<!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>Prepare leafcutter pheno combined peak</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-5.0.13/css/fa-svg-with-js.css" rel="stylesheet" />
<script src="site_libs/font-awesome-5.0.13/js/fontawesome-all.min.js"></script>
<script src="site_libs/font-awesome-5.0.13/js/fa-v4-shims.min.js"></script>
<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;
}
.html-widget {
margin-bottom: 20px;
}
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">Prepare leafcutter pheno combined peak</h1>
<h4 class="author"><em>Briana Mittleman</em></h4>
<h4 class="date"><em>8/14/2018</em></h4>
</div>
<p><strong>Last updated:</strong> 2018-08-15</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/695a918f5197757e39ac49d497f042413ed15f96" target="_blank">695a918</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: .DS_Store
Ignored: .Rhistory
Ignored: .Rproj.user/
Ignored: output/.DS_Store
Untracked files:
Untracked: analysis/ncbiRefSeq_sm.sort.mRNA.bed
Untracked: analysis/snake.config.notes.Rmd
Untracked: data/18486.genecov.txt
Untracked: data/APApeaksYL.total.inbrain.bed
Untracked: data/Totalpeaks_filtered_clean.bed
Untracked: data/YL-SP-18486-T-combined-genecov.txt
Untracked: data/YL-SP-18486-T_S9_R1_001-genecov.txt
Untracked: data/bedgraph_peaks/
Untracked: data/bin200.5.T.nuccov.bed
Untracked: data/bin200.Anuccov.bed
Untracked: data/bin200.nuccov.bed
Untracked: data/clean_peaks/
Untracked: data/comb_map_stats.csv
Untracked: data/comb_map_stats.xlsx
Untracked: data/combined_reads_mapped_three_prime_seq.csv
Untracked: data/gencov.test.csv
Untracked: data/gencov.test.txt
Untracked: data/gencov_zero.test.csv
Untracked: data/gencov_zero.test.txt
Untracked: data/gene_cov/
Untracked: data/joined
Untracked: data/leafcutter/
Untracked: data/merged_combined_YL-SP-threeprimeseq.bg
Untracked: data/nuc6up/
Untracked: data/reads_mapped_three_prime_seq.csv
Untracked: data/smash.cov.results.bed
Untracked: data/smash.cov.results.csv
Untracked: data/smash.cov.results.txt
Untracked: data/smash_testregion/
Untracked: data/ssFC200.cov.bed
Untracked: data/temp.file1
Untracked: data/temp.file2
Untracked: data/temp.gencov.test.txt
Untracked: data/temp.gencov_zero.test.txt
Untracked: output/picard/
Untracked: output/plots/
Untracked: output/qual.fig2.pdf
Unstaged changes:
Modified: analysis/28ind.peak.explore.Rmd
Modified: analysis/cleanupdtseq.internalpriming.Rmd
Modified: analysis/dif.iso.usage.leafcutter.Rmd
Modified: analysis/explore.filters.Rmd
Modified: analysis/peak.cov.pipeline.Rmd
Modified: analysis/test.max2.Rmd
Modified: code/Snakefile
</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/695a918f5197757e39ac49d497f042413ed15f96/analysis/pheno.leaf.comb.Rmd" target="_blank">695a918</a>
</td>
<td style="text-align:left;">
brimittleman
</td>
<td style="text-align:left;">
2018-08-15
</td>
<td style="text-align:left;">
code for pheno file sep total and nuc
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/0db7822ff5f434d73a8b86cc493829b58b4aae07/docs/pheno.leaf.comb.html" target="_blank">0db7822</a>
</td>
<td style="text-align:left;">
brimittleman
</td>
<td style="text-align:left;">
2018-08-15
</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/7ccb243cc9fe39c33fe78c7ebfe68812be107016/analysis/pheno.leaf.comb.Rmd" target="_blank">7ccb243</a>
</td>
<td style="text-align:left;">
brimittleman
