<!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="Briana Mittleman" />
<title>Total and Nuclear fraction RNA seq</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/journal.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">Three Prime Sequencing in Human LCLs</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/brimittleman/threeprimeseq">
<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">Total and Nuclear fraction RNA seq</h1>
<h4 class="author"><em>Briana Mittleman</em></h4>
<h4 class="date"><em>5/8/2018</em></h4>
</div>
<p><strong>Last updated:</strong> 2018-05-09</p>
<strong>workflowr checks:</strong> <small>(Click a bullet for more information)</small>
<ul>
<li>
<p><details> <summary> <strong style="color:blue;">✔</strong> <strong>R Markdown file:</strong> up-to-date </summary></p>
<p>Great! Since the R Markdown file has been committed to the Git repository, you know the exact version of the code that produced these results.</p>
</details>
</li>
<li>
<p><details> <summary> <strong style="color:blue;">✔</strong> <strong>Environment:</strong> empty </summary></p>
<p>Great job! The global environment was empty. Objects defined in the global environment can affect the analysis in your R Markdown file in unknown ways. For reproduciblity it’s best to always run the code in an empty environment.</p>
</details>
</li>
<li>
<p><details> <summary> <strong style="color:blue;">✔</strong> <strong>Seed:</strong> <code>set.seed(12345)</code> </summary></p>
<p>The command <code>set.seed(12345)</code> was run prior to running the code in the R Markdown file. Setting a seed ensures that any results that rely on randomness, e.g. subsampling or permutations, are reproducible.</p>
</details>
</li>
<li>
<p><details> <summary> <strong style="color:blue;">✔</strong> <strong>Session information:</strong> recorded </summary></p>
<p>Great job! Recording the operating system, R version, and package versions is critical for reproducibility.</p>
</details>
</li>
<li>
<p><details> <summary> <strong style="color:blue;">✔</strong> <strong>Repository version:</strong> <a href="https://github.com/brimittleman/threeprimeseq/tree/f8ce0fcfc549967f30ad08e19962c8135bb5dc27" target="_blank">f8ce0fc</a> </summary></p>
Great! You are using Git for version control. Tracking code development and connecting the code version to the results is critical for reproducibility. The version displayed above was the version of the Git repository at the time these results were generated. <br><br> Note that you need to be careful to ensure that all relevant files for the analysis have been committed to Git prior to generating the results (you can use <code>wflow_publish</code> or <code>wflow_git_commit</code>). workflowr only checks the R Markdown file, but you know if there are other scripts or data files that it depends on. Below is the status of the Git repository when the results were generated:
<pre><code>
Ignored files:
Ignored: .Rhistory
Ignored: .Rproj.user/
Ignored: docs/figure/
</code></pre>
Note that any generated files, e.g. HTML, png, CSS, etc., are not included in this status report because it is ok for generated content to have uncommitted changes. </details>
</li>
</ul>
<details> <summary> <small><strong>Expand here to see past versions:</strong></small> </summary>
<ul>
<table style="border-collapse:separate; border-spacing:5px;">
<thead>
<tr>
<th style="text-align:left;">
File
</th>
<th style="text-align:left;">
Version
</th>
<th style="text-align:left;">
Author
</th>
<th style="text-align:left;">
Date
</th>
<th style="text-align:left;">
Message
</th>
</tr>
</thead>
<tbody>
<tr>
<td style="text-align:left;">
Rmd
</td>
<td style="text-align:left;">
<a href="https://github.com/brimittleman/threeprimeseq/blob/f8ce0fcfc549967f30ad08e19962c8135bb5dc27/analysis/total.nuc.rnaseq.Rmd" target="_blank">f8ce0fc</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-05-09
</td>
<td style="text-align:left;">
Update to 1.0
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/f8ce0fcfc549967f30ad08e19962c8135bb5dc27/docs/total.nuc.rnaseq.html" target="_blank">f8ce0fc</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-05-09
</td>
<td style="text-align:left;">
Update to 1.0
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/7c5705dc5fce4a7f0f59c92254256453d72d7bfa/docs/total.nuc.rnaseq.html" target="_blank">7c5705d</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-05-09
</td>
<td style="text-align:left;">
Build site.
</td>
</tr>
<tr>
<td style="text-align:left;">
Rmd
</td>
<td style="text-align:left;">
<a href="https://github.com/brimittleman/threeprimeseq/blob/7a9e443b7a894452fd4b4db43ce09c23a3674144/analysis/total.nuc.rnaseq.Rmd" target="_blank">7a9e443</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-05-09
</td>
<td style="text-align:left;">
fix sample switch
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/ec089e50f7dfbac42616eb9e9899d97a24320a86/docs/total.nuc.rnaseq.html" target="_blank">ec089e5</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-05-09
</td>
<td style="text-align:left;">
Build site.
