<!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" />
<meta name="date" content="2018-01-29" />
<title>Explore coverage within 3` UTRs</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">Net-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/brimittleman/Net-seq">
<span class="fa fa-github"></span>
</a>
</li>
</ul>
</div><!--/.nav-collapse -->
</div><!--/.container -->
</div><!--/.navbar -->
<div class="fluid-row" id="header">
<h1 class="title toc-ignore">Explore coverage within 3` UTRs</h1>
<h4 class="author"><em>Briana Mittleman</em></h4>
<h4 class="date"><em>2018-01-29</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> 2018-01-31</p>
<!-- Insert the code version (Git commit SHA1) if Git repository exists and R
package git2r is installed -->
<p><strong>Code version:</strong> 308d2b5</p>
<!-- Add your analysis here -->
<p>I have a file with the 3` UTRs and I want to extract coverage from the drop and dronc seq bam files that are in these UTR regions.</p>
<p>I will use:</p>
<ul>
<li>bedtools coverage -d -a /project2/gilad/spott/dropBams/Day7_cardiomyocytes_drop_seq.bam -b /project2/gilad/briana/apa_sites/three_prime_utr.bed > drop7_cardio_3utr.txt</li>
</ul>
<p>This is taking too much memory. I am going to convert bam to a bed file then sort it.</p>
<pre class="bash"><code>bedtools bamtobed -i /project2/gilad/spott/dropBams/Day7_cardiomyocytes_drop_seq.bam > Day7_cardiomyocytes_drop_seq.bed
sort -k1,1 -k2,2n Day7_cardiomyocytes_drop_seq.bed > Day7_cardiomyocytes_drop_seq_sort.bed </code></pre>
<p>Do this for the UTR file as well.</p>
<pre class="bash"><code>sort -k1,1 -k2,2n three_prime_utr.bed > three_prime_utr_sort.bed </code></pre>
<p>Now add the sorted to the coverage: Update the drop7_cardio_3UTR_cov.sh script</p>
<pre class="bash"><code>bedtools coverage -d -sorted -a /project2/gilad/briana/apa_sites/Day7_cardiomyocytes_drop_seq_sort.bed -b /project2/gilad/briana/apa_sites/three_prime_utr_sort.bed > drop7_cardio_3utr.txt</code></pre>
<p>Do this for one of 3’ seq lines too (LCL). The scipt is called lcl_3UTR_cov.sh.</p>
<p>These files are not correct. They have coverage for a region rather than per base in each UTR. Try to switch a and b in the script.</p>
<p>Now this seems correct. THe file has the UTR regions. A line for each base in the region in column 6 and the coverage at that base in column 7.</p>
<ul>
<li><p>LCL_3utrAB.bed</p></li>
<li><p>drop7_cardio_3utrAB.bed</p></li>
</ul>
<p>I will continue this analysis on the Rstudio for midway because the coverage files are so big.</p>
<div id="change-data-structure" class="section level3">
<h3>Change data structure:</h3>
<p>I am now using a python dictionary to create a file that has the UTRs as keys and the values as a list of the read count for that UTR. The script is /project2/gilad/briana/apa_sites/code/cov_per_UTR.py</p>
<p>To run this I have to make a bash script. I called it test.sh for now.</p>
<p>It has the bash heading, module load python, and the following line to call the pythn script.</p>
<p>‘python cov_per_UTR.py ../LCL_3utrAB.bed ../output/cov_at_UTRs_LCL.csv’</p>
<p>This takes too long to run. I will up the time and add a step that creates a file from the UTR list. This will help me know if the keys are created partway through the run. The new py script is cov_per_UTR2.py and takes 3 arguments, data, a UTR_names file and a full output file. The bash script to run this is /project2/gilad/briana/apa_sites/code/utr_py_lcl.sh. I updates this file for the drop7 coverage file as well. The bash script for this is /project2/gilad/briana/apa_sites/code/utr_py_drop7.sh.</p>