</td>
<td style="text-align:left;">
2018-08-15
</td>
<td style="text-align:left;">
code for pheno file sep total and nuc
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/1ca608429c3464514896e6fac730819506c8f424/docs/pheno.leaf.comb.html" target="_blank">1ca6084</a>
</td>
<td style="text-align:left;">
brimittleman
</td>
<td style="text-align:left;">
2018-08-15
</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/73930028442670ceac17a9bf881b660a7c9a7174/analysis/pheno.leaf.comb.Rmd" target="_blank">7393002</a>
</td>
<td style="text-align:left;">
brimittleman
</td>
<td style="text-align:left;">
2018-08-15
</td>
<td style="text-align:left;">
code for pheno file
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/e0eefe62622a9c5fe9ae0628e364887c16ebf2e6/docs/pheno.leaf.comb.html" target="_blank">e0eefe6</a>
</td>
<td style="text-align:left;">
brimittleman
</td>
<td style="text-align:left;">
2018-08-14
</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/edbdbccfe8dca23b26715ac25ed0c35c815142f7/analysis/pheno.leaf.comb.Rmd" target="_blank">edbdbcc</a>
</td>
<td style="text-align:left;">
brimittleman
</td>
<td style="text-align:left;">
2018-08-14
</td>
<td style="text-align:left;">
attempt at x/y pheno format
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/c67380e570e74625b061e504b345fae77f0e3a6e/docs/pheno.leaf.comb.html" target="_blank">c67380e</a>
</td>
<td style="text-align:left;">
brimittleman
</td>
<td style="text-align:left;">
2018-08-14
</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/ba9a74f4e00c39a9fbf415e1d876195e9c0621e9/analysis/pheno.leaf.comb.Rmd" target="_blank">ba9a74f</a>
</td>
<td style="text-align:left;">
brimittleman
</td>
<td style="text-align:left;">
2018-08-14
</td>
<td style="text-align:left;">
add phenotype leafcutter analysis
</td>
</tr>
</tbody>
</table>
</ul>
<p></details></p>
<hr />
<p>Like I did on the first 16 individuals, I want to prepare a phenotype file for leafcutter. I will use this to start calling QTLs. I am using the filtered peaks called with Yang’s script. I need a file that has the peak and the coverage per individual. The phenotype per peak per individual is coverage at peak/coverage for all peaks in the same gene. First step is to map the peaks to a gene. I am going to use the refseq genes because they look like that have better annotated UTRs. I am going to subset to only the NM tagged mRNAs.</p>
<p>/project2/gilad/briana/genome_anotation_data/ncbiRefSeq_sm.sort.bed</p>
<pre class="bash"><code>awk '$4 ~ /NM/ {print}' ncbiRefSeq_sm.sort.bed > ncbiRefSeq_sm.sort.mRNA.bed</code></pre>
<p>I will use bedtools intersect and have it write peak and the gene that it intersects with. A is the peaks and B is the genes. I want to write out A with -wa and -wb because I want all of the info. I can then subset the parts I care about after. I want to force strandedness with -s. I say it is sorted with -sorted</p>
<pre class="bash"><code>#!/bin/bash
#SBATCH --job-name=intGenes_combfilterPeaks
#SBATCH --account=pi-yangili1
#SBATCH --time=24:00:00
#SBATCH --output=intGenes_combfilterPeaks.out
#SBATCH --error=intGenes_combfilterPeaks.err
#SBATCH --partition=broadwl
#SBATCH --mem=12G
#SBATCH --mail-type=END
module load Anaconda3
source activate three-prime-env
