<!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="2017-11-30" />
<title>Check read counts in binned genome</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">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">Check read counts in binned genome</h1>
<h4 class="author"><em>Briana Mittleman</em></h4>
<h4 class="date"><em>2017-11-30</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> 2017-12-04</p>
<!-- Insert the code version (Git commit SHA1) if Git repository exists and R
package git2r is installed -->
<p><strong>Code version:</strong> a63bb5f</p>
<!-- Add your analysis here -->
<div id="bash-script" class="section level3">
<h3>Bash script</h3>
<p>Split genome into 200bp windows and run the coverage command:</p>
<p>/project2/gilad/briana/Net-seq/genome_bed/hg19_200bp_window.bed</p>
<p>/project2/gilad/briana/Net-seq/ref_genes/windows_200</p>
<p>make window_200_cov.sh</p>
<pre class="bash"><code>#!/bin/bash
#SBATCH --job-name=window_200_cov
#SBATCH --time=8:00:00
#SBATCH --partition=broadwl
#SBATCH --mem=50G
#SBATCH --tasks-per-node=4
#SBATCH --mail-type=END
bedtools coverage -counts -a /project2/gilad/briana/Net-seq/genome_bed/hg19_200bp_window.bed -b /project2/gilad/briana/Net-seq/Net-seq1/data/bed_sort/net1_18486_dep_chr_sort.bed > /project2/gilad/briana/Net-seq/ref_genes/windows_200/window_200_cov_18486.txt
bedtools coverage -counts -a /project2/gilad/briana/Net-seq/genome_bed/hg19_200bp_window.bed -b /project2/gilad/briana/Net-seq/Net-seq1/data/bed_sort/net1_18508_dep_chr_sort.bed > /project2/gilad/briana/Net-seq/ref_genes/windows_200/window_200_cov_18508_dep.txt
bedtools coverage -counts -a /project2/gilad/briana/Net-seq/genome_bed/hg19_200bp_window.bed -b /project2/gilad/briana/Net-seq/Net-seq1/data/bed_sort/net1_18508_nondep_chr_sort.bed > /project2/gilad/briana/Net-seq/ref_genes/windows_200/window_200_cov_18508_nondep.txt
bedtools coverage -counts -a /project2/gilad/briana/Net-seq/genome_bed/hg19_200bp_window.bed -b /project2/gilad/briana/Net-seq/Net-seq1/data/bed_sort/net1_19238_dep_chr_sort.bed > /project2/gilad/briana/Net-seq/ref_genes/windows_200/window_200_cov_19238.txt
bedtools coverage -counts -a /project2/gilad/briana/Net-seq/genome_bed/hg19_200bp_window.bed -b /project2/gilad/briana/Net-seq/data/bed_sort/mayer_SRR1575922_chr_sort.bed > /project2/gilad/briana/Net-seq/ref_genes/windows_200/window_200_cov_mayer.txt
#bedtools coverage -counts -a /project2/gilad/briana/Net-seq/genome_bed/hg19_200bp_window.bed -b /project2/gilad/briana/Net-seq/Net-seq1/data/bed/merged_Net1.chr.bed > /project2/gilad/briana/Net-seq/ref_genes/windows_200/window_200_cov_merged.txt
#step memory exceeded!</code></pre>
</div>
<div id="import-data" class="section level3">
<h3>Import data</h3>
<pre class="r"><code>window_200_18486=read.csv("../data/windows_200/window_200_cov_18486.txt", header=FALSE, sep="\t")
window_200_18508_dep=read.csv("../data/windows_200/window_200_cov_18508_dep.txt", header=FALSE, sep="\t")
window_200_18508_nondep=read.csv("../data/windows_200/window_200_cov_18508_nondep.txt", header=FALSE, sep="\t")
window_200_19238=read.csv("../data/windows_200/window_200_cov_19238.txt", header=FALSE, sep="\t")
window_200_mayer= read.csv("../data/windows_200/window_200_cov_mayer.txt", header=FALSE, sep="\t")</code></pre>
<p>Add col labels to each file:</p>
<pre class="r"><code>colnames(window_200_18486) = c("chr", "start", "end", "count")
colnames(window_200_18508_dep) = c("chr", "start", "end", "count")
colnames(window_200_18508_nondep) = c("chr", "start", "end", "count")
colnames(window_200_19238) = c("chr", "start", "end", "count")
colnames(window_200_mayer) = c("chr", "start", "end", "count")</code></pre>
</div>
<div id="plot-data" class="section level3">
<h3>Plot data</h3>
<p>Data I want to look at:</p>
<ul>
<li>summary per library</li>
</ul>
<pre class="r"><code>summary(window_200_18486$count)</code></pre>
<pre><code> Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 0 1 0 4076520 </code></pre>
<pre class="r"><code>summary(window_200_18508_dep$count)</code></pre>
<pre><code> Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 0 21 0 27069584 </code></pre>
<pre class="r"><code>summary(window_200_18508_nondep$count)</code></pre>
<pre><code> Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 0 23 0 30571781 </code></pre>
<pre class="r"><code>summary(window_200_19238$count)</code></pre>
<pre><code> Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 0 4 0 13033253 </code></pre>
<pre class="r"><code>summary(window_200_mayer$count)</code></pre>
<pre><code> Min. 1st Qu. Median Mean 3rd Qu. Max.
