<!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="Joyce Hsiao" />
<title>Gene filtering</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-9.12.0/textmate.css" rel="stylesheet" />
<script src="site_libs/highlightjs-9.12.0/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) {
hljs.configure({languages: []});
hljs.initHighlightingOnLoad();
if (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">Gene filtering</h1>
<h4 class="author"><em>Joyce Hsiao</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> 2017-12-21</p>
<!-- Insert the code version (Git commit SHA1) if Git repository exists and R
package git2r is installed -->
<p><strong>Code version:</strong> 62c60ea</p>
<hr />
<div id="summary" class="section level2">
<h2>Summary</h2>
<p>I performed gene filtering based on the criterion set forth in our previous paper.</p>
<ol style="list-style-type: decimal">
<li>Remove mitochrodrial genes: filter out mitochrondrial genes verified and listed in <a href="https://www.broadinstitute.org/scientific-community/science/programs/metabolic-disease-program/publications/mitocarta/mitocarta-in-0">MitoCarta</a>.</li>
</ol>
<p><em>Results</em>:Found 1,150 genes previously quantified in <code>MitoCarta</code> inventory.</p>
<p><em>Output</em>: gene annotation saved in <code>../output/gene-filtering.Rmd/mito-genes-info.csv</code></p>
<p><span class="math inline">\(~\)</span></p>
<ol start="2" style="list-style-type: decimal">
<li>Remove outlier genes: molecule counts > 4,096 in any sample (x is the theoretical maximum of UMI count for 6-bp UMI)</li>
</ol>
<p><em>Results</em> There’s one, and turns out this over-expressed gene is one of the mitochrondrial genes.</p>
<p><em>Output</em>: gene annotation saved in <code>../output/gene-filtering.Rmd/over-expressed-genes-info.csv</code></p>
<p><span class="math inline">\(~\)</span></p>
<ol start="3" style="list-style-type: decimal">
<li>Remove lowly expressed genes: Lowly-expressed genes := gene mean < 2 CPM.</li>
</ol>
<p><em>Results</em>: * Of 20,421 genes, 7,864 genes are classifed as lowly-expressed. Of these, 34 are ERCC control genes and 7,830 are endogenoeus genes.</p>
<p><em>Output</em>: gene annotation saved in <code>../output/gene-filtering.Rmd/lowly-expressed-genes-info.csv</code></p>
<p><strong>Finally</strong>, filtered eset (<code>eset_filtered</code>) and cpm normalized count (<code>cpm_filtered</code>) are saved in <code>../output/gene-filtering.Rmd/eset-filterd.rdata</code>.</p>
<p><span class="math inline">\(~\)</span></p>
<hr />
</div>
<div id="import-data" class="section level2">
<h2>Import data</h2>
<p>Combine <code>eSet</code> objects.</p>
<pre class="r"><code>library(knitr)
library(Biobase)
#library(gdata)
library(testit)
library(cowplot)
library(biomaRt)
library(knitr)
library(data.table)
source("../code/pca.R")
eset <- readRDS("../output_tmp/eset.rds")</code></pre>
<p>Filter out low-quality single cell samples.</p>
<pre class="r"><code>pdata_filter <- pData(eset)[pData(eset)$filter_all == TRUE,]
count_filter <- exprs(eset[,pData(eset)$filter_all == TRUE])
dim(count_filter)</code></pre>
<pre><code>[1] 20421 1025</code></pre>
<p><span class="math inline">\(~\)</span></p>
<hr />
</div>
<div id="mitochrondrial-genes" class="section level2">
<h2>Mitochrondrial genes</h2>
<p>Found 1,150 genes previously quantified in <code>MitoCarta</code> inventory.</p>
<pre class="r"><code>human_mito <- gdata::read.xls("../data/Human.MitoCarta2.0.xls",
sheet = 2, header = TRUE, stringsAsFactors=FALSE)
human_mito_ensembl <- human_mito$EnsemblGeneID
which_mito <- which(rownames(count_filter) %in% human_mito_ensembl)