bedtools intersect -wa -wb -sorted -s -a /project2/gilad/briana/threeprimeseq/data/mergedPeaks_comb/filtered_APApeaks_merged_allchrom.named.fixed.bed -b /project2/gilad/briana/genome_anotation_data/ncbiRefSeq_sm_noChr.sort.mRNA.bed > /project2/gilad/briana/threeprimeseq/data/mergedPeaks_comb/filtered_APApeaks_merged_allchrom_refseqGenes.bed</code></pre>
<p>The result of this file has both files. I want to keep columns 1-6 and 10. This will be the peaks and the gene that overlaped it.</p>
<pre class="bash"><code>awk '{print $1 "\t" $2 "\t" $3 "\t" $4 "\t" $5 "\t" $6 "\t" $10}' /project2/gilad/briana/threeprimeseq/data/mergedPeaks_comb/filtered_APApeaks_merged_allchrom_refseqGenes.bed > /project2/gilad/briana/threeprimeseq/data/mergedPeaks_comb/filtered_APApeaks_merged_allchrom_refseqGenes_sm.bed
</code></pre>
<p>Now I can run feature counts on this file. In need to make the file into a saf file. This file has GeneID, Chr, Start, End, Strand. I want the ID to be peak#:chr1:start:end:strand:gene</p>
<pre class="bash"><code>from misc_helper import *
fout = file("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm.SAF",'w')
fout.write("GeneID\tChr\tStart\tEnd\tStrand\n")
for ln in open("/project2/gilad/briana/threeprimeseq/data/mergedPeaks_comb/filtered_APApeaks_merged_allchrom_refseqGenes_sm.bed"):
chrom, start, end, name, score, strand, gene = ln.split()
name_i=int(name)
start_i=int(start)
end_i=int(end)
ID = "peak%d:%s:%d:%d:%s:%s"%(name_i, chrom, start_i, end_i, strand, gene)
fout.write("%s\t%s\t%d\t%d\t%s\n"%(ID, chrom, start_i, end_i, strand))
fout.close()</code></pre>
<p>ref_gene_peak_fc.sh</p>
<pre class="bash"><code>#!/bin/bash
#SBATCH --job-name=ref_gene_peak_fc
#SBATCH --account=pi-yangili1
#SBATCH --time=24:00:00
#SBATCH --output=ref_gene_peak_fc.out
#SBATCH --error=ref_gene_peak_fc.err
#SBATCH --partition=broadwl
#SBATCH --mem=12G
#SBATCH --mail-type=END
module load Anaconda3
source activate three-prime-env
featureCounts -a /project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm.SAF -F SAF -o /project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant.fc /project2/gilad/briana/threeprimeseq/data/sort/*-sort.bam -s 1
</code></pre>
<p>The header of this file will need to be changed. I can do this by writing it out in python. fix_head_fc.py</p>
<pre class="bash"><code>
infile= open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant.fc", "r")
fout = file("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_fixed.fc",'w')
for line, i in enumerate(infile):
if line == 1:
i_list=i.split()
libraries=i_list[:6]
for sample in i_list[6:]:
full = sample.split("/")[7]
samp= full.split("-")[2:4]
lim="_"
samp_st=lim.join(samp)
libraries.append(samp_st)
first_line= "\t".join(libraries)
fout.write(first_line + '\n')
else :
fout.write(i)
fout.close()
</code></pre>
<p>The next step is looking by gene and make the x/y form. x is the number that already appears and y is the sum for all peaks in a specific gene.</p>
<p>The final file will just have the GeneID column and a column for each individual.</p>
<p>To work on this step I am going to make a smaller version of this file that I can easily work with interactively in python.</p>
<pre class="bash"><code>head -n 4 filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_fixed.fc > small.test.txt
</code></pre>
<pre class="bash"><code>#example from yangs dir /project2/yangili1/CMC/reformat_counts,py
from misc_helper import *
import gzip
dic_IND = {}
dic_BAM = {}