0.0 0.0 0.0 113.3 0.0 701170.0 </code></pre>
<p>Use a plot to see the distribution:</p>
<ul>
<li>summaries not including zero</li>
</ul>
<p>Make dataframe excluding the zeros:</p>
<pre class="r"><code>window_200_18486_non0= window_200_18486[window_200_18486$count!=0,]
window_200_18508_dep_non0= window_200_18508_dep[window_200_18508_dep$count!=0,]
window_200_18508_nondep_non0= window_200_18508_nondep[window_200_18508_nondep$count!=0,]
window_200_19238_non0= window_200_19238[window_200_19238$count!=0,]
window_200_mayer_non0= window_200_mayer[window_200_mayer$count!=0,]</code></pre>
<p>summarise</p>
<pre class="r"><code>summary(window_200_18486_non0$count)</code></pre>
<pre><code> Min. 1st Qu. Median Mean 3rd Qu. Max.
1 1 1 45 3 4076520 </code></pre>
<pre class="r"><code>summary(window_200_18508_dep_non0$count)</code></pre>
<pre><code> Min. 1st Qu. Median Mean 3rd Qu. Max.
1 1 1 624 3 27069584 </code></pre>
<pre class="r"><code>summary(window_200_18508_nondep_non0$count)</code></pre>
<pre><code> Min. 1st Qu. Median Mean 3rd Qu. Max.
1 1 1 633 3 30571781 </code></pre>
<pre class="r"><code>summary(window_200_19238_non0$count)</code></pre>
<pre><code> Min. 1st Qu. Median Mean 3rd Qu. Max.
1 1 1 149 3 13033253 </code></pre>
<pre class="r"><code>summary(window_200_mayer_non0$count)</code></pre>
<pre><code> Min. 1st Qu. Median Mean 3rd Qu. Max.
1 1 1 2200 2 701170 </code></pre>
<pre class="r"><code>plot(sort(log(window_200_19238_non0$count), decreasing=TRUE))</code></pre>
<p><img src="figure/bin_windows.Rmd/unnamed-chunk-7-1.png" width="672" style="display: block; margin: auto;" /></p>
<ul>
<li>number of entries that are non zero</li>
</ul>
<pre class="r"><code>x= nrow(window_200_18486)
barplot(c(nrow(window_200_18486_non0)/x,nrow(window_200_18508_dep_non0)/x,nrow(window_200_18508_nondep_non0)/x, nrow(window_200_19238_non0)/x), main="Proportion of detected bins", names=c("18486", "18508 \n dep", "18508 \n nondep", "19238"))</code></pre>
<p><img src="figure/bin_windows.Rmd/unnamed-chunk-8-1.png" width="672" style="display: block; margin: auto;" /></p>
<pre class="r"><code>nrow(window_200_mayer_non0)/x</code></pre>
<pre><code>[1] 0.05149546</code></pre>
</div>
<div id="integrate-sets" class="section level3">
<h3>Integrate sets:</h3>
<pre class="r"><code>window_non_0_all= nrow(window_200_18486[window_200_18486$count!=0 | window_200_18508_dep$count!=0 | window_200_18486$count!=0,] )
prop_window_non0= window_non_0_all/x
prop_window_non0</code></pre>
<pre><code>[1] 0.05416194</code></pre>
<pre class="r"><code>window_non_0_2= nrow(window_200_18486[window_200_18486$count!=0 | window_200_18508_dep$count!=0,] )
prop_window_non0_2= window_non_0_2/x
prop_window_non0_2</code></pre>
<pre><code>[1] 0.05416194</code></pre>
<pre class="r"><code>window_non_0_2b= nrow(window_200_18486[window_200_18486$count!=0 |window_200_18486$count!=0,] )
prop_window_non0_2b= window_non_0_2b/x
prop_window_non0_2b</code></pre>
<pre><code>[1] 0.03282309</code></pre>
</div>
<div id="explore-bin-overlap" class="section level3">
<h3>Explore bin overlap</h3>
<p>I will combine the depleted samples counts in one data frame:</p>
<pre class="r"><code>window_200_3lib= cbind(window_200_18486, window_200_18508_dep$count, window_200_19238$count)
colnames(window_200_3lib)= c("chr", "start", "end", "18486", "18508", "19238")</code></pre>
