<!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="Kaixuan Luo" />
<title>DNase footprint profiles using ENCODE DNase-seq data</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>
<script src="site_libs/navigation-1.1/codefolding.js"></script>
<link href="site_libs/highlightjs-9.12.0/textmate.css" rel="stylesheet" />
<script src="site_libs/highlightjs-9.12.0/highlight.js"></script>
<link href="site_libs/font-awesome-4.5.0/css/font-awesome.min.css" rel="stylesheet" />
<style type="text/css">code{white-space: pre;}</style>
<style type="text/css">
pre:not([class]) {
background-color: white;
}
</style>
<script type="text/javascript">
if (window.hljs) {
hljs.configure({languages: []});
hljs.initHighlightingOnLoad();
if (document.readyState && document.readyState === "complete") {
window.setTimeout(function() { hljs.initHighlighting(); }, 0);
}
}
</script>
<style type="text/css">
h1 {
font-size: 34px;
}
h1.title {
font-size: 38px;
}
h2 {
font-size: 30px;
}
h3 {
font-size: 24px;
}
h4 {
font-size: 18px;
}
h5 {
font-size: 16px;
}
h6 {
font-size: 12px;
}
.table th:not([align]) {
text-align: left;
}
</style>
</head>
<body>
<style type = "text/css">
.main-container {
max-width: 940px;
margin-left: auto;
margin-right: auto;
}
code {
color: inherit;
background-color: rgba(0, 0, 0, 0.04);
}
img {
max-width:100%;
height: auto;
}
.tabbed-pane {
padding-top: 12px;
}
button.code-folding-btn:focus {
outline: none;
}
</style>
<style type="text/css">
/* padding for bootstrap navbar */
body {
padding-top: 51px;
padding-bottom: 40px;
}
/* offset scroll position for anchor links (for fixed navbar) */
.section h1 {
padding-top: 56px;
margin-top: -56px;
}
.section h2 {
padding-top: 56px;
margin-top: -56px;
}
.section h3 {
padding-top: 56px;
margin-top: -56px;
}
.section h4 {
padding-top: 56px;
margin-top: -56px;
}
.section h5 {
padding-top: 56px;
margin-top: -56px;
}
.section h6 {
padding-top: 56px;
margin-top: -56px;
}
</style>
<script>
// manage active state of menu based on current page
$(document).ready(function () {
// active menu anchor
href = window.location.pathname
href = href.substr(href.lastIndexOf('/') + 1)
if (href === "")
href = "index.html";
var menuAnchor = $('a[href="' + href + '"]');
// mark it active
menuAnchor.parent().addClass('active');
// if it's got a parent navbar menu mark it active as well
menuAnchor.closest('li.dropdown').addClass('active');
});
</script>
<div class="container-fluid main-container">
<!-- tabsets -->
<script>
$(document).ready(function () {
window.buildTabsets("TOC");
});
</script>
<!-- code folding -->
<style type="text/css">
.code-folding-btn { margin-bottom: 4px; }
</style>
<script>
$(document).ready(function () {
window.initializeCodeFolding("hide" === "show");
});
</script>
<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">ATAC-seq analysis</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/kevinlkx/ATAC-seq_footprint_analysis">
<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">
<div class="btn-group pull-right">
<button type="button" class="btn btn-default btn-xs dropdown-toggle" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false"><span>Code</span> <span class="caret"></span></button>
<ul class="dropdown-menu" style="min-width: 50px;">
<li><a id="rmd-show-all-code" href="#">Show All Code</a></li>
<li><a id="rmd-hide-all-code" href="#">Hide All Code</a></li>
</ul>
</div>
<h1 class="title toc-ignore">DNase footprint profiles using ENCODE DNase-seq data</h1>
<h4 class="author"><em>Kaixuan Luo</em></h4>
<h4 class="date"><em>7/31/2018</em></h4>
</div>
<p><strong>Last updated:</strong> 2018-08-29</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(20180613)</code> </summary></p>
<p>The command <code>set.seed(20180613)</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/kevinlkx/ATAC-seq_footprint_analysis/tree/2f894eb9b9c93c5fb33c417d4aa7db3d6e996912" target="_blank">2f894eb</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: code_RCC/.DS_Store