</div>
<div id="use-the-group-by-function" class="section level3">
<h3>Use the group by function:</h3>
<p>First seperate the files by pos and neg strand UTR</p>
<pre class="bash"><code>
awk '{if ($6 == "+") {print} }' drop7_cardio_3utrAB.bed > drop7_cardio_3utrAB.pos.bed
awk '{if ($6 == "-") {print} }' drop7_cardio_3utrAB.bed > drop7_cardio_3utrAB.neg.bed
awk '{if ($6 == "-") {print} }' LCL_3utrAB.bed > LCL_3utrAB.neg.bed
awk '{if ($6 == "+") {print} }' LCL_3utrAB.bed > LCL_3utrAB.pos.bed
</code></pre>
<p>Use the group by bedtools function to group by the 7th column (base number in the UTR) and get the mean for the coverage at that base. This script is /project2/gilad/briana/apa_sites/groupby/per_base_mean.sh</p>
<pre class="bash"><code>#!/bin/bash
#SBATCH --job-name=mean_UTR
#SBATCH --time=2:00:00
#SBATCH --partition=gilad
#SBATCH --mem=10G
#SBATCH --mail-type=END
#SBATCH --ntasks-per-node=2
module load Anaconda3
source activate net-seq
bedtools groupby -i drop7_cardio_3utrAB.pos.bed -g 7 -c 8 -o mean > drop7_cardio_pos_mean.bed
bedtools groupby -i drop7_cardio_3utrAB.neg.bed -g 7 -c 8 -o mean > drop7_cardio_neg_mean.bed
bedtools groupby -i LCL_3utrAB.pos.bed -g 7 -c 8 -o mean > LCL_pos_mean.bed
bedtools groupby -i LCL_3utrAB.neg.bed -g 7 -c 8 -o mean > LCL_neg_mean.bed</code></pre>
<p>This doesnt work. I am going to subset the file and try this for 1 chromosome.</p>
<ul>
<li>less drop7_cardio_3utrAB.pos.bed |head -n 10000 |sort -k7,7n |bedtools groupby -i stdin -g 7 -c 8 -o mean | head -n 10000</li>
</ul>
<pre class="bash"><code>awk '{if ($1 == "chr21") {print} }' drop7_cardio_3utrAB.pos.bed > drop7_cardio_3utrAB.pos.chr21.bed</code></pre>
<pre class="r"><code>drop7_3UTR_pos_chr21= read.table("../data/drop7_cardio_3utrAB.pos.chr21.bed", header=FALSE)</code></pre>
<pre class="r"><code>library(dplyr)</code></pre>
<pre><code>
Attaching package: 'dplyr'</code></pre>
<pre><code>The following objects are masked from 'package:stats':
filter, lag</code></pre>
<pre><code>The following objects are masked from 'package:base':
intersect, setdiff, setequal, union</code></pre>
<pre class="r"><code>group_by(drop7_3UTR_pos_chr21, V7) %>% summarise(sum=sum(V8)) -> UTR_21_cov
plot(UTR_21_cov$sum, ylab="sum expression", xlab="UTR base position", main="Chr 21 3' UTR coverage Dropseq day 7")</code></pre>
<p><img src="figure/UTR_coverage.Rmd/unnamed-chunk-8-1.png" width="672" style="display: block; margin: auto;" /></p>
<pre class="r"><code>utr_unique_pos= unique(drop7_3UTR_pos_chr21[,1:3])
summary(utr_unique_pos$V3-utr_unique_pos$V2)</code></pre>
<pre><code> Min. 1st Qu. Median Mean 3rd Qu. Max.
2 286 642 1269 1443 8907 </code></pre>
<pre class="r"><code>plot(UTR_21_cov$sum, ylab="sum expression", xlab="UTR base position", main="Chr 21 3' UTR coverage Dropseq day 7", xlim = c(0,1000))</code></pre>
<p><img src="figure/UTR_coverage.Rmd/unnamed-chunk-10-1.png" width="672" style="display: block; margin: auto;" /></p>
<p>Do this on the negative strand.</p>
<pre class="r"><code>drop7_3UTR_neg_chr21= read.table("../data/drop7_cardio_3utrAB.neg.chr21.bed", header=FALSE)
group_by(drop7_3UTR_neg_chr21, V7) %>% summarise(sum=sum(V8)) -> UTR_21neg_cov
plot(UTR_21neg_cov$sum, ylab="sum expression", xlab="UTR base position", main="Chr 21 3' UTR coverage Dropseq day 7")</code></pre>
<p><img src="figure/UTR_coverage.Rmd/unnamed-chunk-11-1.png" width="672" style="display: block; margin: auto;" /></p>
<p>Average utr size:</p>
<pre class="r"><code>utr_unique= unique(drop7_3UTR_neg_chr21[,1:3])
summary(utr_unique$V3-utr_unique$V2)</code></pre>
<pre><code> Min. 1st Qu. Median Mean 3rd Qu. Max.
