<!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>Use cleanUpdTSeq for internal priming</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">Use cleanUpdTSeq for internal priming</h1>
<h4 class="author"><em>Briana Mittleman</em></h4>
<h4 class="date"><em>7/24/2018</em></h4>
</div>
<p><strong>Last updated:</strong> 2018-07-26</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/31118c688b6d5fc5f8fa7a390965b1c557707a50" target="_blank">31118c6</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/clean_peaks/
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/31118c688b6d5fc5f8fa7a390965b1c557707a50/analysis/cleanupdtseq.internalpriming.Rmd" target="_blank">31118c6</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-07-26
</td>
<td style="text-align:left;">
add length and coverage analysis
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/f3eaa0b416677872ab9f982813007c8d5b044768/docs/cleanupdtseq.internalpriming.html" target="_blank">f3eaa0b</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-07-25
</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/be5fac4c31b52fe11818ab0e508be8c8f964ec12/analysis/cleanupdtseq.internalpriming.Rmd" target="_blank">be5fac4</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-07-25
</td>
<td style="text-align:left;">
explore cleanup results
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/3a5a8fe9a053a464ef64ed3c411bdedf82003927/docs/cleanupdtseq.internalpriming.html" target="_blank">3a5a8fe</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-07-25
</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/d8394a3fa4502ca49a5717ec98ae74f48b14734c/analysis/cleanupdtseq.internalpriming.Rmd" target="_blank">d8394a3</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-07-25
</td>
<td style="text-align:left;">
start clean up code analysis
</td>
</tr>
</tbody>
</table>
</ul>
<p></details></p>
<hr />
<p>Install new packages:</p>
<pre class="r"><code>source("https://bioconductor.org/biocLite.R")
biocLite("BSgenome.Hsapiens.UCSC.hg19")</code></pre>
<p>Load Packages:</p>
<pre class="r"><code>library(workflowr)</code></pre>
<pre><code>This is workflowr version 1.1.1
Run ?workflowr for help getting started</code></pre>
<pre class="r"><code>library(cleanUpdTSeq)</code></pre>
<pre><code>Loading required package: BiocGenerics</code></pre>
<pre><code>Loading required package: parallel</code></pre>
<pre><code>
Attaching package: 'BiocGenerics'</code></pre>
<pre><code>The following objects are masked from 'package:parallel':
clusterApply, clusterApplyLB, clusterCall, clusterEvalQ,
clusterExport, clusterMap, parApply, parCapply, parLapply,
parLapplyLB, parRapply, parSapply, parSapplyLB</code></pre>
<pre><code>The following objects are masked from 'package:stats':
IQR, mad, sd, var, xtabs</code></pre>
<pre><code>The following objects are masked from 'package:base':
anyDuplicated, append, as.data.frame, basename, cbind,
colMeans, colnames, colSums, dirname, do.call, duplicated,
eval, evalq, Filter, Find, get, grep, grepl, intersect,
is.unsorted, lapply, lengths, Map, mapply, match, mget, order,
paste, pmax, pmax.int, pmin, pmin.int, Position, rank, rbind,
Reduce, rowMeans, rownames, rowSums, sapply, setdiff, sort,
table, tapply, union, unique, unsplit, which, which.max,
which.min</code></pre>
<pre><code>Loading required package: BSgenome</code></pre>
<pre><code>Loading required package: S4Vectors</code></pre>