header = [x for x in gzip.open("DGN_perind.counts.gz").readline().split()]
for ln in open("file_id_mapping.txt"):
bam, IND = ln.split()
if bam not in header: continue
IND = IND.strip()
dic_IND[bam] = IND
if IND not in dic_BAM:
dic_BAM[IND] = []
dic_BAM[IND].append(bam)
INDs = dic_BAM.keys()
print INDs, len(INDs)
fout = gzip.open("DGNmerged_perind.counts.gz",'w')
fout.write(" ".join(['chrom']+INDs)+'\n')
for dic in stream_table(gzip.open("DGN_perind.counts.gz"),' '):
buf = [dic['chrom']]
for ind in INDs:
T,B = 0, 0
for bam in dic_BAM[ind]:
t,b =dic[bam].split('/')
T+=int(t)
B+=int(b)
#print ind, t,b
buf.append("%d/%d"%(T,B))
fout.write(" ".join(buf)+'\n')
fout.close()</code></pre>
<p>Re-write this for my test file. I need a file with the bams and the individuals. I can make this using the header from the previous file.</p>
<p>create_fileid.py</p>
<pre class="bash"><code>fout = file("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/file_id_mapping.txt",'w')
infile= open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_fixed.fc", "r")
for line, i in enumerate(infile):
if line == 0:
i_list=i.split()
files= i_list[10:-2]
for each in files:
full = each.split("/")[7]
samp= full.split("-")[2:4]
lim="_"
samp_st=lim.join(samp)
outLine= full[:-1] + "\t" + samp_st
fout.write(outLine + "\n")
fout.close()
</code></pre>
<pre class="bash"><code>
<!-- from misc_helper import * -->
<!-- dic_IND = {} -->
<!-- dic_BAM = {} -->
<!-- for ln in open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/file_id_mapping.txt"): -->
<!-- bam, IND = ln.split() -->
<!-- IND = IND.strip() -->
<!-- dic_IND[bam] = IND -->
<!-- if IND not in dic_BAM: -->
<!-- dic_BAM[IND] = [] -->
<!-- dic_BAM[IND].append(bam) -->
<!-- INDs = dic_BAM.keys() -->
<!-- print INDs, len(INDs) -->
<!-- fout = open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/small.test.counts.txt",'w') -->
<!-- fout.write(" ".join(['chrom']+INDs)+'\n') -->
<!-- for dic in stream_table(open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/small.test.txt"),' '): -->
<!-- print(dic) -->
<!-- buf = [dic['chrom']] -->
<!-- for ind in INDs: -->
<!-- T,B = 0, 0 -->
<!-- for bam in dic_BAM[ind]: -->
<!-- t,b =dic[bam].split('/') -->
<!-- T+=int(t) -->
<!-- B+=int(b) -->
<!-- print ind, t,b -->
<!-- buf.append("%d/%d"%(T,B)) -->
<!-- fout.write(" ".join(buf)+'\n') -->
<!-- fout.close() --></code></pre>
<p>I dont think this is the right script. It looks like the DGN_perind.counts.gz file is already in the x/y format. I need to look more into this script or write my own. I will def need dictionaries for the genes and for the individuals.</p>
<p>makePhenoRefSeqPeaks.py</p>
<pre class="bash"><code>
#PYTHON 3
dic_IND = {}
dic_BAM = {}
for ln in open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/file_id_mapping.txt"):
bam, IND = ln.split()
IND = IND.strip()
dic_IND[bam] = IND
if IND not in dic_BAM:
dic_BAM[IND] = []
dic_BAM[IND].append(bam)
#now I have ind dic with keys as the bam and ind as the values
#I also have a bam dic with ind as the keys and bam as the values
inds=list(dic_BAM.keys()) #list of ind libraries
#list of genes
count_file=open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_fixed.fc", "r")
genes=[]
for line , i in enumerate(count_file):
if line > 1:
i_list=i.split()
id=i_list[0]
id_list=id.split(":")
gene=id_list[5]
if gene not in genes:
genes.append(gene)
#make the ind and gene dic
dic_dub={}
