<!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>Expand Smash</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">Expand Smash</h1>
<h4 class="author"><em>Briana Mittleman</em></h4>
<h4 class="date"><em>7/24/2018</em></h4>
</div>
<p><strong>Last updated:</strong> 2018-07-25</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/2d41f11ceda8b51e78e2a040bc3ab99084c228a9" target="_blank">2d41f11</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: data/18486.genecov.txt
Untracked: data/APApeaksYL.total.inbrain.bed
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/gene_cov/
Untracked: data/leafcutter/
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: output/picard/
Untracked: output/plots/
Untracked: output/qual.fig2.pdf
Unstaged changes:
Modified: analysis/dif.iso.usage.leafcutter.Rmd
Modified: analysis/explore.filters.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/2d41f11ceda8b51e78e2a040bc3ab99084c228a9/analysis/expand.smash.Rmd" target="_blank">2d41f11</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-07-25
</td>
<td style="text-align:left;">
add expand smash to index
</td>
</tr>
</tbody>
</table>
</ul>
<p></details></p>
<hr />
<p>I want to run smash on a whole chromosome to see what regions I can do it on to get the whole genome. First I am going to try chromosome 22.</p>
<div id="prepare-data" class="section level2">
<h2>Prepare data</h2>
<p>I want to create a bedgraph for the combined nuclear and total files.</p>
<ul>
<li><p>/project2/gilad/briana/threeprimeseq/data/macs2/TotalBamFiles.sort.bam</p></li>
<li><p>/project2/gilad/briana/threeprimeseq/data/macs2/NuclearBamFiles.bam</p></li>
</ul>
<pre class="bash"><code>#!/bin/bash
#SBATCH --job-name=5gencov_comb
#SBATCH --account=pi-yangili1
#SBATCH --time=24:00:00
#SBATCH --output=5gencov_comb.out
#SBATCH --error=5gencov_com.err
#SBATCH --partition=broadwl
#SBATCH --mem=40G
#SBATCH --mail-type=END
module load Anaconda3
source activate three-prime-env
bedtools genomecov -d -5 -ibam /project2/gilad/briana/threeprimeseq/data/macs2/TotalBamFiles.sort.bam > /project2/gilad/briana/threeprimeseq/data/genomecov/gencov5prime.combinedTotal.bed
bedtools genomecov -d -5 -ibam /project2/gilad/briana/threeprimeseq/data/macs2/NuclearBamFiles.sort.bam > /project2/gilad/briana/threeprimeseq/data/genomecov/gencov5prime.combinedNuclear.bed</code></pre>
<p>I now need to subset the bed files to chr22.</p>
<pre class="bash"><code>#!/bin/bash
#SBATCH --job-name=subset22
#SBATCH --account=pi-yangili1
#SBATCH --time=24:00:00
#SBATCH --output=subset22.out
#SBATCH --error=subset22.err
#SBATCH --partition=broadwl
#SBATCH --mem=40G
#SBATCH --mail-type=END
module load Anaconda3
source activate three-prime-env
awk '$1==22 {print}' /project2/gilad/briana/threeprimeseq/data/genomecov/gencov5prime.combinedNuclear.bed > /project2/gilad/briana/threeprimeseq/data/genomecov_chr22/gencov5prime.combinedNuclear.chr22.bed
awk '$1==22 {print}' /project2/gilad/briana/threeprimeseq/data/genomecov/gencov5prime.combinedTotal.bed > /project2/gilad/briana/threeprimeseq/data/genomecov_chr22/gencov5prime.combinedTotal.chr22.bed</code></pre>
</div>
<div id="run-smash" class="section level2">
<h2>Run smash</h2>
<p>Chromosome 22 is 51304566 bases. I need this to satisfy the <span class="math inline">\(2^{x}\)</span> criteria. I can use the log rule, <span class="math inline">\(log_{2}length=x\)</span></p>
<pre class="r"><code>log2(51304566)</code></pre>