<pre><code>Loading required package: stats4</code></pre>
<pre><code>
Attaching package: 'S4Vectors'</code></pre>
<pre><code>The following object is masked from 'package:base':
expand.grid</code></pre>
<pre><code>Loading required package: IRanges</code></pre>
<pre><code>Loading required package: GenomeInfoDb</code></pre>
<pre><code>Loading required package: GenomicRanges</code></pre>
<pre><code>Loading required package: Biostrings</code></pre>
<pre><code>Loading required package: XVector</code></pre>
<pre><code>
Attaching package: 'Biostrings'</code></pre>
<pre><code>The following object is masked from 'package:base':
strsplit</code></pre>
<pre><code>Loading required package: rtracklayer</code></pre>
<pre><code>Loading required package: BSgenome.Drerio.UCSC.danRer7</code></pre>
<pre><code>Loading required package: seqinr</code></pre>
<pre><code>
Attaching package: 'seqinr'</code></pre>
<pre><code>The following object is masked from 'package:Biostrings':
translate</code></pre>
<pre><code>Loading required package: e1071</code></pre>
<pre class="r"><code>library(GenomicRanges)
library(BSgenome.Hsapiens.UCSC.hg19)
library(ggseqlogo)
library(ggplot2)
library(dplyr)</code></pre>
<pre><code>
Attaching package: 'dplyr'</code></pre>
<pre><code>The following object is masked from 'package:seqinr':
count</code></pre>
<pre><code>The following objects are masked from 'package:Biostrings':
collapse, intersect, setdiff, setequal, union</code></pre>
<pre><code>The following object is masked from 'package:XVector':
slice</code></pre>
<pre><code>The following objects are masked from 'package:GenomicRanges':
intersect, setdiff, union</code></pre>
<pre><code>The following object is masked from 'package:GenomeInfoDb':
intersect</code></pre>
<pre><code>The following objects are masked from 'package:IRanges':
collapse, desc, intersect, setdiff, slice, union</code></pre>
<pre><code>The following objects are masked from 'package:S4Vectors':
first, intersect, rename, setdiff, setequal, union</code></pre>
<pre><code>The following objects are masked from 'package:BiocGenerics':
combine, intersect, setdiff, union</code></pre>
<pre><code>The following objects are masked from 'package:stats':
filter, lag</code></pre>
<pre><code>The following objects are masked from 'package:base':
intersect, setdiff, setequal, union</code></pre>
<pre class="r"><code>library(gridExtra)</code></pre>
<pre><code>
Attaching package: 'gridExtra'</code></pre>
<pre><code>The following object is masked from 'package:dplyr':
combine</code></pre>
<pre><code>The following object is masked from 'package:BiocGenerics':
combine</code></pre>
<pre class="r"><code>library(tidyr)</code></pre>
<pre><code>
Attaching package: 'tidyr'</code></pre>
<pre><code>The following object is masked from 'package:S4Vectors':
expand</code></pre>
<div id="clean-peaks" class="section level2">
<h2>Clean Peaks</h2>
<p>I am also going to install cleanUpdTSeq on my midway account because I will want to write scripts using this package that can take in any bedfile and will write out the file with the classification results. I can also have the cutoff option be a parameter that will change.</p>
<p>The test set should have chr, start, end, name, score, strand.</p>
<pre class="r"><code>#!/bin/rscripts
# usage: ./cleanupdtseq.R in_bedfile, outfile, cuttoff
#this script takes a putative peak file, and output file name and a cuttoff for classification and outputs the file with all of the seqs classified.