Ignored: data/.DS_Store
Untracked files:
Untracked: analysis/ATACseq_footprint_profiles_GGR_Duke.Rmd
Untracked: analysis/ATACseq_footprint_profiles_OliviaGray.Rmd
Untracked: analysis/ATACseq_footprint_profiles_OliviaGray_HAEC.Rmd
Untracked: analysis/ATACseq_preprocessing_pipeline_GGR_hg38.Rmd
Untracked: code_RCC/update_bamnames.R
Untracked: docs/figure/ATACseq_footprint_profiles_GGR_Duke.Rmd/
Untracked: docs/figure/ATACseq_footprint_profiles_OliviaGray.Rmd/
Untracked: docs/figure/ATACseq_footprint_profiles_OliviaGray_HAEC.Rmd/
Untracked: docs/figure/ATACseq_footprint_profiles_smooth.Rmd/
Untracked: workflow_setup.R
Unstaged changes:
Modified: analysis/ATACseq_preprocessing_pipeline.Rmd
Modified: code_RCC/fimo_jaspar_motif_rcc.sh
Modified: code_RCC/genome_coverage_bamToBigwig_GGR_hg38.sh
Modified: code_RCC/get_motif_count_matrices_GGR_hg38.sh
</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/kevinlkx/ATAC-seq_footprint_analysis/blob/2f894eb9b9c93c5fb33c417d4aa7db3d6e996912/analysis/DNase_footprint_profiles_ENCODE.Rmd" target="_blank">2f894eb</a>
</td>
<td style="text-align:left;">
kevinlkx
</td>
<td style="text-align:left;">
2018-08-29
</td>
<td style="text-align:left;">
plot DNase footprint profiles of CTCF and REST using ENCODE data
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/kevinlkx/ATAC-seq_footprint_analysis/0e205934303845949e9352f636cf0da9f8eba69b/docs/DNase_footprint_profiles_ENCODE.html" target="_blank">0e20593</a>
</td>
<td style="text-align:left;">
kevinlkx
</td>
<td style="text-align:left;">
2018-08-29
</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/kevinlkx/ATAC-seq_footprint_analysis/blob/a233f1177ac0ece88d304d8224beeef928fa07b1/analysis/DNase_footprint_profiles_ENCODE.Rmd" target="_blank">a233f11</a>
</td>
<td style="text-align:left;">
kevinlkx
</td>
<td style="text-align:left;">
2018-08-29
</td>
<td style="text-align:left;">
plot DNase footprint profiles of CTCF and REST using ENCODE data
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/kevinlkx/ATAC-seq_footprint_analysis/b182c051faf1139658d4929ecb4a27b2d66980dc/docs/DNase_footprint_profiles_ENCODE.html" target="_blank">b182c05</a>
</td>
<td style="text-align:left;">
kevinlkx
</td>
<td style="text-align:left;">
2018-08-29
</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/kevinlkx/ATAC-seq_footprint_analysis/blob/09836f913cb5f7958e50af47869dd8a2018408c3/analysis/DNase_footprint_profiles_ENCODE.Rmd" target="_blank">09836f9</a>
</td>
<td style="text-align:left;">
kevinlkx
</td>
<td style="text-align:left;">
2018-08-29
</td>
<td style="text-align:left;">
plot DNase footprint profiles of CTCF and REST using ENCODE data
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/kevinlkx/ATAC-seq_footprint_analysis/35c5febbef498dccc388240f29dadafc0474c080/docs/DNase_footprint_profiles_ENCODE.html" target="_blank">35c5feb</a>
</td>
<td style="text-align:left;">
kevinlkx
</td>
<td style="text-align:left;">
2018-08-29
</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/kevinlkx/ATAC-seq_footprint_analysis/blob/f318dd5d9b5748f8abe4c0efda7176a6bd1ff2e5/analysis/DNase_footprint_profiles_ENCODE.Rmd" target="_blank">f318dd5</a>
</td>
<td style="text-align:left;">
kevinlkx
</td>
<td style="text-align:left;">
2018-08-29
</td>
<td style="text-align:left;">
plot DNase footprint profiles of CTCF and REST using ENCODE data
</td>
</tr>
</tbody>
</table>
</ul>
<p></details></p>
<hr />
<div id="functions" class="section level2">
<h2>functions</h2>
<pre class="r"><code>##### Functions #####
## load and combine count matrices
load_combine_counts <- function(tf_name, pwm_name, dir_count_matrix){
cat("Loading count matrices ... \n")
counts_fwd.df <- read.table(paste0(dir_count_matrix, "/", tf_name, "/", pwm_name, "_hg19_dnase_fwdcounts.m.gz"))
counts_rev.df <- read.table(paste0(dir_count_matrix, "/", tf_name, "/", pwm_name, "_hg19_dnase_revcounts.m.gz"))