for g in genes:
dic_dub[g]={}
for i in inds:
dic_dub[g][i]=0
#populate the dictionary
count_file=open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_fixed.fc", "r")
for line, i in enumerate(count_file):
if line > 1:
i_list=i.split()
id=i_list[0]
id_list=id.split(":")
g= id_list[5]
values=list(i_list[6:])
list_list=[]
for ind,val in zip(inds, values):
list_list.append([ind, val])
for num, name in enumerate(list_list):
dic_dub[g][list_list[num][0]] += int(list_list[num][1])
#write the file by acessing the dictionary and putting values in the table ver the value in the dic
fout=open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_pheno.txt","w")
peak=["PeakID"]
fout.write(" ".join(peak + inds) + '\n' )
count_file=open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_fixed.fc", "r")
for line , i in enumerate(count_file):
if line > 1:
i_list=i.split()
id=i_list[0]
id_list=id.split(":")
gene=id_list[5]
buff=[id]
for x,y in zip(i_list[6:], inds):
b=int(dic_dub[gene][y])
t=int(x)
buff.append("%d/%d"%(t,b))
fout.write(" ".join(buff)+ '\n')
fout.close()</code></pre>
<p>run_makePhen.sh</p>
<pre class="bash"><code>#!/bin/bash
#SBATCH --job-name=run_makepheno
#SBATCH --account=pi-yangili1
#SBATCH --time=24:00:00
#SBATCH --output=run_makepheno.out
#SBATCH --error=run_makepheno.err
#SBATCH --partition=broadwl
#SBATCH --mem=12G
#SBATCH --mail-type=END
module load Anaconda3
source activate three-prime-env
python makePhenoRefSeqPeaks.py </code></pre>
<p>Seperate total and nuclear columns. I can run FC seperatly then fix the headers and rerun the makephen file.</p>
<pre class="bash"><code>#!/bin/bash
#SBATCH --job-name=ref_gene_peak_fc_total
#SBATCH --account=pi-yangili1
#SBATCH --time=24:00:00
#SBATCH --output=ref_gene_peak_fc_T.out
#SBATCH --error=ref_gene_peak_fc_T.err
#SBATCH --partition=broadwl
#SBATCH --mem=12G
#SBATCH --mail-type=END
module load Anaconda3
source activate three-prime-env
featureCounts -a /project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm.SAF -F SAF -o /project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_Total.fc /project2/gilad/briana/threeprimeseq/data/sort/*-T-*-sort.bam -s 1
</code></pre>
<pre class="bash"><code>#!/bin/bash
#SBATCH --job-name=ref_gene_peak_fc_nuc
#SBATCH --account=pi-yangili1
#SBATCH --time=24:00:00
#SBATCH --output=ref_gene_peak_fc_N.out
#SBATCH --error=ref_gene_peak_fc_N.err
#SBATCH --partition=broadwl
#SBATCH --mem=12G
#SBATCH --mail-type=END
module load Anaconda3
source activate three-prime-env
featureCounts -a /project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm.SAF -F SAF -o /project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_Nuclear.fc /project2/gilad/briana/threeprimeseq/data/sort/*-N-*-sort.bam -s 1
</code></pre>
<p>Fix the headers: * fix_head_fc_tot.py</p>
<pre class="bash"><code>
infile= open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_Total.fc", "r")
fout = file("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_Total_fixed.fc",'w')
for line, i in enumerate(infile):
if line == 1:
i_list=i.split()
libraries=i_list[:6]
for sample in i_list[6:]:
full = sample.split("/")[7]
samp= full.split("-")[2:4]
lim="_"
samp_st=lim.join(samp)
libraries.append(samp_st)
first_line= "\t".join(libraries)
fout.write(first_line + '\n')
else :
fout.write(i)
fout.close()</code></pre>
<ul>
<li>fix_head_fc_nuc.py</li>
</ul>
<pre class="bash"><code>
