<!DOCTYPE html>

<html xmlns="http://www.w3.org/1999/xhtml">

<head>

<meta charset="utf-8" />
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta name="generator" content="pandoc" />


<meta name="author" content="Briana Mittleman" />

<meta name="date" content="2018-10-26" />

<title>apaQTL GWAS overlap</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">apaQTL GWAS overlap</h1>
<h4 class="author"><em>Briana Mittleman</em></h4>
<h4 class="date"><em>10/26/2018</em></h4>

</div>


<p><strong>Last updated:</strong> 2018-11-15</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/7960cbb6bc2a5df2fd758d4885351146e2627e4a" target="_blank">7960cbb</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:    data/.DS_Store
    Ignored:    output/.DS_Store

Untracked files:
    Untracked:  KalistoAbundance18486.txt
    Untracked:  analysis/ncbiRefSeq_sm.sort.mRNA.bed
    Untracked:  analysis/snake.config.notes.Rmd
    Untracked:  analysis/verifyBAM.Rmd
    Untracked:  data/18486.genecov.txt
    Untracked:  data/APApeaksYL.total.inbrain.bed
    Untracked:  data/ChromHmmOverlap/
    Untracked:  data/GM12878.chromHMM.bed
    Untracked:  data/GM12878.chromHMM.txt
    Untracked:  data/LocusZoom/
    Untracked:  data/NuclearApaQTLs.txt
    Untracked:  data/PeaksUsed/
    Untracked:  data/RNAkalisto/
    Untracked:  data/TotalApaQTLs.txt
    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/apaExamp/
    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/comb_map_stats_39ind.csv
    Untracked:  data/combined_reads_mapped_three_prime_seq.csv
    Untracked:  data/diff_iso_trans/
    Untracked:  data/ensemble_to_genename.txt
    Untracked:  data/example_gene_peakQuant/
    Untracked:  data/filtered_APApeaks_merged_allchrom_refseqTrans.closest2End.bed
    Untracked:  data/filtered_APApeaks_merged_allchrom_refseqTrans.closest2End.noties.bed
    Untracked:  data/first50lines_closest.txt
    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/mol_overlap/
    Untracked:  data/mol_pheno/
    Untracked:  data/nom_QTL/
    Untracked:  data/nom_QTL_opp/
    Untracked:  data/nom_QTL_trans/
    Untracked:  data/nuc6up/
    Untracked:  data/other_qtls/
    Untracked:  data/peakPerRefSeqGene/
    Untracked:  data/perm_QTL/
    Untracked:  data/perm_QTL_opp/
    Untracked:  data/perm_QTL_trans/
    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/39indQC.Rmd
    Modified:   analysis/cleanupdtseq.internalpriming.Rmd
    Modified:   analysis/coloc_apaQTLs_protQTLs.Rmd
    Modified:   analysis/dif.iso.usage.leafcutter.Rmd
    Modified:   analysis/diff_iso_pipeline.Rmd
    Modified:   analysis/explore.filters.Rmd
    Modified:   analysis/flash2mash.Rmd
    Modified:   analysis/overlapMolQTL.Rmd
    Modified:   analysis/overlap_qtls.Rmd
    Modified:   analysis/peakOverlap_oppstrand.Rmd
    Modified:   analysis/pheno.leaf.comb.Rmd
    Modified:   analysis/swarmPlots_QTLs.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/7960cbb6bc2a5df2fd758d4885351146e2627e4a/analysis/apaQTLoverlapGWAS.Rmd" target="_blank">7960cbb</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-11-15
</td>
<td style="text-align:left;">
new plink call
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/4a4b5c7261b220189f8f2bc433f79618ec4c2bab/docs/apaQTLoverlapGWAS.html" target="_blank">4a4b5c7</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-11-12
</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/89b780f6c7117e4f7ec14e1e19ed95c11e65d34b/analysis/apaQTLoverlapGWAS.Rmd" target="_blank">89b780f</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-11-12
</td>
<td style="text-align:left;">
add analysis of hits
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/7462a2d18003bfe95950899be69da183c533c94c/docs/apaQTLoverlapGWAS.html" target="_blank">7462a2d</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-11-09
</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/489bf91806282e31a19f8558e7d18f33eb6af085/analysis/apaQTLoverlapGWAS.Rmd" target="_blank">489bf91</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-11-09
</td>
<td style="text-align:left;">
code for plink r2
</td>
</tr>
<tr>
<td style="text-align:left;">
html
</td>
<td style="text-align:left;">
<a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/0428c8cc7dbe48e523ec661d5a0215e784135d7b/docs/apaQTLoverlapGWAS.html" target="_blank">0428c8c</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-10-29
</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/brimittleman/threeprimeseq/blob/42d0e3d7c7875581d9b5bd1d63dc658b03e21f11/analysis/apaQTLoverlapGWAS.Rmd" target="_blank">42d0e3d</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-10-29
</td>
<td style="text-align:left;">
add gwas overlap to index
</td>
</tr>
</tbody>
</table>
</ul>
<p></details></p>
<hr />
<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(tidyverse)</code></pre>
<pre><code>── Attaching packages ─────────────────────────────────────────────────────────────────────────── tidyverse 1.2.1 ──</code></pre>
<pre><code>✔ ggplot2 3.0.0     ✔ purrr   0.2.5
✔ tibble  1.4.2     ✔ dplyr   0.7.6
✔ tidyr   0.8.1     ✔ stringr 1.3.1
✔ readr   1.1.1     ✔ forcats 0.3.0</code></pre>
<pre><code>── Conflicts ────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()</code></pre>
<pre class="r"><code>library(cowplot)</code></pre>
<pre><code>
Attaching package: &#39;cowplot&#39;</code></pre>
<pre><code>The following object is masked from &#39;package:ggplot2&#39;:

    ggsave</code></pre>
<p>In this analysis I want to see if APAqtls show up in the GWAS catelog. I then want to see if they explain different signal then overlappnig the eQTLs.</p>
<p>I can use my significant snp bed file from /project2/gilad/briana/threeprimeseq/data/perm_APAqtl_trans/sigSnps to overlap with the GWAS catelog. First I can look at direct location then I will use an LD cutoff to colocalize.</p>
<ul>
<li>/project2/gilad/briana/threeprimeseq/data/perm_APAqtl_trans/sigSnps/ApaQTLsignificantSnps_10percFDR_Nuclear.sort.bed</li>
<li>/project2/gilad/briana/threeprimeseq/data/perm_APAqtl_trans/sigSnps/ApaQTLsignificantSnps_10percFDR_Total.sort.bed</li>
</ul>
<p>The downloaded GWAS catalog from the UCSD table browser.</p>
<ul>
<li>/project2/gilad/briana/genome_anotation_data/hg19GwasCatalog.txt</li>
</ul>
<p>I will make this into a bed format to use with pybedtools.</p>
<p>-Chrom -start -end -name -score</p>
<pre class="bash"><code>fin=open(&quot;&quot;/project2/gilad/briana/genome_anotation_data/hg19GwasCatalog.txt&quot;, &quot;r&quot;)
fout=open(&quot;/project2/gilad/briana/genome_anotation_data/hg19GwasCatalog.bed&quot;,&quot;w&quot;)

for num, ln in enumerate(fin):
  if num &gt; 0: 
    line=ln.split(&quot;\t&quot;)
    id_list=[line[4],line[5], line[14]]
    start=int(line[2])
    end=int(line[3])
    id=&quot;:&quot;.join(id_list)
    chr=line[1][3:]
    pval=line[16]
    fout.write(&quot;%s\t%d\t%d\t%s\t%s\n&quot;%(chr,start, end, id, pval)
fout.close() 
    </code></pre>
<p>Pybedtools to intersect my snps with catelog /project2/gilad/briana/threeprimeseq/data/GWAS_overlap</p>
<p>output dir:</p>
<pre class="bash"><code>import pybedtools
gwas=pybedtools.BedTool(&quot;/project2/gilad/briana/genome_anotation_data/hg19GwasCatalog.sort.bed&quot;)
nuc=pybedtools.BedTool(&quot;/project2/gilad/briana/threeprimeseq/data/perm_APAqtl_trans/sigSnps/ApaQTLsignificantSnps_10percFDR_Nuclear.sort.bed&quot;)
tot=pybedtools.BedTool(&quot;/project2/gilad/briana/threeprimeseq/data/perm_APAqtl_trans/sigSnps/ApaQTLsignificantSnps_10percFDR_Total.sort.bed&quot;) 

nucOverGWAS=nuc.intersect(gwas, wa=True,wb=True)
totOverGWAS=tot.intersect(gwas,wa=True, wb=True)