#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(cleanUpdTSeq)
library(GenomicRanges)
library(BSgenome.Hsapiens.UCSC.hg19)
option_list = list(
make_option(c("-f", "--file"), action="store", default=NA, type='character',
help="input file"),
make_option(c("-o", "--output"), action="store", default=NA, type='character',
help="output file"),
make_option(c("-c", "--cutoff"), action="store", default=NA, type='double',
help="assignment cuttoff")
)
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)
}
#imput file for test data
testSet <- read.table(file = opt$file, sep="\t", header=TRUE)
peaks <- BED2GRangesSeq(testSet, withSeq=FALSE)
#build vector with human genome
testSet.NaiveBayes <- buildFeatureVector(peaks, BSgenomeName=Hsapiens,
upstream=40, downstream=30,
wordSize=6, alphabet=c("ACGT"),
sampleType="unknown",
replaceNAdistance=30,
method="NaiveBayes",
ZeroBasedIndex=1, fetchSeq=TRUE)
#classfy sites with built in classsifer
data(classifier)
testResults <- predictTestSet(testSet.NaiveBayes=testSet.NaiveBayes,
classifier=classifier,
outputFile=NULL,
assignmentCutoff=opt$cutoff)
#write results
write.table(testResults, file=opt$output, quote = F, row.names = F, col.names = T) </code></pre>
<p>I will need to module load R in the bash script that writes this.</p>
<pre class="bash"><code>#!/bin/bash
#SBATCH --job-name=clean_filteredpeakstotal
#SBATCH --account=pi-yangili1
#SBATCH --time=24:00:00
#SBATCH --output=clean_filteredpeakstotal.out
#SBATCH --error=clean_filteredpeakstotal.err
#SBATCH --partition=broadwl
#SBATCH --mem=40G
#SBATCH --mail-type=END
module load R
Rscript cleanupdtseq.R -f /project2/gilad/briana/threeprimeseq/data/clean.peaks/APAfiltered_named.bed -o /project2/gilad/briana/threeprimeseq/data/clean.peaks/clean_APAfilteredTotal.txt -c .5
</code></pre>
<pre class="bash"><code>#add names to bed file with peaks
#awk '{print $1 "\t" $2 "\t" $3 "\t" $1 ":" $2 ":" $3 "\t" $4 "\t" $5 "\t" $6}' APAfiltered.bed > APAfiltered_named.bed
seq 1 199880 > peak.num.txt
paste APAfiltered.bed peak.num.txt | column -s $'\t' -t > temp
awk '{print $1 "\t" $2 "\t" $3 "\t" $7 "\t" $4 "\t" $5 "\t" $6}' temp > APAfiltered_named.bed
</code></pre>
</div>
<div id="characterize-results" class="section level2">
<h2>Characterize results</h2>
<p>This cuttoff results in a move from 199880 to 125825 called sites.</p>
<pre class="r"><code>peaks=read.table("../data/clean_peaks/clean_APAfilteredTotal.txt", header = T, stringsAsFactors = F)</code></pre>
<p>Plot the density of the probabilities. I expect a bimodal distribution.</p>
<pre class="r"><code>ggplot(peaks, aes(probTrue)) + geom_density(fill="blue") + labs(title="Density of Probability Peak is a True APA peak", x="Probability True PAS")</code></pre>
<p><img src="figure/cleanupdtseq.internalpriming.Rmd/unnamed-chunk-7-1.png" width="672" style="display: block; margin: auto;" /></p>
<details> <summary><em>Expand here to see past versions of unnamed-chunk-7-1.png:</em></summary>
<table style="border-collapse:separate; border-spacing:5px;">
<thead>
<tr>
<th style="text-align:left;">
Version
</th>
<th style="text-align:left;">
Author
</th>
<th style="text-align:left;">
Date
</th>
</tr>
</thead>
<tbody>
<tr>
<td style="text-align:left;">