## the first 5 columns from "bwtool extract" are chr, start, end, name, and the number of data points
counts_fwd.df <- counts_fwd.df[, -c(1:5)]
counts_rev.df <- counts_rev.df[, -c(1:5)]
colnames(counts_fwd.df) <- paste0("fwd", 1:ncol(counts_fwd.df))
colnames(counts_rev.df) <- paste0("rev", 1:ncol(counts_rev.df))
counts_combined.m <- as.matrix(cbind(counts_fwd.df, counts_rev.df))
return(counts_combined.m)
}
## select candidate sites by mapability and PWM score cutoffs
select_sites <- function(sites.df, thresh_mapability=NULL, thresh_PWMscore=NULL, readstats_name=NULL){
# cat("loading sites ...\n")
cat("Select candidate sites \n")
if(!is.null(thresh_mapability) || !is.na(thresh_mapability)){
cat("Select candidate sites with mapability >=", thresh_mapability, "\n")
idx_mapability <- (sites.df[,"mapability"] >= thresh_mapability)
}else{
idx_mapability <- rep(TRUE, nrow(sites.df))
}
if(!is.null(thresh_PWMscore) || !is.na(thresh_PWMscore)){
cat("Select candidate sites with PWM score >=", thresh_PWMscore, "\n")
idx_pwm <- (sites.df[,"pwm_score"] >= thresh_PWMscore)
}else{
idx_pwm <- rep(TRUE, nrow(sites.df))
}
if(!is.null(readstats_name)){
readstats.df <- read.table(readstats_name, header = F)
## if the readstats.df contains chrY, then it means the cell type is male, then the candidate sites should contain chrY,
## otherwise, the cell type is female, then the candidate sites on chrY should be removed.
if( "chrY" %in% readstats.df[,1] ){
cat("include chrY sites \n")
idx_chr <- (sites.df[,1] != "")
}else{
cat("chrY NOT in the bam file, filter out chrY sites \n")
## remove chrY from candidate (motif) sites
idx_chr <- (sites.df[,1] != "chrY")
}
}else{
idx_chr <- rep(TRUE, nrow(sites.df))
}
idx_select <- which(idx_mapability & idx_pwm & idx_chr)
return(idx_select)
}</code></pre>
</div>
<div id="parameters" class="section level2">
<h2>parameters</h2>
<pre class="r"><code>ver_genome <- "hg19"
flank <- 100
thresh_mapability <- 0.8
thresh_PWMscore <- 10
num_top_sites <- 1000 # plot top sites
max_cuts <- 20 # Clip extreme values
dir_data <- "~/Dropbox/research/ATAC_DNase/"</code></pre>
</div>
<div id="ctcf-in-gm12878-cell-type" class="section level2">
<h2>CTCF in GM12878 cell type</h2>
<div id="load-dnase-footprint-data" class="section level3">
<h3>load DNase footprint data</h3>
<pre class="r"><code>cell_type <- "GM12878"
tf_name <- "CTCF"
pwm_name <- "CTCF_MA0139.1_1e-5"
dir_count_matrix <- paste0(dir_data, "/DNase-seq_ENCODE/", cell_type, "/DNaseSeq/DNase_tagcount_matrix/")
dir_sites_chip <- paste0(dir_data, "/DNase-seq_ENCODE/", cell_type, "/ChIPSeq/")
filename_sites <- paste0(dir_sites_chip, "/", "chipseq_", cell_type, "_", pwm_name, "_flank", flank, "_exp1.totalcount")
sites.df <- read.table(filename_sites, header = T, comment.char = "!", stringsAsFactors = F)
sites.df <- sites.df[, c("chr", "start", "end", "site", "pwmScore", "strand", "pValue", "mapability", "ChIP_mean")]
colnames(sites.df) = c("chr", "start", "end", "name", "pwm_score", "strand", "p_value", "mapability", "ChIP")
idx_select <- select_sites(sites.df, thresh_mapability, thresh_PWMscore)</code></pre>
<pre><code>Select candidate sites
Select candidate sites with mapability >= 0.8
Select candidate sites with PWM score >= 10 </code></pre>
<pre class="r"><code>sites.df <- sites.df[idx_select, ]
cat("Number of sites:", nrow(sites.df), "\n")</code></pre>
<pre><code>Number of sites: 54859 </code></pre>
<pre class="r"><code>counts_combined.m <- load_combine_counts(tf_name, pwm_name, dir_count_matrix)</code></pre>
<pre><code>Loading count matrices ... </code></pre>
<pre class="r"><code>counts_combined.m <- counts_combined.m[idx_select,]
## Clip extreme values
counts_combined.m[counts_combined.m > max_cuts] <- max_cuts
cat("Dimension of", dim(counts_combined.m), "\n")</code></pre>
<pre><code>Dimension of 54859 436 </code></pre>
<pre class="r"><code>if(nrow(counts_combined.m) != nrow(sites.df)){
stop("Sites not matched!")