#this only results in one overlap:  
nucOverGWAS.saveas(&quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/nucFDR10overlapGWAS.txt&quot;)
</code></pre>
<p><em>Problem: I see this snp but it is assoicated with a different gene. I need to think about gene and snp overlap. </em></p>
<p>I can see if this snp is an eqtl.</p>
<p>16:30482494</p>
<pre class="r"><code>eqtl=read.table(file = &quot;../data/other_qtls/fastqtl_qqnorm_RNAseq_phase2.fixed.perm.out&quot;)
eqtl_g= read.table(&quot;../data/other_qtls/fastqtl_qqnorm_RNAseqGeuvadis.fixed.perm.out&quot;)</code></pre>
<p>This snp is not in either of these files. I will check for them in the nominal results.</p>
<pre class="bash"><code>grep 16:30482494   /project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_RNAseq_phase2.fixed.nominal.out


grep 16:30482494   /project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_RNAseqGeuvadis.fixed.nominal.out
</code></pre>
<div id="ld-structure" class="section level2">
<h2>LD structure</h2>
<p><a href="https://vcftools.github.io/man_latest.html" class="uri">https://vcftools.github.io/man_latest.html</a> –vcf (vcf file) –geno-r2 –out (prefix) vcf tools is on midway 2 “module load vcftools”</p>
<p>I can use the snp files I created for the chromHMM analysis.</p>
<ul>
<li>/project2/gilad/briana/threeprimeseq/data/perm_APAqtl_trans/sigSnps/ApaQTLsignificantSnps_10percFDR_Total.sort.bed</li>
<li>/project2/gilad/briana/threeprimeseq/data/perm_APAqtl_trans/sigSnp/ApaQTLsignificantSnps_10percFDR_Nuclear.sort.bed</li>
</ul>
<p>I can use awk to get the first and third column.</p>
<pre class="bash"><code>awk &#39;{print $1 &quot;:&quot; $3}&#39; /project2/gilad/briana/threeprimeseq/data/perm_APAqtl_trans/sigSnps/ApaQTLsignificantSnps_10percFDR_Nuclear.sort.bed &gt; /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Nuclear.txt

awk &#39;{print $1&quot;:&quot;$3}&#39; /project2/gilad/briana/threeprimeseq/data/perm_APAqtl_trans/sigSnps/ApaQTLsignificantSnps_10percFDR_Total.sort.bed &gt; /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Total.txt</code></pre>
<p>testLD_vcftools_totQTL.sh</p>
<pre class="bash"><code>
#!/bin/bash

#SBATCH --job-name=testLD_vcftools_totQTL.sh
#SBATCH --account=pi-yangili1
#SBATCH --time=36:00:00
#SBATCH --output=testLD_vcftools_totQTL.out
#SBATCH --error=testLD_vcftools_totQTL.err
#SBATCH --partition=broadwl
#SBATCH --mem=16G
#SBATCH --mail-type=END

module load vcftools

vcftools --gzvcf chr1.dose.vcf.gz  --snps  /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Total.txt --out /project2/gilad/briana/YRI_geno_hg19/chr1.totQTL.LD --geno-r2 </code></pre>
<p>/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/TotalApaQTL_LD</p>
<p>/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/NuclearApaQTL_LD</p>
<p>Now run this for all chr in both fractions.</p>
<p>LD_vcftools.sh</p>
<pre class="bash"><code>#!/bin/bash

#SBATCH --job-name=LD_vcftools.sh
#SBATCH --account=pi-yangili1
#SBATCH --time=36:00:00
#SBATCH --output=LD_vcftools.out
#SBATCH --error=rLD_vcftools.err
#SBATCH --partition=broadwl
#SBATCH --mem=30G
#SBATCH --mail-type=END

module load vcftools

for i  in {1..22};
do
vcftools --gzvcf /project2/gilad/briana/YRI_geno_hg19/chr${i}.dose.vcf.gz  --snps  /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Total.txt --out /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/TotalApaQTL_LD/chr${i}.totQTL.LD --geno-r2 --min-r2 .8
done


for i  in {1..22};
do
vcftools --gzvcf /project2/gilad/briana/YRI_geno_hg19/chr${i}.dose.vcf.gz  --snps  /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Nuclear.txt --out /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/NuclearApaQTL_LD/chr${i}.nucQTL.LD --geno-r2 --min-r2 .8
done
</code></pre>
<p>This doesnt give very many more snps. Let me try this with Tony’s vcf files from the larger panel of LCLs.</p>
<p>Try it with the –hap-r2 argument.</p>
<p>LD_vcftools.hap.sh</p>
<pre class="bash"><code>#!/bin/bash