</td>
</tr>
<tr>
<td style="text-align:left;">
Rmd
</td>
<td style="text-align:left;">
<a href="https://github.com/brimittleman/threeprimeseq/blob/ca8eb3aaa448b4336f8a355f687e2a81c83cd5f3/analysis/total.nuc.rnaseq.Rmd" target="_blank">ca8eb3a</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-05-09
</td>
<td style="text-align:left;">
add dist. gene body plot
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/076baa0d108f22cfac6c24eafa23e47845ee0c7b/docs/total.nuc.rnaseq.html" target="_blank">076baa0</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-05-08
</td>
<td style="text-align:left;">
Build site.
</td>
</tr>
<tr>
<td style="text-align:left;">
Rmd
</td>
<td style="text-align:left;">
<a href="https://github.com/brimittleman/threeprimeseq/blob/8f6c959712b542890ddf5e143a9cb22f07692ffd/analysis/total.nuc.rnaseq.Rmd" target="_blank">8f6c959</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-05-08
</td>
<td style="text-align:left;">
add count boxplots
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/95a41f993eddeb728c847a147df217e1d59ad410/docs/total.nuc.rnaseq.html" target="_blank">95a41f9</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-05-08
</td>
<td style="text-align:left;">
Build site.
</td>
</tr>
<tr>
<td style="text-align:left;">
Rmd
</td>
<td style="text-align:left;">
<a href="https://github.com/brimittleman/threeprimeseq/blob/1f9e243afd0155091411a276a3ca8e5b76d4e672/analysis/total.nuc.rnaseq.Rmd" target="_blank">1f9e243</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-05-08
</td>
<td style="text-align:left;">
fix typo
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/394259e0e190633005c3c395286bd3a8b78b19bf/docs/total.nuc.rnaseq.html" target="_blank">394259e</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-05-08
</td>
<td style="text-align:left;">
Build site.
</td>
</tr>
<tr>
<td style="text-align:left;">
Rmd
</td>
<td style="text-align:left;">
<a href="https://github.com/brimittleman/threeprimeseq/blob/6b7d92137c81918942d73ef10435d319a51264c5/analysis/total.nuc.rnaseq.Rmd" target="_blank">6b7d921</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-05-08
</td>
<td style="text-align:left;">
correlation heatplot
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/3f23e0e8a27b875de7bd967922ca961293da2f71/docs/total.nuc.rnaseq.html" target="_blank">3f23e0e</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-05-08
</td>
<td style="text-align:left;">
Build site.
</td>
</tr>
<tr>
<td style="text-align:left;">
Rmd
</td>
<td style="text-align:left;">
<a href="https://github.com/brimittleman/threeprimeseq/blob/c5535649cef9bea5bd5d8bbfb85bb97dce4a801a/analysis/total.nuc.rnaseq.Rmd" target="_blank">c553564</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-05-08
</td>
<td style="text-align:left;">
low level analysis for RNA seq
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/3dd80ef12a6e2e8ba83dc7987ec22d667d4b7492/docs/total.nuc.rnaseq.html" target="_blank">3dd80ef</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-05-08
</td>
<td style="text-align:left;">
Build site.