<p>Make a vector with how many of the libraries have coverage for each bin</p>
<pre class="r"><code>sum_vec= apply(window_200_3lib[,4:6],1,function(x)sum(x>=1))
window_200_3lib= cbind(window_200_3lib, sum_vec)</code></pre>
<p>Explore the results:</p>
<pre class="r"><code>bin_0= sum(sum_vec==0)
bin_1= sum(sum_vec==1)
bin_2= sum(sum_vec==2)
bin_3= sum(sum_vec==3)
prop0=bin_0/x
prop1=bin_1/x
prop2=bin_2/x
prop3=bin_3/x
barplot_prop=(barplot(c(prop1, prop2, prop3),names = c("1 bin", "2 bins", "3 bins"), main="Proportion of bins with coverage in 3 libaries", ylab="proportion", xlab="library" ))</code></pre>
<p><img src="figure/bin_windows.Rmd/unnamed-chunk-14-1.png" width="672" style="display: block; margin: auto;" /></p>
<pre class="r"><code>prop_vec=c(prop0,prop1, prop2, prop3)
names_vec= c("0 bins","1 bin", "2 bins", "3 bins")
prop_table=rbind(names_vec,prop_vec)
prop_table</code></pre>
<pre><code> [,1] [,2] [,3]
names_vec "0 bins" "1 bin" "2 bins"
prop_vec "0.934702546224945" "0.0453430987382321" "0.0115298190107529"
[,4]
names_vec "3 bins"
prop_vec "0.00842453602607038"</code></pre>
</div>
<div id="perform-on-mayer-data-or-multiple-lanes" class="section level3">
<h3>Perform on mayer data or multiple lanes</h3>
<pre class="bash"><code>#!/bin/bash
#SBATCH --job-name=window_200_cov_mayer
#SBATCH --time=8:00:00
#SBATCH --partition=broadwl
#SBATCH --mem=50G
#SBATCH --tasks-per-node=4
#SBATCH --mail-type=END
module load bedtools
bedtools coverage -counts -a /project2/gilad/briana/Net-seq/genome_bed/hg19_200bp_window.bed -b /project2/gilad/briana/mayer.data/mayer_hek/data/bed/mayer_hek-sort.chr.bed > /project2/gilad/briana/mayer.data/mayer_hek/data/window_200_cov_mayer_hek.txt</code></pre>
<p>Not enough memory</p>
</div>
<div id="bin-the-gene-file" class="section level3">
<h3>Bin the gene file:</h3>
<pre class="bash"><code>bedtools makewindows -b ref_seq_gene_hg19 -w 200 > ref_seq_gene_hg16_bins.bed</code></pre>
<p>Make a bash script to get coverage in these bins. This is in /project2/gilad/briana/Net-seq/ref_genes/gene_windows_200/gene_window_200.sh</p>
<pre class="bash"><code>#!/bin/bash
#SBATCH --job-name=gene_window_200_cov
#SBATCH --time=8:00:00
#SBATCH --partition=broadwl
#SBATCH --mem=30G
#SBATCH --tasks-per-node=4
#SBATCH --mail-type=END
bedtools coverage -counts -a /project2/gilad/briana/Net-seq/ref_genes/ref_seq_gene_hg16_bins.bed -b /project2/gilad/briana/Net-seq/Net-seq1/data/bed_sort/net1_18486_dep_chr_sort.bed > /project2/gilad/briana/Net-seq/ref_genes/gene_windows_200/gene_window_cov_18486.txt
bedtools coverage -counts -a /project2/gilad/briana/Net-seq/ref_genes/ref_seq_gene_hg16_bins.bed -b /project2/gilad/briana/Net-seq/Net-seq1/data/bed_sort/net1_18508_dep_chr_sort.bed > /project2/gilad/briana/Net-seq/ref_genes/gene_windows_200/gene_window_cov_18508_dep.txt
bedtools coverage -counts -a /project2/gilad/briana/Net-seq/ref_genes/ref_seq_gene_hg16_bins.bed -b /project2/gilad/briana/Net-seq/Net-seq1/data/bed_sort/net1_19238_dep_chr_sort.bed > /project2/gilad/briana/Net-seq/ref_genes/gene_windows_200/gene_window_cov_19238.txt
bedtools coverage -counts -a /project2/gilad/briana/Net-seq/ref_genes/ref_seq_gene_hg16_bins.bed -b /project2/gilad/briana/Net-seq/data/bed_sort/mayer_SRR1575922_chr_sort.bed > /project2/gilad/briana/Net-seq/ref_genes/gene_windows_200/gene_window_cov_mayer.txt
</code></pre>