<pre><code>[1] 25.61258</code></pre>
<pre class="r"><code>2^26</code></pre>
<pre><code>[1] 67108864</code></pre>
<pre class="r"><code>zeros_to_add=67108864 -51304566</code></pre>
<p>I will use 2^26, 67108864. This means I need to add 1.580429810^{7} 0s to the matrix. I can do this by making a matrix with the correct number of zeros and row binding it.</p>
<pre class="r"><code>zero_matrix=matrix(0.1, zeros_to_add)</code></pre>
<p>I will write and R script that I can run on the cluster. The file will take in the genomecoverage file and will output the graph and the smash results in a bedgraph format.</p>
<pre class="r"><code>#!/bin/rscripts
# usage: ./run_smash.R gencoverage, outfile_plot, outfile_bedgraph
#this script takes the genomecov file and a name for an output plot (.png) and an output bedgraph (.bg)
#use optparse for management of input arguments I want to be able to imput the 6up nuc file and write out a filter file
#script needs to run outside of conda env. should module load R in bash script when I submit it
library(optparse)
library(dplyr)
library(tidyr)
library(ggplot2)
library(scales)
library(smashr)
option_list = list(
make_option(c("-f", "--file"), action="store", default=NA, type='character',
help="input file"),
make_option(c("-p", "--plot"), action="store", default=NA, type='character',
help="output plot file"),
make_option(c("-o", "--output"), action="store", default=NA, type='character',
help="output file")
)
opt_parser <- OptionParser(option_list=option_list)
opt <- parse_args(opt_parser)
#interrupt execution if no file is supplied
if (is.null(opt$file)){
print_help(opt_parser)
stop("Need input file", call.=FALSE)
}
#Functions for this script
criteria=function(x){
#function takes a number and makes the matrix with 0s
exp=log2(x)
exp_round=ceiling(exp)
zerosadd= 2^exp_round - x
seq_0=rep(0, zerosadd)
return(seq_0)
}
#import bedgraph
names=c("Chr", "Pos", "Count")
cov=read.table(file = opt$file, col.names = names)
chromosome=cov[1,1]
#prepare data by adding 0s
zero_seq=criteria(nrow(cov))
data_vec=as.vector(cov$Count)
data_zero_vec=c(data_vec, zero_seq)
data_zero_matrix=matrix(data_zero_vec, 1, length(data_zero_vec))
#run smash
smash_res=smash.poiss(data_zero_matrix[1,],post.var=TRUE)
#create and save plot
pos=1:length(data_vec)
png(opt$plot)
finalplot=plot(pos,smash_res$est[1:length(data_vec)],type='l',xlab="position",ylab="intensity", main="SMASH results")
dev.off()
#create bedgraph and write it out
bedgraph=cbind(lapply(cov$Chr, function(x) paste("chr", x, sep="")), cov$Pos, cov$Pos + 1, smash_res$est[1:length(data_vec)])
write.table(bedgraph, file=opt$output, quote = F, row.names = F, col.names = F) </code></pre>
<p>To run this I will have to create a batch script similar to the following.</p>
<pre class="bash"><code>#!/bin/bash
#SBATCH --job-name=run.run_smash
#SBATCH --account=pi-yangili1
#SBATCH --time=8:00:00
#SBATCH --output=run_runsmash.out
#SBATCH --error=run_runsmash.err
#SBATCH --partition=broadwl
#SBATCH --mem=20G
#SBATCH --mail-type=END
module load R
Rscript run_smash.R -f /project2/gilad/briana/threeprimeseq/data/genomecov_chr22/gencov5prime.combinedTotal.chr22.bed -p /project2/gilad/briana/threeprimeseq/data/smash.chr22/smooth.combinedTotal.chr22.png -o /project2/gilad/briana/threeprimeseq/data/smash.chr22/smooth.combinedTotal.chr22.bg
</code></pre>
</div>
<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>