which_mito_genes <- rownames(count_filter)[which_mito]
length(which_mito)</code></pre>
<pre><code>[1] 1150</code></pre>
<p>Get mito gene info via <code>biomaRt</code>.</p>
<pre class="r"><code># do biomart to verfiy these genes
ensembl <- useMart(host = "grch37.ensembl.org",
biomart = "ENSEMBL_MART_ENSEMBL",
dataset = "hsapiens_gene_ensembl")
mito_genes_info <- getBM(
attributes = c("ensembl_gene_id", "chromosome_name",
"external_gene_name", "transcript_count",
"description"),
filters = "ensembl_gene_id",
values = which_mito_genes[grep("ENSG", which_mito_genes)],
mart = ensembl)
fwrite(mito_genes_info,
file = "../output/gene-filtering.Rmd/mito-genes-info.csv")</code></pre>
<p><span class="math inline">\(~\)</span></p>
<hr />
</div>
<div id="over-expressed-genes" class="section level2">
<h2>Over-expressed genes</h2>
<p>There’s one, and turns out this over-expressed gene is one of the mitochrondrial genes.</p>
<pre class="r"><code>which_over_expressed <- which(apply(count_filter, 1, function(x) any(x>(4^6)) ))
over_expressed_genes <- rownames(count_filter)[which_over_expressed]
over_expressed_genes %in% human_mito_ensembl</code></pre>
<pre><code>[1] TRUE</code></pre>
<pre class="r"><code>over_expressed_genes</code></pre>
<pre><code>[1] "ENSG00000198886"</code></pre>
<p>Get over-expressed gene info via <code>biomaRt</code>.</p>
<pre class="r"><code>over_expressed_genes_info <- getBM(
attributes = c("ensembl_gene_id", "chromosome_name",
"external_gene_name", "transcript_count",
"description"),
filters = "ensembl_gene_id",
values = over_expressed_genes,
mart = ensembl)
fwrite(over_expressed_genes_info,
file = "../output/gene-filtering.Rmd/over-expressed-genes-info.csv")</code></pre>
<p><span class="math inline">\(~\)</span></p>
<hr />
</div>
<div id="filter-out-lowly-expressed-genes" class="section level2">
<h2>Filter out lowly-expressed genes</h2>
<ul>
<li>Of 20,421 genes, 7,864 genes are classifed as lowly-expressed. Of these, 34 are ERCC control genes and 7,830 are endogenoeus genes.</li>
</ul>
<p>Compute CPM</p>
<pre class="r"><code>cpm <- t(t(count_filter)/colSums(count_filter))*(10^6)</code></pre>
<p>Lowly-expressed genes := gene mean < 2 CPM</p>
<pre class="r"><code>which_lowly_expressed <- which(rowMeans(cpm) < 2)
length(which_lowly_expressed)</code></pre>
<pre><code>[1] 7864</code></pre>
<pre class="r"><code>which_lowly_expressed_genes <- rownames(cpm)[which_lowly_expressed]
length(grep("ERCC", which_lowly_expressed_genes))</code></pre>
<pre><code>[1] 34</code></pre>
<pre class="r"><code>length(grep("ENSG", which_lowly_expressed_genes))</code></pre>
<pre><code>[1] 7830</code></pre>
<p>Get gene info via <code>biomaRt</code>.</p>
<pre class="r"><code>lowly_expressed_genes_info <- getBM(
attributes = c("ensembl_gene_id", "chromosome_name",
"external_gene_name", "transcript_count",
"description"),
filters = "ensembl_gene_id",
values = which_lowly_expressed_genes[grep("ENSG", which_lowly_expressed_genes)],
mart = ensembl)
fwrite(lowly_expressed_genes_info,
file = "../output/gene-filtering.Rmd/lowly-expressed-genes-info.csv")</code></pre>
<p><span class="math inline">\(~\)</span></p>
<hr />
</div>
<div id="combine-filters" class="section level2">
<h2>Combine filters</h2>
<p>Including 16,460 genes.</p>
<pre class="r"><code>gene_filter <- unique(c(which_lowly_expressed, which_mito, which_over_expressed))
genes_to_include <- setdiff(1:nrow(count_filter), gene_filter)
length(genes_to_include)</code></pre>
<pre><code>[1] 11489</code></pre>
<p><span class="math inline">\(~\)</span></p>
<hr />
</div>
<div id="make-filtered-data" class="section level2">