<p><strong>This file has 22071951 bins. This is not a good representation because some locations in the genome are in multiple genes. I need to think about this more. Maybe I can only keep unique windows.</strong></p>
<p>``ref_seq_gene_hg16_bins.bed | uniq -u | wc -l```</p>
<p><strong>This leaves 5023160 lines. Still not right because the genes start at different positions but overlap then the lines wouldnt be unique.</strong></p>
<p>Use bedtools intersect -a genome -b genes -wa:</p>
<ul>
<li><p>a is the genome windows</p></li>
<li><p>b is the gene file</p></li>
</ul>
<p>This should keep the windows of a that intersect b. This means I will only have windows that contain a gene.</p>
<pre class="bash"><code>
bedtools intersect -a /project2/gilad/briana/Net-seq/genome_bed/hg19_windows_sort_2.bed -b /project2/gilad/briana/Net-seq/ref_genes/ref_seq_gene_hg19_small.bed -wa > /project2/gilad/briana/Net-seq/genome_bed/hg19_windows_with_gene.bed
</code></pre>
<p>ERROR:</p>
<p>ERROR: Received illegal bin number 262143 from getBin call.<br />
ERROR: Unable to add record to tree</p>
<p>Potential problem: hg19 file starts with chrom 10 and the gene file starts with chr1. Maybe try sorting the gene file the way I sorted the hg19 file.</p>
<p>Get the chr# list from the genes file using:</p>
<p><code>cut -f 1 | uniq /project2/gilad/briana/Net-seq/ref_genes/ref_seq_gene_hg19_small.bed > names.txt</code></p>
<pre class="bash"><code>#!/bin/bash
#SBATCH --job-name=sortgene
#SBATCH --time=8:00:00
#SBATCH --partition=broadwl
#SBATCH --mem=20G
#SBATCH --tasks-per-node=4
#SBATCH --mail-type=END
module load bedtools
cd /project2/gilad/briana/Net-seq/genome_bed
bedtools sort -faidx names_uniq.txt -i hg19_200bp_window.bed -o hg19_windows_sort.bed</code></pre>
<p>ERROR: Chromosome “chr1” undefined in names_uniq.txt</p>
<p>Try:</p>
<p><code>sort -k 1,1 -k2,2n hg19_200bp_window.bed > hg19_windows_sort_2.bed</code></p>
<p>Cut the gene file to only have the first 3 columns with:</p>
<p><code>cut -f 1,2,3 ref_seq_gene_hg19 > ref_seq_gene_hg19_3col.bed</code></p>
<p>Run intersect:</p>
<pre class="bash"><code>bedtools intersect -a /project2/gilad/briana/Net-seq/genome_bed/hg19_windows_sort_2.bed -b /project2/gilad/briana/Net-seq/ref_genes/ref_seq_gene_hg19_3col.bed -wa > /project2/gilad/briana/Net-seq/genome_bed/hg19_windows_with_gene.bed </code></pre>
<p>This worked but you still have multiples. I will take the unique lines of this with:</p>
<p><code>cat hg19_windows_with_gene.bed | uniq > hg19_windows_with_gene_uniq.bed</code></p>
<p>Now I can run the coverage counts on this file to see the how many of the genome bins that had at least one gene have coverage.</p>
<p>Call this script. uniq_gene_window.sh in /project2/gilad/briana/Net-seq/ref_genes/uniq_gene_windows_200</p>
<pre class="bash"><code>#!/bin/bash
#SBATCH --job-name=uniq_gene_window
#SBATCH --time=8:00:00
#SBATCH --partition=broadwl
#SBATCH --mem=30G
#SBATCH --tasks-per-node=4
#SBATCH --mail-type=END
bedtools coverage -counts -a /project2/gilad/briana/Net-seq/genome_bed/hg19_windows_with_gene_uniq.bed -b /project2/gilad/briana/Net-seq/Net-seq1/data/bed_sort/net1_18486_dep_chr_sort.bed > /project2/gilad/briana/Net-seq/ref_genes/uniq_gene_windows_200/uniq_gene_window_cov_18486.txt
bedtools coverage -counts -a /project2/gilad/briana/Net-seq/genome_bed/hg19_windows_with_gene_uniq.bed -b /project2/gilad/briana/Net-seq/Net-seq1/data/bed_sort/net1_18508_dep_chr_sort.bed > /project2/gilad/briana/Net-seq/ref_genes/uniq_gene_windows_200/uniq_gene_window_cov_18508_dep.txt