</td>
</tr>
<tr>
<td style="text-align:left;">
Rmd
</td>
<td style="text-align:left;">
<a href="https://github.com/brimittleman/threeprimeseq/blob/519447d91969a0dc7db57d52cc61ecd71a9c53ab/analysis/total.nuc.rnaseq.Rmd" target="_blank">519447d</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-05-08
</td>
<td style="text-align:left;">
Add total.nuc.rnaseq analysis
</td>
</tr>
</tbody>
</table>
</ul>
<p></details></p>
<hr />
<p>I will use this analysis to look at general QC measurements for the RNA seq on the total and nuclear fraction with respect to my three-prime-seq snakemake pipeline.</p>
<p>There are 2 lines with files for chromatin, nuclear and cytoplasmic. There is a sample switch in this anaylsis chrom.2.S3 and Cyt.2.S1 are switched. We know this from a heatmap analysis.</p>
<div id="library" class="section level3">
<h3>Library</h3>
<pre class="r"><code>library(ggplot2)
library(dplyr)</code></pre>
<pre><code>
Attaching package: 'dplyr'</code></pre>
<pre><code>The following objects are masked from 'package:stats':
filter, lag</code></pre>
<pre><code>The following objects are masked from 'package:base':
intersect, setdiff, setequal, union</code></pre>
<pre class="r"><code>library(edgeR)</code></pre>
<pre><code>Warning: package 'edgeR' was built under R version 3.4.3</code></pre>
<pre><code>Loading required package: limma</code></pre>
<pre><code>Warning: package 'limma' was built under R version 3.4.3</code></pre>
<pre class="r"><code>library(workflowr)</code></pre>
<pre><code>Loading required package: rmarkdown</code></pre>
<pre><code>This is workflowr version 1.0.1
Run ?workflowr for help getting started</code></pre>
<pre class="r"><code>library(reshape2)</code></pre>
<pre><code>Warning: package 'reshape2' was built under R version 3.4.3</code></pre>
</div>
<div id="mapped-reads" class="section level3">
<h3>Mapped reads</h3>
<p>First I want to look at the number of reads that map. I will flip the sample swap for this analysis so it it correct.</p>
<pre class="r"><code>#wc -l file / 4
read_chrom1=74784589
read_chrom2= 56100500
read_nuc1= 73481177
read_nuc2= 60386733
read_cyt1= 63641411
read_cyt2= 61957677</code></pre>
<p>Now look at how many reads mapped:</p>
<pre class="r"><code>#samtools view -c -F 4 file
map_chrom1=67829422
map_chrom2=49619272
map_nuc1= 65023318
map_nuc2= 53445556
map_cyt1=53856948
map_cyt2=52630632</code></pre>
<p>Percent mapped per line:</p>
<pre class="r"><code>perc_map_chrom1= map_chrom1/read_chrom1 *100
perc_map_chrom2=map_chrom2/read_chrom2 * 100
perc_map_nuc1=map_nuc1/read_nuc1 * 100
perc_map_nuc2= map_nuc2/read_nuc2 * 100
perc_map_cyt1=map_cyt1/read_cyt1 * 100
perc_map_cyt2=map_cyt2/read_cyt2 * 100</code></pre>
<p>Put this information in a dataframe to plot it:</p>
<pre class="r"><code>percmap=c(perc_map_chrom1,perc_map_chrom2,perc_map_nuc1,perc_map_nuc2,perc_map_cyt1, perc_map_cyt2)
fraction=c("chrom", "chrom", "nuc", "nuc", "cyt", "cyt")
sample=c("chrom1", "chrom2", "nuc1", "nuc2", "cyt1", "cyt2")
percmap_df=as.data.frame(cbind(sample,fraction, percmap), stringsAsFactors = F)
percmap_df$percmap= as.numeric(percmap_df$percmap)
ggplot(percmap_df, aes(y=percmap, x=sample, fill=fraction)) + geom_col() + scale_y_continuous(limits=c(0,100)) + labs(y="Percent mapped", title="Percent of reads mapped")</code></pre>
<p><img src="figure/total.nuc.rnaseq.Rmd/percmap%20df-1.png" width="672" style="display: block; margin: auto;" /> This shows that mapping is a little bit higher for the cytoplasmic and nuclear fractions than for the chromatin fraction.</p>
</div>
<div id="gene-count-analysis" class="section level3">
<h3>Gene count analysis:</h3>
<p>Import gene count data. I will fix the sample switch at this point.</p>
<pre class="r"><code>cov_chrom1=read.table("../data/total.nuc.cyt.genecounts/gene_covYG-SP20-Chrom-1_S3_L005_R1_001-genecov.txt", stringsAsFactors = FALSE)
names(cov_chrom1)=c("chr", "start", "end", "gene", "score", "strand", "count" )