#SBATCH --job-name=LD_vcftools.hap.sh
#SBATCH --account=pi-yangili1
#SBATCH --time=36:00:00
#SBATCH --output=LD_vcftools.hap.out
#SBATCH --error=rLD_vcftools.hap.err
#SBATCH --partition=broadwl
#SBATCH --mem=30G
#SBATCH --mail-type=END

module load vcftools

for i  in {1..22};
do
vcftools --gzvcf /project2/gilad/briana/YRI_geno_hg19/chr${i}.dose.vcf.gz  --snps  /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Total.txt --out /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/TotalApaQTL_LD/chr${i}.totQTL.hap.LD --hap-r2--min-r2 .8
done


for i  in {1..22};
do
vcftools --gzvcf /project2/gilad/briana/YRI_geno_hg19/chr${i}.dose.vcf.gz  --snps  /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Nuclear.txt --out /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/NuclearApaQTL_LD/chr${i}.nucQTL.hap.LD --hap-r2 --min-r2 .8
done
</code></pre>
<p>still not a lot of snps.</p>
<p>testLDGeu_vcftools_totQTL.sh</p>
<pre class="bash"><code>
#!/bin/bash

#SBATCH --job-name=testLDGeu_vcftools_totQTL.sh
#SBATCH --account=pi-yangili1
#SBATCH --time=36:00:00
#SBATCH --output=testLDGeu_vcftools_totQTL.out
#SBATCH --error=testLDGeu_vcftools_totQTL.err
#SBATCH --partition=broadwl
#SBATCH --mem=16G
#SBATCH --mail-type=END

module load vcftools

vcftools --gzvcf /project2/yangili1/LCL/genotypesYRI.gen.txt.gz   --snps  /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Total.txt --out /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/geuvadis.totQTL.LD --geno-r2 </code></pre>
<p>Error: Insufficient sites remained after filtering</p>
<p>vcf2Plink.sh</p>
<pre class="bash"><code>#!/bin/bash

#SBATCH --job-name=vcf2Plink
#SBATCH --account=pi-yangili1
#SBATCH --time=36:00:00
#SBATCH --output=vcf2Plink.out
#SBATCH --error=vcf2Plink.err
#SBATCH --partition=broadwl
#SBATCH --mem=30G
#SBATCH --mail-type=END

module load vcftools

for i  in {1..22};
do
vcftools --gzvcf /project2/gilad/briana/YRI_geno_hg19/chr${i}.dose.vcf.gz --plink --chr ${i} --out /project2/gilad/briana/YRI_geno_hg19/plinkYRIgeno_chr${i}
done</code></pre>
<p>Try with plink:<br />
I will use the ped and map files: –ped /project2/gilad/briana/YRI_geno_hg19/plinkYRIgeno_chr$i.ped –map /project2/gilad/briana/YRI_geno_hg19/plinkYRIgeno_chri.map</p>
<p>–ld-snp-list /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Total.txt</p>
<p>–r2</p>
<p>–ld-window-r2 0.20.8 testPlink_r2.sh</p>
<pre class="bash"><code>#!/bin/bash

#SBATCH --job-name=testPlink_r2
#SBATCH --account=pi-yangili1
#SBATCH --time=36:00:00
#SBATCH --output=testPlink_r2.out
#SBATCH --error=testPlink_r2.err
#SBATCH --partition=broadwl
#SBATCH --mem=30G
#SBATCH --mail-type=END

module load plink

plink --ped /project2/gilad/briana/YRI_geno_hg19/plinkYRIgeno_chr22.ped  --map /project2/gilad/briana/YRI_geno_hg19/plinkYRIgeno_chr22.map --r2  --ld-window-r2 0.8 --out /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/plinkYRI_LDchr22
</code></pre>
<p>This gives me 77,000 pairs. I will run this on all of the chromosomes then subset by snps i have QTLs for.</p>
<p>RunPlink_r2.sh</p>
<pre class="bash"><code>#!/bin/bash