bedtools coverage -counts -a /project2/gilad/briana/Net-seq/genome_bed/hg19_windows_with_gene_uniq.bed -b /project2/gilad/briana/Net-seq/Net-seq1/data/bed_sort/net1_19238_dep_chr_sort.bed > /project2/gilad/briana/Net-seq/ref_genes/uniq_gene_windows_200/uniq_gene_window_cov_19238.txt
bedtools coverage -counts -a /project2/gilad/briana/Net-seq/genome_bed/hg19_windows_with_gene_uniq.bed -b /project2/gilad/briana/Net-seq/data/bed_sort/mayer_SRR1575922_chr_sort.bed > /project2/gilad/briana/Net-seq/ref_genes/uniq_gene_windows_200/uniq_gene_window_cov_mayer.txt
</code></pre>
<div id="load-uniq-gene-files" class="section level4">
<h4>Load uniq gene files:</h4>
<p>These are the uniq bind in the genome 200bp window file that include a gene.</p>
<pre class="r"><code>uniq_gene_window_18486=read.csv("../data/uniq_genes/uniq_gene_window_cov_18486.txt", header=FALSE, sep="\t")
uniq_gene_window_18508=read.csv("../data/uniq_genes/uniq_gene_window_cov_18508_dep.txt", header=FALSE, sep="\t")
uniq_gene_window_19238=read.csv("../data/uniq_genes/uniq_gene_window_cov_19238.txt", header=FALSE, sep="\t")
uniq_gene_window_mayer=read.csv("../data/uniq_genes/uniq_gene_window_cov_mayer.txt", header=FALSE, sep="\t")</code></pre>
<pre class="r"><code>colnames(uniq_gene_window_mayer)= c("chr", "start", "end", "count")
colnames(uniq_gene_window_19238)= c("chr", "start", "end", "count")
colnames(uniq_gene_window_18486)= c("chr", "start", "end", "count")
colnames(uniq_gene_window_18508)= c("chr", "start", "end", "count")</code></pre>
<p>Look at the number of windows with coverage:</p>
<pre class="r"><code>uniq_gene_window_18486_no0= uniq_gene_window_18486[uniq_gene_window_18486$count!=0,]
uniq_gene_window_18508_no0= uniq_gene_window_18508[uniq_gene_window_18508$count!=0,]
uniq_gene_window_19238_no0= uniq_gene_window_19238[uniq_gene_window_19238$count!=0,]
uniq_gene_window_mayer_no0= uniq_gene_window_mayer[uniq_gene_window_mayer$count!=0,]</code></pre>
<p>Bar plot for coverage:</p>
<pre class="r"><code>gene_windows= nrow(uniq_gene_window_mayer)
barplot(c(nrow(uniq_gene_window_18486_no0)/gene_windows, nrow(uniq_gene_window_18508_no0)/gene_windows, nrow(uniq_gene_window_19238_no0)/gene_windows, nrow(uniq_gene_window_mayer_no0)/gene_windows), main="Coverage for windows with genes", names= c("18486", "18508", "19238", "Mayer"), xlab="Library")</code></pre>
<p><img src="figure/bin_windows.Rmd/unnamed-chunk-25-1.png" width="672" style="display: block; margin: auto;" /></p>
<pre class="r"><code>mayer_gene_coverage=nrow(uniq_gene_window_mayer_no0)/gene_windows</code></pre>
<p>Mayer has more coverage for this parameter. Their library has 0.0954862.</p>
<p>Ours:</p>
<ul>
<li><p>18486: 0.0495328</p></li>
<li><p>18508: 0.0460654</p></li>
<li><p>19238: 0.0346009</p></li>
</ul>
</div>
</div>
<div id="session-information" class="section level3">
<h3>Session information</h3>
<!-- 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
loaded via a namespace (and not attached):
[1] compiler_3.4.2 backports_1.1.1 magrittr_1.5 rprojroot_1.2
[5] tools_3.4.2 htmltools_0.3.6 yaml_2.1.14 Rcpp_0.12.13
[9] stringi_1.1.5 rmarkdown_1.6 knitr_1.17 git2r_0.19.0
[13] stringr_1.2.0 digest_0.6.12 evaluate_0.10.1</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>