infile= open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_Nuclear.fc", "r")
fout = file("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_Nuclear_fixed.fc",'w')
for line, i in enumerate(infile):
if line == 1:
i_list=i.split()
libraries=i_list[:6]
for sample in i_list[6:]:
full = sample.split("/")[7]
samp= full.split("-")[2:4]
lim="_"
samp_st=lim.join(samp)
libraries.append(samp_st)
first_line= "\t".join(libraries)
fout.write(first_line + '\n')
else :
fout.write(i)
fout.close()</code></pre>
<p>Create file IDs:</p>
<p>create_fileid_total.py</p>
<pre class="bash"><code>fout = file("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/file_id_mapping_total.txt",'w')
infile= open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_Total_fixed.fc", "r")
for line, i in enumerate(infile):
if line == 0:
i_list=i.split()
files= i_list[10:-2]
for each in files:
full = each.split("/")[7]
samp= full.split("-")[2:4]
lim="_"
samp_st=lim.join(samp)
outLine= full[:-1] + "\t" + samp_st
fout.write(outLine + "\n")
fout.close()
</code></pre>
<p>create_fileid_nuc.py</p>
<pre class="bash"><code>fout = file("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/file_id_mapping_nuc.txt",'w')
infile= open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_Nuclear_fixed.fc", "r")
for line, i in enumerate(infile):
if line == 0:
i_list=i.split()
files= i_list[10:-2]
for each in files:
full = each.split("/")[7]
samp= full.split("-")[2:4]
lim="_"
samp_st=lim.join(samp)
outLine= full[:-1] + "\t" + samp_st
fout.write(outLine + "\n")
fout.close()
</code></pre>
<p>Make pheno:</p>
<p>makePhenoRefSeqPeaks_Total.py</p>
<pre class="bash"><code>
#PYTHON 3
dic_IND = {}
dic_BAM = {}
for ln in open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/file_id_mapping_total.txt"):
bam, IND = ln.split()
IND = IND.strip()
dic_IND[bam] = IND
if IND not in dic_BAM:
dic_BAM[IND] = []
dic_BAM[IND].append(bam)
#now I have ind dic with keys as the bam and ind as the values
#I also have a bam dic with ind as the keys and bam as the values
inds=list(dic_BAM.keys()) #list of ind libraries
#list of genes
count_file=open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_Total_fixed.fc", "r")
genes=[]
for line , i in enumerate(count_file):
if line > 1:
i_list=i.split()
id=i_list[0]
id_list=id.split(":")
gene=id_list[5]
if gene not in genes:
genes.append(gene)
#make the ind and gene dic
dic_dub={}
for g in genes:
dic_dub[g]={}
for i in inds:
dic_dub[g][i]=0
#populate the dictionary
count_file=open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_Total_fixed.fc", "r")
for line, i in enumerate(count_file):
if line > 1:
i_list=i.split()
id=i_list[0]
id_list=id.split(":")
g= id_list[5]
values=list(i_list[6:])
list_list=[]
for ind,val in zip(inds, values):
list_list.append([ind, val])
for num, name in enumerate(list_list):
dic_dub[g][list_list[num][0]] += int(list_list[num][1])
#write the file by acessing the dictionary and putting values in the table ver the value in the dic
fout=open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_pheno_Total.txt","w")
peak=["PeakID"]
fout.write(" ".join(peak + inds) + '\n' )
count_file=open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_Total_fixed.fc", "r")
for line , i in enumerate(count_file):
if line > 1:
i_list=i.split()
id=i_list[0]
id_list=id.split(":")
gene=id_list[5]
buff=[id]
for x,y in zip(i_list[6:], inds):