}</code></pre>
</div>
<div id="plot-footprint-profiles-of-highest-occupancy" class="section level3">
<h3>plot footprint profiles of highest occupancy</h3>
<pre class="r"><code>order_selected <- order(sites.df$ChIP, decreasing = T)[1:num_top_sites]
counts_selected.m <- counts_combined.m[order_selected,]
counts_profile <- apply(counts_selected.m, 2, mean)
par(mfrow = c(1,2))
counts <- counts_profile[1:(length(counts_profile)/2)]
plot(counts, type = "l", col = "blue", xlab = "Relative position (bp)", ylab = "Average counts",
main = "", xaxt = "n")
mtext(text = paste(tf_name, cell_type, "forward strand"), side = 3, line = 1, cex = 1)
axis(1,at=c(1, flank+1, length(counts)-flank, length(counts)), labels=c(-flank, '','' ,flank),
cex.axis = 1, tck=-0.03, tick = T, cex = 1)
counts <- counts_profile[(length(counts_profile)/2+1): length(counts_profile)]
plot(counts, type = "l", col = "red", xlab = "Relative position (bp)", ylab = "Average counts",
main = "", xaxt = "n")
mtext(text = paste(tf_name, cell_type, "reverse strand"), side = 3, line = 1, cex = 1)
axis(1,at=c(1, flank+1, length(counts)-flank, length(counts)), labels=c(-flank, '','' ,flank),
cex.axis = 1, tck=-0.03, tick = T, cex = 1)</code></pre>
<p><img src="figure/DNase_footprint_profiles_ENCODE.Rmd/unnamed-chunk-4-1.png" width="672" style="display: block; margin: auto;" /></p>
<details> <summary><em>Expand here to see past versions of unnamed-chunk-4-1.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/kevinlkx/ATAC-seq_footprint_analysis/blob/35c5febbef498dccc388240f29dadafc0474c080/docs/figure/DNase_footprint_profiles_ENCODE.Rmd/unnamed-chunk-4-1.png" target="_blank">35c5feb</a>
</td>
<td style="text-align:left;">
kevinlkx
</td>
<td style="text-align:left;">
2018-08-29
</td>
</tr>
</tbody>
</table>
<p></details></p>
<pre class="r"><code>## save counts matrix
rds_name <- paste0(dir_data, "/DNase-seq_ENCODE/", cell_type, "/DNaseSeq/DNase_tagcount_matrix/", tf_name, "/",
pwm_name, "_hg19_dnase_fwdcounts_selected_sites.rds")
saveRDS(counts_selected.m, rds_name)</code></pre>
</div>
<div id="plot-footprint-profiles-of-most-accessible-sites" class="section level3">
<h3>plot footprint profiles of most accessible sites</h3>
<pre class="r"><code>order_selected <- order(rowSums(counts_combined.m), decreasing = T)[1:num_top_sites]
counts_selected.m <- counts_combined.m[order_selected,]
counts_profile <- apply(counts_selected.m, 2, mean)
par(mfrow = c(1,2))
counts <- counts_profile[1:(length(counts_profile)/2)]
plot(counts, type = "l", col = "blue", xlab = "Relative position (bp)", ylab = "Average counts",
main = "", xaxt = "n")
mtext(text = paste(tf_name, cell_type, "forward strand"), side = 3, line = 1, cex = 1)
axis(1,at=c(1, flank+1, length(counts)-flank, length(counts)), labels=c(-flank, '','' ,flank),
cex.axis = 1, tck=-0.03, tick = T, cex = 1)
counts <- counts_profile[(length(counts_profile)/2+1): length(counts_profile)]
plot(counts, type = "l", col = "red", xlab = "Relative position (bp)", ylab = "Average counts",
main = "", xaxt = "n")
mtext(text = paste(tf_name, cell_type, "reverse strand"), side = 3, line = 1, cex = 1)
axis(1,at=c(1, flank+1, length(counts)-flank, length(counts)), labels=c(-flank, '','' ,flank),
cex.axis = 1, tck=-0.03, tick = T, cex = 1)</code></pre>
<p><img src="figure/DNase_footprint_profiles_ENCODE.Rmd/unnamed-chunk-5-1.png" width="672" style="display: block; margin: auto;" /></p>
<details> <summary><em>Expand here to see past versions of unnamed-chunk-5-1.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/kevinlkx/ATAC-seq_footprint_analysis/blob/35c5febbef498dccc388240f29dadafc0474c080/docs/figure/DNase_footprint_profiles_ENCODE.Rmd/unnamed-chunk-5-1.png" target="_blank">35c5feb</a>
</td>
<td style="text-align:left;">
kevinlkx
</td>
<td style="text-align:left;">
2018-08-29
</td>
</tr>
</tbody>