<a href="https://github.com/brimittleman/threeprimeseq/blob/f3eaa0b416677872ab9f982813007c8d5b044768/docs/figure/cleanupdtseq.internalpriming.Rmd/unnamed-chunk-7-1.png" target="_blank">f3eaa0b</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-07-25
</td>
</tr>
</tbody>
</table>
<p></details></p>
<p>Next I want to make logo plots for the upstream sequences seperated by class. I expect to see an overrepresentation of A/T in the upstream of the false samples.</p>
<pre class="r"><code>true_peaks=peaks %>% filter(pred.class==1)
false_peaks=peaks %>% filter(pred.class==0)</code></pre>
<p>I can extract just the upstream seq for each class.</p>
<pre class="r"><code>true_peaks_up=peaks %>% filter(pred.class==1) %>% select(UpstreamSeq)
false_peaks_up= peaks %>% filter(pred.class==0) %>% select(UpstreamSeq)</code></pre>
<div id="sequence-composition" class="section level3">
<h3>Sequence composition</h3>
<pre class="r"><code>trueplot_up=ggseqlogo(true_peaks_up,seq_type='dna', method = 'prob') + labs(x="Base number", title="Upstream Seq: True PAS")
falseplot_up=ggseqlogo(false_peaks_up,seq_type='dna', method = 'prob') + labs(x="Base number", title="Upstream Seq: False PAS")
gridExtra::grid.arrange(trueplot_up,falseplot_up)</code></pre>
<p><img src="figure/cleanupdtseq.internalpriming.Rmd/unnamed-chunk-10-1.png" width="672" style="display: block; margin: auto;" /></p>
<details> <summary><em>Expand here to see past versions of unnamed-chunk-10-1.png:</em></summary>
<table style="border-collapse:separate; border-spacing:5px;">
<thead>
<tr>
<th style="text-align:left;">
Version
</th>
<th style="text-align:left;">
Author
</th>
<th style="text-align:left;">
Date
</th>
</tr>
</thead>
<tbody>
<tr>
<td style="text-align:left;">
<a href="https://github.com/brimittleman/threeprimeseq/blob/f3eaa0b416677872ab9f982813007c8d5b044768/docs/figure/cleanupdtseq.internalpriming.Rmd/unnamed-chunk-10-1.png" target="_blank">f3eaa0b</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-07-25
</td>
</tr>
</tbody>
</table>
<p></details></p>
<p>I can do the same thing for the downstream seq.</p>
<pre class="r"><code>true_peaks_down=peaks %>% filter(pred.class==1) %>% select(DownstreamSeq)
false_peaks_down= peaks %>% filter(pred.class==0) %>% select(DownstreamSeq)
trueplot_down=ggseqlogo(true_peaks_down,seq_type='dna', method = 'prob') + labs(x="Base number", title="Downstream Seq: True PAS")
falseplot_down=ggseqlogo(false_peaks_down,seq_type='dna', method = 'prob') + labs(x="Base number", title="Downstream Seq: False PAS")
gridExtra::grid.arrange(trueplot_down,falseplot_down)</code></pre>
<p><img src="figure/cleanupdtseq.internalpriming.Rmd/unnamed-chunk-11-1.png" width="672" style="display: block; margin: auto;" /></p>
<details> <summary><em>Expand here to see past versions of unnamed-chunk-11-1.png:</em></summary>
<table style="border-collapse:separate; border-spacing:5px;">
<thead>
<tr>
<th style="text-align:left;">
Version
</th>
<th style="text-align:left;">
Author
</th>
<th style="text-align:left;">
Date
</th>
</tr>
</thead>
<tbody>
<tr>
<td style="text-align:left;">
<a href="https://github.com/brimittleman/threeprimeseq/blob/f3eaa0b416677872ab9f982813007c8d5b044768/docs/figure/cleanupdtseq.internalpriming.Rmd/unnamed-chunk-11-1.png" target="_blank">f3eaa0b</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-07-25
</td>
</tr>
</tbody>
</table>
<p></details></p>
</div>