<h2>Make filtered data</h2>
<pre class="r"><code>cpm_filtered <- cpm[genes_to_include, ]
eset_filtered <- eset[genes_to_include, pData(eset)$filter_all==TRUE]
eset_filtered</code></pre>
<pre><code>ExpressionSet (storageMode: lockedEnvironment)
assayData: 11489 features, 1025 samples
element names: exprs
protocolData: none
phenoData
sampleNames: 20170905-A01 20170905-A02 ... 20170924-H12 (1025
total)
varLabels: experiment well ... filter_all (43 total)
varMetadata: labelDescription
featureData
featureNames: EGFP ENSG00000000003 ... mCherry (11489 total)
fvarLabels: chr start ... source (6 total)
fvarMetadata: labelDescription
experimentData: use 'experimentData(object)'
Annotation: </code></pre>
<pre class="r"><code>save(cpm_filtered, eset_filtered,
file = "../output/gene-filtering.Rmd/eset-filtered.rdata")</code></pre>
<p><span class="math inline">\(~\)</span></p>
<hr />
</div>
<div id="compute-log2-cpm" class="section level2">
<h2>Compute log2 CPM</h2>
<p>Import data post sample and gene filtering.</p>
<pre class="r"><code>load(file="../output/gene-filtering.Rmd/eset-filtered.rdata")</code></pre>
<p>Compute log2 CPM based on the library size before filtering.</p>
<pre class="r"><code>log2cpm <- log2(cpm_filtered+1)</code></pre>
<p><span class="math inline">\(~\)</span></p>
<hr />
</div>
<div id="pca" class="section level2">
<h2>PCA</h2>
<pre class="r"><code>pca_log2cpm <- run_pca(log2cpm)
pdata <- pData(eset_filtered)
pdata$experiment <- as.factor(pdata$experiment)
plot_grid(
plot_pca(x=pca_log2cpm$PCs, explained=pca_log2cpm$explained,
metadata=pdata, color="chip_id"),
plot_pca(x=pca_log2cpm$PCs, explained=pca_log2cpm$explained,
metadata=pdata, color="experiment"),
ncol=2)</code></pre>
<p><img src="figure/gene-filtering.Rmd/unnamed-chunk-15-1.png" width="672" style="display: block; margin: auto;" /></p>
<p><span class="math inline">\(~\)</span></p>
<hr />
</div>
<div id="session-information" class="section level2">
<h2>Session information</h2>
<pre><code>R version 3.4.1 (2017-06-30)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Scientific Linux 7.2 (Nitrogen)
Matrix products: default
BLAS: /home/joycehsiao/miniconda3/envs/fucci-seq/lib/R/lib/libRblas.so
LAPACK: /home/joycehsiao/miniconda3/envs/fucci-seq/lib/R/lib/libRlapack.so
locale:
[1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
[3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
[5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
[7] LC_PAPER=en_US.UTF-8 LC_NAME=C
[9] LC_ADDRESS=C LC_TELEPHONE=C
[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
attached base packages:
[1] parallel stats graphics grDevices utils datasets methods
[8] base
other attached packages:
[1] data.table_1.10.4 biomaRt_2.34.0 cowplot_0.8.0
[4] ggplot2_2.2.1 testit_0.7 Biobase_2.38.0
[7] BiocGenerics_0.24.0 knitr_1.17
loaded via a namespace (and not attached):
[1] Rcpp_0.12.14 compiler_3.4.1 git2r_0.19.0
[4] plyr_1.8.4 prettyunits_1.0.2 progress_1.1.2
[7] bitops_1.0-6 tools_3.4.1 digest_0.6.12
[10] bit_1.1-12 evaluate_0.10.1 RSQLite_2.0
[13] memoise_1.1.0 tibble_1.3.3 gtable_0.2.0
[16] rlang_0.1.4.9000 DBI_0.6-1 yaml_2.1.16
[19] stringr_1.2.0 gtools_3.5.0 IRanges_2.12.0
[22] S4Vectors_0.16.0 stats4_3.4.1 rprojroot_1.2
[25] bit64_0.9-5 grid_3.4.1 R6_2.2.2
[28] AnnotationDbi_1.40.0 XML_3.98-1.6 rmarkdown_1.8
[31] gdata_2.18.0 blob_1.1.0 magrittr_1.5
[34] backports_1.0.5 scales_0.4.1 htmltools_0.3.6
[37] assertthat_0.2.0 colorspace_1.3-2 labeling_0.3
[40] stringi_1.1.2 RCurl_1.95-4.8 lazyeval_0.2.0
[43] munsell_0.4.3 </code></pre>
</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>