</table>
<p></details></p>
</div>
</div>
<div id="ctcf-in-k562-cell-type" class="section level2">
<h2>CTCF in K562 cell type</h2>
<div id="load-dnase-footprint-data-1" class="section level3">
<h3>load DNase footprint data</h3>
<pre class="r"><code>cell_type <- "K562"
tf_name <- "CTCF"
pwm_name <- "CTCF_MA0139.1_1e-5"
dir_count_matrix <- paste0(dir_data, "/DNase-seq_ENCODE/", cell_type, "/DNaseSeq/DNase_tagcount_matrix/")
dir_sites_chip <- paste0(dir_data, "/DNase-seq_ENCODE/", cell_type, "/ChIPSeq/")
filename_sites <- paste0(dir_sites_chip, "/", "chipseq_", cell_type, "_", pwm_name, "_flank", flank, "_exp1.totalcount")
sites.df <- read.table(filename_sites, header = T, comment.char = "!", stringsAsFactors = F)
sites.df <- sites.df[, c("chr", "start", "end", "site", "pwmScore", "strand", "pValue", "mapability", "ChIP_mean")]
colnames(sites.df) = c("chr", "start", "end", "name", "pwm_score", "strand", "p_value", "mapability", "ChIP")
idx_select <- select_sites(sites.df, thresh_mapability, thresh_PWMscore)</code></pre>
<pre><code>Select candidate sites
Select candidate sites with mapability >= 0.8
Select candidate sites with PWM score >= 10 </code></pre>
<pre class="r"><code>sites.df <- sites.df[idx_select, ]
cat("Number of sites:", nrow(sites.df), "\n")</code></pre>
<pre><code>Number of sites: 54859 </code></pre>
<pre class="r"><code>counts_combined.m <- load_combine_counts(tf_name, pwm_name, dir_count_matrix)</code></pre>
<pre><code>Loading count matrices ... </code></pre>
<pre class="r"><code>counts_combined.m <- counts_combined.m[idx_select,]
## Clip extreme values
counts_combined.m[counts_combined.m > max_cuts] <- max_cuts
cat("Dimension of", dim(counts_combined.m), "\n")</code></pre>
<pre><code>Dimension of 54859 436 </code></pre>
<pre class="r"><code>if(nrow(counts_combined.m) != nrow(sites.df)){
stop("Sites not matched!")
}</code></pre>
</div>
<div id="plot-footprint-profiles-of-highest-occupancy-sites" class="section level3">
<h3>plot footprint profiles of highest occupancy sites</h3>
<pre class="r"><code>order_selected <- order(sites.df$ChIP, decreasing = T)[1:num_top_sites]
counts_selected.m <- counts_combined.m[order_selected,]
counts_profile <- apply(counts_selected.m, 2, mean)
par(mfrow = c(1,2))
counts <- counts_profile[1:(length(counts_profile)/2)]
plot(counts, type = "l", col = "blue", xlab = "Relative position (bp)", ylab = "Average counts",
main = "", xaxt = "n")
mtext(text = paste(tf_name, cell_type, "forward strand"), side = 3, line = 1, cex = 1)
axis(1,at=c(1, flank+1, length(counts)-flank, length(counts)), labels=c(-flank, '','' ,flank),
cex.axis = 1, tck=-0.03, tick = T, cex = 1)
counts <- counts_profile[(length(counts_profile)/2+1): length(counts_profile)]
plot(counts, type = "l", col = "red", xlab = "Relative position (bp)", ylab = "Average counts",
main = "", xaxt = "n")
mtext(text = paste(tf_name, cell_type, "reverse strand"), side = 3, line = 1, cex = 1)
axis(1,at=c(1, flank+1, length(counts)-flank, length(counts)), labels=c(-flank, '','' ,flank),
cex.axis = 1, tck=-0.03, tick = T, cex = 1)</code></pre>
<p><img src="figure/DNase_footprint_profiles_ENCODE.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/kevinlkx/ATAC-seq_footprint_analysis/blob/35c5febbef498dccc388240f29dadafc0474c080/docs/figure/DNase_footprint_profiles_ENCODE.Rmd/unnamed-chunk-7-1.png" target="_blank">35c5feb</a>
</td>
<td style="text-align:left;">
kevinlkx
</td>
<td style="text-align:left;">
2018-08-29
</td>
</tr>
</tbody>
</table>
<p></details></p>
<pre class="r"><code>## save counts matrix
rds_name <- paste0(dir_data, "/DNase-seq_ENCODE/", cell_type, "/DNaseSeq/DNase_tagcount_matrix/", tf_name, "/",
pwm_name, "_hg19_dnase_fwdcounts_selected_sites.rds")
saveRDS(counts_selected.m, rds_name)</code></pre>
</div>
</div>
<div id="rest-in-gm12878-cell-type" class="section level2">
