = 2, explained = pca_hs$explained, metadata = pData(eset_hs), color="chip_id")</code></pre> <p><img src="figure/pca-tf.Rmd/before-filter-3.png" width="672" style="display: block; margin: auto;" /></p> </div> <div id="after-filter" class="section level3"> <h3>After filter</h3> <p>Import data post <a href="gene-filtering.Rmd">sample and gene filtering</a></p> <pre class="r"><code>eset_filter <- readRDS("../data/eset-filtered.rds")</code></pre> <p>Compute log2 CPM based on the library size before filtering.</p> <pre class="r"><code>log2cpm <- cpm(exprs(eset_filter), log = TRUE) dim(log2cpm)</code></pre> <pre><code>[1] 11093 923</code></pre> <pre class="r"><code>pca_log2cpm <- run_pca(log2cpm) pdata <- pData(eset_filter) pdata$experiment <- as.factor(pdata$experiment) plot_pca(x=pca_log2cpm$PCs, explained=pca_log2cpm$explained, metadata=pdata, color="chip_id")</code></pre> <p><img src="figure/pca-tf.Rmd/after-filter-1.png" width="672" style="display: block; margin: auto;" /></p> <pre class="r"><code>plot_pca(x=pca_log2cpm$PCs, explained=pca_log2cpm$explained, metadata=pdata, color="experiment")</code></pre> <p><img src="figure/pca-tf.Rmd/after-filter-2.png" width="672" style="display: block; margin: auto;" /></p> <pre class="r"><code>## selection of technical factor covariates <- pData(eset_filter) %>% dplyr::select(experiment, well, chip_id, concentration, raw:unmapped, starts_with("detect"), molecules) ## look at the first 6 PCs pcs <- pca_log2cpm$PCs[, 1:6] ## generate the data r2 <- matrix(NA, nrow = ncol(covariates), ncol = ncol(pcs), dimnames = list(colnames(covariates), colnames(pcs))) for (cov in colnames(covariates)) { for (pc in colnames(pcs)) { r2[cov, pc] <- get_r2(covariates[, cov], pcs[, pc]) } } ## plot heatmap heatmap3(r2, cexRow=1, cexCol=1, margins=c(8,8), ylab="technical factor", main = "After filter")</code></pre> <p><img src="figure/pca-tf.Rmd/after-filter-tf-1.png" width="672" style="display: block; margin: auto;" /></p> <pre class="r"><code>heatmap3(r2, cexRow=1, cexCol=1, margins=c(8,8), scale = "none", ylab="technical factor", main = "After filter w/o scale")</code></pre> <p><img src="figure/pca-tf.Rmd/after-filter-tf-2.png" width="672" style="display: block; margin: auto;" /></p> <p>PC1 correlated with number of genes detected, which is described in <a href="https://academic.oup.com/biostatistics/advance-article/doi/10.1093/biostatistics/kxx053/4599254">Hicks et al 2017</a></p> <p>Number of genes detected also highly correlated with sequencing metrics, especially total molecule number per sample.</p> <pre class="r"><code>cor_tech <- cor(as.matrix(covariates[,4:11]),use="pairwise.complete.obs") heatmap(cor_tech, symm = TRUE)</code></pre> <p><img src="figure/pca-tf.Rmd/cor-1.png" width="672" style="display: block; margin: auto;" /></p> <p>Look at the top 10% expression genes to see if the correlation of PC1 and number of detected gene would go away. However, the PC1 is still not individual (chip_id).</p> <pre class="r"><code>## look at top 10% of genes log2cpm_mean <- rowMeans(log2cpm) summary(log2cpm_mean)</code></pre> <pre><code> Min. 1st Qu. Median Mean 3rd Qu. Max. 2.447 3.482 4.505 4.865 5.882 13.434 </code></pre> <pre class="r"><code>log2cpm_top <- log2cpm[rank(log2cpm_mean) / length(log2cpm_mean) > 1 - 0.1, ] dim(log2cpm_top)</code></pre> <pre><code>[1] 1110 923</code></pre> <pre class="r"><code>pca_top <- run_pca(log2cpm_top) ## look at the first 6 PCs pcs <- pca_top$PCs[, 1:6] ## generate the data r2_top <- matrix(NA, nrow = ncol(covariates), ncol = ncol(pcs), dimnames = list(colnames(covariates), colnames(pcs))) for (cov in colnames(covariates)) { for (pc in colnames(pcs)) { r2_top[cov, pc] <- get_r2(covariates[, cov], pcs[, pc]) } } ## plot heatmap heatmap3(r2_top, cexRow=1, cexCol=1, margins=c(8,8), ylab="technical factor", main = "Top 10 % gene")</code></pre> <p><img src="figure/pca-tf.Rmd/top-1.png" width="672" style="display: block; margin: auto;" /></p> <pre class="r"><code>heatmap3(r2_top, cexRow=1, cexCol=1, margins=c(8,8), scale = "none", ylab="technical factor", main = "Top 10 % gene w/o scale")</code></pre> <p><img src="figure/pca-tf.Rmd/top-2.png" width="672" style="display: block; margin: auto;" /></p> </div> </div> <!-- Adjust MathJax settings so that all math formulae are shown using TeX fonts only; see http://docs.mathjax.org/en/latest/configuration.html. This will make the presentation more consistent at the cost of the webpage sometimes taking slightly longer to load. Note that this only works because the footer is added to webpages before the MathJax javascript. --> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <hr> <p> This <a href="http://rmarkdown.rstudio.com">R Markdown</a> site was created with <a href="https://github.com/jdblischak/workflowr">workflowr</a> </p> <hr> <!-- To enable disqus, uncomment the section below and provide your disqus_shortname --> <!-- disqus <div id="disqus_thread"></div> <script type="text/javascript"> /* * * CONFIGURATION VARIABLES: EDIT BEFORE PASTING INTO YOUR WEBPAGE * * */ var disqus_shortname = 'rmarkdown'; // required: replace example with your forum shortname /* * * DON'T EDIT BELOW THIS LINE * * */ (function() { var dsq = document.createElement('script'); dsq.type = 'text/javascript'; dsq.async = true; dsq.src = '//' + disqus_shortname + '.disqus.com/embed.js'; (document.getElementsByTagName('head')[0] || document.getElementsByTagName('body')[0]).appendChild(dsq); })(); </script> <noscript>Please enable JavaScript to view the <a href="http://disqus.com/?ref_noscript">comments powered by Disqus.</a></noscript> <a href="http://disqus.com" class="dsq-brlink">comments powered by <span class="logo-disqus">Disqus</span></a> --> </div> </div> </div> <script> // add bootstrap table styles to pandoc tables function bootstrapStylePandocTables() { $('tr.header').parent('thead').parent('table').addClass('table table-condensed'); } $(document).ready(function () { bootstrapStylePandocTables(); }); </script> <!-- dynamically load mathjax for compatibility with self-contained --> <script> (function () { var script = document.createElement("script"); script.type = "text/javascript"; script.src = "https://mathjax.rstudio.com/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"; document.getElementsByTagName("head")[0].appendChild(script); })(); </script> </body> </html>