b=int(dic_dub[gene][y])
t=int(x)
buff.append("%d/%d"%(t,b))
fout.write(" ".join(buff)+ '\n')
fout.close()</code></pre>
<p>makePhenoRefSeqPeaks_Nuclear.py</p>
<pre class="bash"><code>
#PYTHON 3
dic_IND = {}
dic_BAM = {}
for ln in open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/file_id_mapping_nuc.txt"):
bam, IND = ln.split()
IND = IND.strip()
dic_IND[bam] = IND
if IND not in dic_BAM:
dic_BAM[IND] = []
dic_BAM[IND].append(bam)
#now I have ind dic with keys as the bam and ind as the values
#I also have a bam dic with ind as the keys and bam as the values
inds=list(dic_BAM.keys()) #list of ind libraries
#list of genes
count_file=open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_Nuclear_fixed.fc", "r")
genes=[]
for line , i in enumerate(count_file):
if line > 1:
i_list=i.split()
id=i_list[0]
id_list=id.split(":")
gene=id_list[5]
if gene not in genes:
genes.append(gene)
#make the ind and gene dic
dic_dub={}
for g in genes:
dic_dub[g]={}
for i in inds:
dic_dub[g][i]=0
#populate the dictionary
count_file=open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_Nuclear_fixed.fc", "r")
for line, i in enumerate(count_file):
if line > 1:
i_list=i.split()
id=i_list[0]
id_list=id.split(":")
g= id_list[5]
values=list(i_list[6:])
list_list=[]
for ind,val in zip(inds, values):
list_list.append([ind, val])
for num, name in enumerate(list_list):
dic_dub[g][list_list[num][0]] += int(list_list[num][1])
#write the file by acessing the dictionary and putting values in the table ver the value in the dic
fout=open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_pheno_Nuclear.txt","w")
peak=["PeakID"]
fout.write(" ".join(peak + inds) + '\n' )
count_file=open("/project2/gilad/briana/threeprimeseq/data/filt_peak_refGene_cov/filtered_APApeaks_merged_allchrom_refseqGenes_sm_quant_Nuclear_fixed.fc", "r")
for line , i in enumerate(count_file):
if line > 1:
i_list=i.split()
id=i_list[0]
id_list=id.split(":")
gene=id_list[5]
buff=[id]
for x,y in zip(i_list[6:], inds):
b=int(dic_dub[gene][y])
t=int(x)
buff.append("%d/%d"%(t,b))
fout.write(" ".join(buff)+ '\n')
fout.close()</code></pre>
<p>run the pheno.py scripts.</p>
<p>run_makePhen_sep.sh</p>
<pre class="bash"><code>#!/bin/bash
#SBATCH --job-name=run_makepheno_sep
#SBATCH --account=pi-yangili1
#SBATCH --time=24:00:00
#SBATCH --output=run_makepheno_sep.out
#SBATCH --error=run_makepheno_sep.err
#SBATCH --partition=broadwl
#SBATCH --mem=12G
#SBATCH --mail-type=END
module load Anaconda3
source activate three-prime-env
python makePhenoRefSeqPeaks_Total.py
python makePhenoRefSeqPeaks_Nuclear.py </code></pre>
<div id="session-information" class="section level2">
<h2>Session information</h2>
<pre class="r"><code>sessionInfo()</code></pre>
<pre><code>R version 3.5.1 (2018-07-02)
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/3.5/Resources/lib/libRblas.0.dylib
LAPACK: /Library/Frameworks/R.framework/Versions/3.5/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] workflowr_1.1.1 Rcpp_0.12.18 digest_0.6.15
[4] rprojroot_1.3-2 R.methodsS3_1.7.1 backports_1.1.2
[7] git2r_0.23.0 magrittr_1.5 evaluate_0.11
[10] stringi_1.2.4 whisker_0.3-2 R.oo_1.22.0
[13] R.utils_2.6.0 rmarkdown_1.10 tools_3.5.1
[16] stringr_1.3.1 yaml_2.1.19 compiler_3.5.1
[19] htmltools_0.3.6 knitr_1.20 </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> 1.1.1
</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>