2.0 102.0 166.0 564.4 414.0 10781.0 </code></pre>
<p>Subset plot wit this information:</p>
<pre class="r"><code>plot(UTR_21neg_cov$sum, ylab="sum expression", xlab="UTR base position- negative strand", main="Chr 21 3' UTR coverage Dropseq day 7", xlim=c(0,1000))</code></pre>
<p><img src="figure/UTR_coverage.Rmd/unnamed-chunk-13-1.png" width="672" style="display: block; margin: auto;" /></p>
<p>With the 3` seq:</p>
<pre class="r"><code>LCL_3UTR_neg_chr20= read.table("../data/LCL_3utrAB.neg.chr20.bed", header=FALSE)
group_by(LCL_3UTR_neg_chr20, V7) %>% summarise(sum=sum(V8)) -> LCL_UTR_20_cov
plot(LCL_UTR_20_cov$sum, ylab="mean expression", xlab="UTR base position", main="Chr 20 3' UTR coverage LCL")</code></pre>
<p><img src="figure/UTR_coverage.Rmd/unnamed-chunk-14-1.png" width="672" style="display: block; margin: auto;" /></p>
<pre class="r"><code>utr_lclneg_unique= unique(LCL_3UTR_neg_chr20[,1:3])
summary(utr_lclneg_unique$V3-utr_lclneg_unique$V2)</code></pre>
<pre><code> Min. 1st Qu. Median Mean 3rd Qu. Max.
2.0 101.0 172.0 582.8 576.2 9106.0 </code></pre>
<p>Plot a little past the median:</p>
<pre class="r"><code>plot(LCL_UTR_20_cov$sum, ylab="mean expression", xlab="UTR base position", main="Chr 20 3' UTR coverage LCL", xlim=c(0,200))</code></pre>
<p><img src="figure/UTR_coverage.Rmd/unnamed-chunk-16-1.png" width="672" style="display: block; margin: auto;" /></p>
<pre class="r"><code>LCL_3UTR_pos_chr1= read.table("../data/LCL_3utrAB_pos.chr1.bed", header=FALSE)
group_by(LCL_3UTR_pos_chr1, V7) %>% summarise(sum=sum(V8)) -> LCL_UTR_1_cov
plot(LCL_UTR_1_cov$sum, ylab="mean expression", xlab="UTR base position", main="Chr 1 3' UTR coverage LCL")</code></pre>
<p><img src="figure/UTR_coverage.Rmd/unnamed-chunk-17-1.png" width="672" style="display: block; margin: auto;" /></p>
</div>
<div id="session-information" class="section level2">
<h2>Session information</h2>
<!-- Insert the session information into the document -->
<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] dplyr_0.7.4
loaded via a namespace (and not attached):
[1] Rcpp_0.12.15 assertthat_0.2.0 digest_0.6.14 rprojroot_1.3-2
[5] R6_2.2.2 backports_1.1.2 git2r_0.21.0 magrittr_1.5
[9] evaluate_0.10.1 pillar_1.1.0 rlang_0.1.6 stringi_1.1.6
[13] bindrcpp_0.2 rmarkdown_1.8.5 tools_3.4.2 stringr_1.2.0
[17] glue_1.2.0 yaml_2.1.16 compiler_3.4.2 pkgconfig_2.0.1
[21] htmltools_0.3.6 bindr_0.1 knitr_1.18 tibble_1.4.2 </code></pre>
</div>
<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>