<h2>REST in GM12878 cell type</h2>
<div id="load-dnase-footprint-data-2" class="section level3">
<h3>load DNase footprint data</h3>
<pre class="r"><code>cell_type <- "GM12878"
tf_name <- "REST"
pwm_name <- "REST_MA0138.2_1e-5"
dir_count_matrix <- paste0(dir_data, "/DNase-seq_ENCODE/", cell_type, "/DNaseSeq/DNase_tagcount_matrix/")
dir_sites_chip <- paste0(dir_data, "/DNase-seq_ENCODE/", cell_type, "/ChIPSeq/")
filename_sites <- paste0(dir_sites_chip, "/", "chipseq_", cell_type, "_", pwm_name, "_flank", flank, "_exp1.totalcount")
sites.df <- read.table(filename_sites, header = T, comment.char = "!", stringsAsFactors = F)
sites.df <- sites.df[, c("chr", "start", "end", "site", "pwmScore", "strand", "pValue", "mapability", "ChIP_mean")]
colnames(sites.df) = c("chr", "start", "end", "name", "pwm_score", "strand", "p_value", "mapability", "ChIP")
idx_select <- select_sites(sites.df, thresh_mapability, thresh_PWMscore)</code></pre>
<pre><code>Select candidate sites
Select candidate sites with mapability >= 0.8
Select candidate sites with PWM score >= 10 </code></pre>
<pre class="r"><code>sites.df <- sites.df[idx_select, ]
cat("Number of sites:", nrow(sites.df), "\n")</code></pre>
<pre><code>Number of sites: 54533 </code></pre>
<pre class="r"><code>counts_combined.m <- load_combine_counts(tf_name, pwm_name, dir_count_matrix)</code></pre>
<pre><code>Loading count matrices ... </code></pre>
<pre class="r"><code>counts_combined.m <- counts_combined.m[idx_select,]
## Clip extreme values
counts_combined.m[counts_combined.m > max_cuts] <- max_cuts
cat("Dimension of", dim(counts_combined.m), "\n")</code></pre>
<pre><code>Dimension of 54533 440 </code></pre>
<pre class="r"><code>if(nrow(counts_combined.m) != nrow(sites.df)){
stop("Sites not matched!")
}</code></pre>
</div>
<div id="plot-footprint-profiles-of-highest-occupancy-sites-1" class="section level3">
<h3>plot footprint profiles of highest occupancy sites</h3>
<pre class="r"><code>order_selected <- order(sites.df$ChIP, decreasing = T)[1:num_top_sites]
counts_selected.m <- counts_combined.m[order_selected,]
counts_profile <- apply(counts_selected.m, 2, mean)
par(mfrow = c(1,2))
counts <- counts_profile[1:(length(counts_profile)/2)]
plot(counts, type = "l", col = "blue", xlab = "Relative position (bp)", ylab = "Average counts",
main = "", xaxt = "n")
mtext(text = paste(tf_name, cell_type, "forward strand"), side = 3, line = 1, cex = 1)
axis(1,at=c(1, flank+1, length(counts)-flank, length(counts)), labels=c(-flank, '','' ,flank),
cex.axis = 1, tck=-0.03, tick = T, cex = 1)
counts <- counts_profile[(length(counts_profile)/2+1): length(counts_profile)]
plot(counts, type = "l", col = "red", xlab = "Relative position (bp)", ylab = "Average counts",
main = "", xaxt = "n")
mtext(text = paste(tf_name, cell_type, "reverse strand"), side = 3, line = 1, cex = 1)
axis(1,at=c(1, flank+1, length(counts)-flank, length(counts)), labels=c(-flank, '','' ,flank),
cex.axis = 1, tck=-0.03, tick = T, cex = 1)</code></pre>
<p><img src="figure/DNase_footprint_profiles_ENCODE.Rmd/unnamed-chunk-9-1.png" width="672" style="display: block; margin: auto;" /></p>
<details> <summary><em>Expand here to see past versions of unnamed-chunk-9-1.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/kevinlkx/ATAC-seq_footprint_analysis/blob/0e205934303845949e9352f636cf0da9f8eba69b/docs/figure/DNase_footprint_profiles_ENCODE.Rmd/unnamed-chunk-9-1.png" target="_blank">0e20593</a>
</td>
<td style="text-align:left;">
kevinlkx
</td>
<td style="text-align:left;">
2018-08-29
</td>
</tr>
</tbody>
</table>
<p></details></p>
<pre class="r"><code>## save counts matrix
rds_name <- paste0(dir_data, "/DNase-seq_ENCODE/", cell_type, "/DNaseSeq/DNase_tagcount_matrix/", tf_name, "/",
pwm_name, "_hg19_dnase_fwdcounts_selected_sites.rds")
saveRDS(counts_selected.m, rds_name)</code></pre>