cov_chrom2=read.table("../data/total.nuc.cyt.genecounts/gene_covYG-SP20-Cyt-2_S4_L005_R1_001-genecov.txt", stringsAsFactors = FALSE)
names(cov_chrom2)=c("chr", "start", "end", "gene", "score", "strand", "count" )
cov_nuc1=read.table("../data/total.nuc.cyt.genecounts/gene_covYG-SP20-Nuc-1_S2_L005_R1_001-genecov.txt", stringsAsFactors = FALSE)
names(cov_nuc1)=c("chr", "start", "end", "gene", "score", "strand", "count" )
cov_nuc2=read.table("../data/total.nuc.cyt.genecounts/gene_covYG-SP20-Nuc-2_S5_L005_R1_001-genecov.txt", stringsAsFactors = FALSE)
names(cov_nuc2)=c("chr", "start", "end", "gene", "score", "strand", "count" )
cov_cyt1= read.table("../data/total.nuc.cyt.genecounts/gene_covYG-SP20-Cyt-1_S1_L005_R1_001-genecov.txt", stringsAsFactors = FALSE)
names(cov_cyt1)=c("chr", "start", "end", "gene", "score", "strand", "count" )
cov_cyt2=read.table("../data/total.nuc.cyt.genecounts/gene_covYG-SP20-Chrom-2_S6_L005_R1_001-genecov.txt", stringsAsFactors = FALSE)
names(cov_cyt2)=c("chr", "start", "end", "gene", "score", "strand", "count" )</code></pre>
<p>Look at the distribution of the gene counts. To do this I need to make a matrix with gene by sample to give the cpm command.</p>
<pre class="r"><code>count_matrix=cbind(cov_chrom1$count, cov_chrom2$count, cov_nuc1$count, cov_nuc2$count, cov_cyt1$count, cov_cyt2$count)
gene_length=cov_chrom1 %>% mutate(genelength=end-start) %>% select(genelength)
gene_length_vec=as.vector(gene_length$genelength)
count_matrix_cpm=cpm(count_matrix, log=T, gene.length=gene_length_vec )</code></pre>
<p>Plot the distribution of the log cpm counts.</p>
<pre class="r"><code>plotDensities(count_matrix_cpm, legend = "bottomright", main="Pre-filtering")
abline(v = 0, lty = 3)</code></pre>
<p><img src="figure/total.nuc.rnaseq.Rmd/plotdensity-1.png" width="672" style="display: block; margin: auto;" /></p>
<p>I will only keep genes that have a log cpm greater than 1 in at least 3 samples.</p>
<pre class="r"><code>keep.exprs=rowSums(count_matrix_cpm>1) >=3
count_matrix_cpm_filt= count_matrix_cpm[keep.exprs,]
plotDensities(count_matrix_cpm_filt, legend = "bottomright", main="Post-filtering")</code></pre>
<p><img src="figure/total.nuc.rnaseq.Rmd/filt-1.png" width="672" style="display: block; margin: auto;" /></p>
<p>Create boxplots:</p>
<pre class="r"><code>#pre standardization
colnames(count_matrix)=sample
boxplot(count_matrix, main="Raw Counts by library")</code></pre>
<p><img src="figure/total.nuc.rnaseq.Rmd/unnamed-chunk-2-1.png" width="672" style="display: block; margin: auto;" /></p>
<pre class="r"><code>#prefilt
colnames(count_matrix_cpm)=sample
boxplot(count_matrix_cpm, main="Log CPM Counts by library prefilter")</code></pre>
<p><img src="figure/total.nuc.rnaseq.Rmd/unnamed-chunk-2-2.png" width="672" style="display: block; margin: auto;" /></p>
<pre class="r"><code>#filtered
colnames(count_matrix_cpm_filt)=sample
boxplot(count_matrix_cpm_filt, las=2,main="Log CPM Counts by library filtered")</code></pre>
<p><img src="figure/total.nuc.rnaseq.Rmd/unnamed-chunk-2-3.png" width="672" style="display: block; margin: auto;" /> This shows that we do not need to do any extreme normalization. I will skip it for this initial analysis.</p>
<p>Now I can look at the number of genes detected in each sample according to this filtering practice. I will use >1 log cpm for “detected”.</p>
<pre class="r"><code>detected_chrom1=sum(count_matrix_cpm_filt[,1] > 1)
detected_chrom2=sum(count_matrix_cpm_filt[,2] > 1)
detected_nuc1=sum(count_matrix_cpm_filt[,3] > 1)
detected_nuc2=sum(count_matrix_cpm_filt[,4] > 1)
detected_cyt1=sum(count_matrix_cpm_filt[,5] > 1)
detected_cyt2=sum(count_matrix_cpm_filt[,6] > 1)</code></pre>
<p>Plot these values like the percent mapped.</p>
<pre class="r"><code>detected_vec=c(detected_chrom1, detected_chrom2, detected_nuc1, detected_nuc2, detected_cyt1, detected_cyt2)
det_df=as.data.frame(cbind(sample,fraction, detected_vec), stringsAsFactors = F)
det_df$detected_vec= as.numeric(det_df$detected_vec)