<div id="length-differnces-between-true-and-false-peaks" class="section level3">
<h3>Length differnces between true and false peaks</h3>
<p>I can join all of the information from the original bed with the results using a join by the name.</p>
<pre class="r"><code>names=c("chr", "start", "end", "PeakName", "Cov", "Strand", "score")
YL_peaks=read.table("../data/clean_peaks/APAfiltered_named.bed", col.names = names)</code></pre>
<pre class="r"><code>full_peaks= inner_join(YL_peaks, peaks, by="PeakName") %>% mutate(length=end-start)
full_peaks$pred.class= as.factor(full_peaks$pred.class)</code></pre>
<pre class="r"><code>ggplot(full_peaks, aes(length, group=pred.class, fill=pred.class)) + geom_density(alpha=.4) + scale_x_log10() + labs(title="Peak lengths do not differ by predicted class", x="Length of called Peak") + scale_fill_manual(values=c("red", "blue"), name="Predicted Class", labels=c("False Positive", "True PAS"))</code></pre>
<p><img src="figure/cleanupdtseq.internalpriming.Rmd/unnamed-chunk-14-1.png" width="672" style="display: block; margin: auto;" /></p>
</div>
<div id="coverage-differnces-between-true-and-false-peaks" class="section level3">
<h3>Coverage differnces between true and false peaks</h3>
<pre class="r"><code>ggplot(full_peaks, aes(x=Cov, group=pred.class, fill=pred.class)) + geom_density(alpha=.4) + scale_x_log10() + labs(title="Peak coverage by predicted class", x=" Peak coverage") + scale_fill_manual(values=c("red", "blue"), name="Predicted Class", labels=c("False Positive", "True PAS"))</code></pre>
<p><img src="figure/cleanupdtseq.internalpriming.Rmd/unnamed-chunk-15-1.png" width="672" style="display: block; margin: auto;" /> ```</p>
</div>
</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] stats4 parallel stats graphics grDevices utils datasets
[8] methods base
other attached packages:
[1] bindrcpp_0.2.2 tidyr_0.8.1
[3] gridExtra_2.3 dplyr_0.7.6
[5] ggplot2_3.0.0 ggseqlogo_0.1
[7] BSgenome.Hsapiens.UCSC.hg19_1.4.0 cleanUpdTSeq_1.18.0
[9] e1071_1.6-8 seqinr_3.4-5
[11] BSgenome.Drerio.UCSC.danRer7_1.4.0 BSgenome_1.48.0
[13] rtracklayer_1.40.3 Biostrings_2.48.0
[15] XVector_0.20.0 GenomicRanges_1.32.6
[17] GenomeInfoDb_1.16.0 IRanges_2.14.10
[19] S4Vectors_0.18.3 BiocGenerics_0.26.0
[21] workflowr_1.1.1
loaded via a namespace (and not attached):
[1] Rcpp_0.12.18 lattice_0.20-35
[3] Rsamtools_1.32.2 class_7.3-14
[5] assertthat_0.2.0 rprojroot_1.3-2
[7] digest_0.6.15 R6_2.2.2
[9] plyr_1.8.4 backports_1.1.2
[11] evaluate_0.11 pillar_1.3.0
[13] zlibbioc_1.26.0 rlang_0.2.1
[15] lazyeval_0.2.1 rstudioapi_0.7
[17] whisker_0.3-2 R.utils_2.6.0
[19] R.oo_1.22.0 Matrix_1.2-14
[21] rmarkdown_1.10 labeling_0.3
[23] BiocParallel_1.14.2 stringr_1.3.1
[25] RCurl_1.95-4.11 munsell_0.5.0
[27] DelayedArray_0.6.2 compiler_3.5.1
[29] pkgconfig_2.0.1 htmltools_0.3.6
[31] tidyselect_0.2.4 SummarizedExperiment_1.10.1
[33] tibble_1.4.2 GenomeInfoDbData_1.1.0
[35] matrixStats_0.54.0 XML_3.98-1.12
[37] withr_2.1.2 crayon_1.3.4
[39] GenomicAlignments_1.16.0 MASS_7.3-50
[41] bitops_1.0-6 R.methodsS3_1.7.1
[43] grid_3.5.1 gtable_0.2.0
[45] git2r_0.23.0 magrittr_1.5
[47] scales_0.5.0 stringi_1.2.4
[49] tools_3.5.1 ade4_1.7-11
[51] Biobase_2.40.0 glue_1.3.0
[53] purrr_0.2.5 yaml_2.1.19
[55] colorspace_1.3-2 knitr_1.20
[57] bindr_0.1.1 </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>