</div>
<div id="plot-footprint-profiles-of-most-accessible-sites-1" class="section level3">
<h3>plot footprint profiles of most accessible sites</h3>
<pre class="r"><code>order_selected <- order(rowSums(counts_combined.m), decreasing = T)[1:num_top_sites]
counts_selected.m <- counts_combined.m[order_selected,]
counts_profile <- apply(counts_selected.m, 2, mean)
par(mfrow = c(1,2))
counts <- counts_profile[1:(length(counts_profile)/2)]
plot(counts, type = "l", col = "blue", xlab = "Relative position (bp)", ylab = "Average counts",
main = "", xaxt = "n")
mtext(text = paste(tf_name, cell_type, "forward strand"), side = 3, line = 1, cex = 1)
axis(1,at=c(1, flank+1, length(counts)-flank, length(counts)), labels=c(-flank, '','' ,flank),
cex.axis = 1, tck=-0.03, tick = T, cex = 1)
counts <- counts_profile[(length(counts_profile)/2+1): length(counts_profile)]
plot(counts, type = "l", col = "red", xlab = "Relative position (bp)", ylab = "Average counts",
main = "", xaxt = "n")
mtext(text = paste(tf_name, cell_type, "reverse strand"), side = 3, line = 1, cex = 1)
axis(1,at=c(1, flank+1, length(counts)-flank, length(counts)), labels=c(-flank, '','' ,flank),
cex.axis = 1, tck=-0.03, tick = T, cex = 1)</code></pre>
<p><img src="figure/DNase_footprint_profiles_ENCODE.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/kevinlkx/ATAC-seq_footprint_analysis/blob/0e205934303845949e9352f636cf0da9f8eba69b/docs/figure/DNase_footprint_profiles_ENCODE.Rmd/unnamed-chunk-10-1.png" target="_blank">0e20593</a>
</td>
<td style="text-align:left;">
kevinlkx
</td>
<td style="text-align:left;">
2018-08-29
</td>
</tr>
<tr>
<td style="text-align:left;">
<a href="https://github.com/kevinlkx/ATAC-seq_footprint_analysis/blob/35c5febbef498dccc388240f29dadafc0474c080/docs/figure/DNase_footprint_profiles_ENCODE.Rmd/unnamed-chunk-10-1.png" target="_blank">35c5feb</a>
</td>
<td style="text-align:left;">
kevinlkx
</td>
<td style="text-align:left;">
2018-08-29
</td>
</tr>
</tbody>
</table>
<p></details></p>
</div>
</div>
<div id="rest-in-k562-cell-type" class="section level2">
<h2>REST in K562 cell type</h2>
<div id="load-dnase-footprint-data-3" class="section level3">
<h3>load DNase footprint data</h3>
<pre class="r"><code>cell_type <- "K562"
tf_name <- "REST"
pwm_name <- "REST_MA0138.2_1e-5"
dir_count_matrix <- paste0(dir_data, "/DNase-seq_ENCODE/", cell_type, "/DNaseSeq/DNase_tagcount_matrix/")
dir_sites_chip <- paste0(dir_data, "/DNase-seq_ENCODE/", cell_type, "/ChIPSeq/")
filename_sites <- paste0(dir_sites_chip, "/", "chipseq_", cell_type, "_", pwm_name, "_flank", flank, "_exp1.totalcount")
sites.df <- read.table(filename_sites, header = T, comment.char = "!", stringsAsFactors = F)
sites.df <- sites.df[, c("chr", "start", "end", "site", "pwmScore", "strand", "pValue", "mapability", "ChIP_mean")]
colnames(sites.df) = c("chr", "start", "end", "name", "pwm_score", "strand", "p_value", "mapability", "ChIP")
idx_select <- select_sites(sites.df, thresh_mapability, thresh_PWMscore)</code></pre>
<pre><code>Select candidate sites
Select candidate sites with mapability >= 0.8
Select candidate sites with PWM score >= 10 </code></pre>
<pre class="r"><code>sites.df <- sites.df[idx_select, ]
cat("Number of sites:", nrow(sites.df), "\n")</code></pre>
<pre><code>Number of sites: 54533 </code></pre>
<pre class="r"><code>counts_combined.m <- load_combine_counts(tf_name, pwm_name, dir_count_matrix)</code></pre>
<pre><code>Loading count matrices ... </code></pre>
<pre class="r"><code>counts_combined.m <- counts_combined.m[idx_select,]
## Clip extreme values
counts_combined.m[counts_combined.m > max_cuts] <- max_cuts
cat("Dimension of", dim(counts_combined.m), "\n")</code></pre>
<pre><code>Dimension of 54533 440 </code></pre>
<pre class="r"><code>if(nrow(counts_combined.m) != nrow(sites.df)){
stop("Sites not matched!")