ggplot(det_df, aes(y=detected_vec, x=sample, fill=fraction)) + geom_col() + labs(x="Sample", y="Number of detected genes", title="Number Detected genes >1 log-cpm") + scale_y_continuous(limits=c(0,20345))</code></pre>
<p><img src="figure/total.nuc.rnaseq.Rmd/unnamed-chunk-3-1.png" width="672" style="display: block; margin: auto;" /></p>
<pre class="r"><code>total_genes=20345
det_df_prop= det_df %>% mutate(prop_det=detected_vec/total_genes)
ggplot(det_df_prop, aes(y=prop_det, x=sample, fill=fraction)) + geom_col() + labs(x="Sample", y="Proportion detected genes", title="Proportion Detected Genes >1 log-cpm") + scale_y_continuous(limits=c(0,1))</code></pre>
<p><img src="figure/total.nuc.rnaseq.Rmd/unnamed-chunk-3-2.png" width="672" style="display: block; margin: auto;" /></p>
</div>
<div id="cluster-analysis" class="section level3">
<h3>Cluster analysis</h3>
<p>Create a correlation matrix between the counts.</p>
<pre class="r"><code>cor_function=function(data){
corr_matrix= matrix(0,ncol(data),ncol(data))
for (i in seq(1,ncol(data))){
for (j in seq(1,ncol(data))){
x=cor.test(data[,i], data[,j], method='pearson')
cor_ij=as.numeric(x$estimate)
corr_matrix[i,j]=cor_ij
}
}
return(corr_matrix)
}
count_cor=cor_function(count_matrix_cpm_filt)
rownames(count_cor)=sample
colnames(count_cor)=sample</code></pre>
<p>Reshape correlation matrix and plot it.</p>
<pre class="r"><code>melted_count_corr=melt(count_cor)
ggheatmap=ggplot(data = melted_count_corr, aes(x=Var1, y=Var2, fill=value)) +
geom_tile() +
labs(title="Correlation Heatplot")
ggheatmap</code></pre>
<p><img src="figure/total.nuc.rnaseq.Rmd/unnamed-chunk-5-1.png" width="672" style="display: block; margin: auto;" /></p>
<p>This is the expected plot. The data clusters by fraction and the total and nuclear are more similar than the chromatin fraction.</p>
</div>
<div id="density-across-genes" class="section level3">
<h3>Density across genes</h3>
<p>My snakefile has a rule collecting metrics with the picard tool. I used the data to make a plot of the normalized read density accross gene bodies.</p>
<div class="figure">
<img src="../data/read.dist.across.gene.rnaseq.png" alt="Normalized reads accross gene bodies" />
<p class="caption">Normalized reads accross gene bodies</p>
</div>
<p>Due to sample switch. The total is actually chromatin and the chromatin samples are actually the total samples.</p>
</div>
<div id="session-information" class="section level2">
<h2>Session information</h2>
<pre class="r"><code>sessionInfo()</code></pre>
<pre><code>R version 3.4.2 (2017-09-28)
Platform: x86_64-apple-darwin15.6.0 (64-bit)
Running under: macOS Sierra 10.12.6
Matrix products: default
BLAS: /Library/Frameworks/R.framework/Versions/3.4/Resources/lib/libRblas.0.dylib
LAPACK: /Library/Frameworks/R.framework/Versions/3.4/Resources/lib/libRlapack.dylib
locale:
[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
attached base packages:
[1] stats graphics grDevices utils datasets methods base
other attached packages:
[1] bindrcpp_0.2 reshape2_1.4.3 workflowr_1.0.1 rmarkdown_1.8.5
[5] edgeR_3.20.9 limma_3.34.9 dplyr_0.7.4 ggplot2_2.2.1
loaded via a namespace (and not attached):
[1] Rcpp_0.12.15 compiler_3.4.2 pillar_1.1.0
[4] git2r_0.21.0 plyr_1.8.4 bindr_0.1
[7] R.methodsS3_1.7.1 R.utils_2.6.0 tools_3.4.2
[10] digest_0.6.14 evaluate_0.10.1 tibble_1.4.2
[13] gtable_0.2.0 lattice_0.20-35 pkgconfig_2.0.1
[16] rlang_0.1.6 yaml_2.1.16 stringr_1.2.0
[19] knitr_1.18 locfit_1.5-9.1 rprojroot_1.3-2
[22] grid_3.4.2 glue_1.2.0 R6_2.2.2
[25] magrittr_1.5 whisker_0.3-2 backports_1.1.2
[28] scales_0.5.0 htmltools_0.3.6 assertthat_0.2.0
[31] colorspace_1.3-2 labeling_0.3 stringi_1.1.6
[34] lazyeval_0.2.1 munsell_0.4.3 R.oo_1.22.0 </code></pre>
</div>
<hr>
<p>
</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>
-->
<!-- 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 reproducible <a href="http://rmarkdown.rstudio.com">R Markdown</a>
analysis was created with
<a href="https://github.com/jdblischak/workflowr">workflowr</a> 1.0.1
</p>
<hr>
</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>