}</code></pre>
</div>
<div id="plot-footprint-profiles-of-highest-occupancy-sites-2" class="section level3">
<h3>plot footprint profiles of highest occupancy sites</h3>
<pre class="r"><code>order_selected <- order(sites.df$ChIP, decreasing = T)[1:num_top_sites]
counts_selected.m <- counts_combined.m[order_selected,]
counts_profile <- apply(counts_selected.m, 2, mean)
par(mfrow = c(1,2))
counts <- counts_profile[1:(length(counts_profile)/2)]
plot(counts, type = "l", col = "blue", xlab = "Relative position (bp)", ylab = "Average counts",
main = "", xaxt = "n")
mtext(text = paste(tf_name, cell_type, "forward strand"), side = 3, line = 1, cex = 1)
axis(1,at=c(1, flank+1, length(counts)-flank, length(counts)), labels=c(-flank, '','' ,flank),
cex.axis = 1, tck=-0.03, tick = T, cex = 1)
counts <- counts_profile[(length(counts_profile)/2+1): length(counts_profile)]
plot(counts, type = "l", col = "red", xlab = "Relative position (bp)", ylab = "Average counts",
main = "", xaxt = "n")
mtext(text = paste(tf_name, cell_type, "reverse strand"), side = 3, line = 1, cex = 1)
axis(1,at=c(1, flank+1, length(counts)-flank, length(counts)), labels=c(-flank, '','' ,flank),
cex.axis = 1, tck=-0.03, tick = T, cex = 1)</code></pre>
<p><img src="figure/DNase_footprint_profiles_ENCODE.Rmd/unnamed-chunk-12-1.png" width="672" style="display: block; margin: auto;" /></p>
<details> <summary><em>Expand here to see past versions of unnamed-chunk-12-1.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/kevinlkx/ATAC-seq_footprint_analysis/blob/0e205934303845949e9352f636cf0da9f8eba69b/docs/figure/DNase_footprint_profiles_ENCODE.Rmd/unnamed-chunk-12-1.png" target="_blank">0e20593</a>
</td>
<td style="text-align:left;">
kevinlkx
</td>
<td style="text-align:left;">
2018-08-29
</td>
</tr>
</tbody>
</table>
<p></details></p>
<pre class="r"><code>## save counts matrix
rds_name <- paste0(dir_data, "/DNase-seq_ENCODE/", cell_type, "/DNaseSeq/DNase_tagcount_matrix/", tf_name, "/",
pwm_name, "_hg19_dnase_fwdcounts_selected_sites.rds")
saveRDS(counts_selected.m, rds_name)</code></pre>
</div>
</div>
<div id="session-information" class="section level2">
<h2>Session information</h2>
<pre class="r"><code>sessionInfo()</code></pre>
<pre><code>R version 3.4.3 (2017-11-30)
Platform: x86_64-apple-darwin15.6.0 (64-bit)
Running under: macOS High Sierra 10.13.6
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] workflowr_1.1.1 Rcpp_0.12.16 digest_0.6.15
[4] rprojroot_1.3-2 R.methodsS3_1.7.1 backports_1.1.2
[7] git2r_0.21.0 magrittr_1.5 evaluate_0.10.1
[10] stringi_1.1.7 whisker_0.3-2 R.oo_1.22.0
[13] R.utils_2.6.0 rmarkdown_1.9 tools_3.4.3
[16] stringr_1.3.0 yaml_2.1.18 compiler_3.4.3
[19] htmltools_0.3.6 knitr_1.20 </code></pre>
</div>
<!-- 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>