#SBATCH --job-name=RunPlink_r2
#SBATCH --account=pi-yangili1
#SBATCH --time=36:00:00
#SBATCH --output=RunPlink_r2.out
#SBATCH --error=RunPlink_r2.err
#SBATCH --partition=broadwl
#SBATCH --mem=30G
#SBATCH --mail-type=END

module load plink


for i  in {1..22};
do
plink --ped /project2/gilad/briana/YRI_geno_hg19/plinkYRIgeno_chr${i}.ped  --map /project2/gilad/briana/YRI_geno_hg19/plinkYRIgeno_chr${i}.map --r2  --ld-window-r2 0.8 --out /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/plinkYRI_LDchr${i}
done
</code></pre>
<p>I can now subset these files for snps in the /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Total.txt and /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Nuclear.txt files using a python script.</p>
<p>This script will take a fraction and chromosome.</p>
<p>subset_plink4QTLs.py</p>
<pre class="bash"><code>
    
def main(genFile, qtlFile, outFile):
  #convert snp file to a list: 
  def file_to_list(file):
    snp_list=[]
    for ln in file:
      snp=ln.strip()
      snp_list.append(snp)
    return(snp_list)

  gen=open(genFile,&quot;r&quot;)
  fout=open(outFile, &quot;w&quot;)
  qtls=open(qtlFile, &quot;r&quot;)
  qtl_list=file_to_list(qtls)
  for ln in gen:
      snp=ln.split()[2]
      if snp in qtl_list:
          fout.write(ln)
  fout.close()
    

if __name__ == &quot;__main__&quot;:
    import sys
    chrom=sys.argv[1]
    fraction=sys.argv[2]
    genFile = &quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/plinkYRI_LDchr%s.ld&quot;%(chrom)
    outFile= &quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/%sApaQTL_LD/chr%s.%sQTL.LD.geno.ld&quot;%(fraction,chrom,fraction)
    qtlFile= &quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_%s.txt&quot;%(fraction)
    main(genFile, qtlFile, outFile) 
    
    
    </code></pre>
<p>Run this for all chr in a bash script:</p>
<p>run_subset_plink4QTLs.sh</p>
<pre class="bash"><code>#!/bin/bash

#SBATCH --job-name=run_subset_plink4QTLs
#SBATCH --account=pi-yangili1
#SBATCH --time=36:00:00
#SBATCH --output=run_subset_plink4QTLs.out
#SBATCH --error=run_subset_plink4QTLs.err
#SBATCH --partition=broadwl
#SBATCH --mem=30G
#SBATCH --mail-type=END


module load Anaconda3
source activate three-prime-env


for i  in {1..22};
do
python subset_plink4QTLs.py ${i} &quot;Total&quot;
done

for i  in {1..22};
do
python subset_plink4QTLs.py ${i} &quot;Nuclear&quot;
done</code></pre>
<p>This results in 385 more snps for the nuclear QTLs and 54 more for the total.</p>
<p>I want to try this method on the bigger panel from Tonys work.</p>
<p>vcf2Plink_geu.sh</p>
<pre class="bash"><code>#!/bin/bash

#SBATCH --job-name=vcf2Plink_geu
#SBATCH --account=pi-yangili1
#SBATCH --time=36:00:00
#SBATCH --output=vcf2Plink_geu2.out
#SBATCH --error=vcf2Plink_geu2.err
#SBATCH --partition=broadwl
#SBATCH --mem=30G
#SBATCH --mail-type=END

module load vcftools

for i  in {1..22};
do
vcftools --gzvcf /project2/yangili1/LCL/geuvadis_genotypes/GEUVADIS.chr${i}.hg19_MAF5AC.vcf.gz --plink --chr ${i} --out /project2/gilad/briana/YRI_geno_hg19/geu_plinkYRIgeno_chr${i}
done</code></pre>
<p>RunPlink_Geu_r2.sh</p>
<pre class="bash"><code>#!/bin/bash

#SBATCH --job-name=RunPlink_geu_r2
#SBATCH --account=pi-yangili1
#SBATCH --time=36:00:00
#SBATCH --output=RunPlink_geu_r2.out
#SBATCH --error=RunPlink_geu_r2.err
#SBATCH --partition=broadwl
#SBATCH --mem=30G
#SBATCH --mail-type=END

module load plink


for i  in {1..22};
do
plink --ped /project2/gilad/briana/YRI_geno_hg19/geu_plinkYRIgeno_chr${i}.ped  --map /project2/gilad/briana/YRI_geno_hg19/geu_plinkYRIgeno_chr${i}.map --r2  --ld-window-r2 0.8 --out /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/geu_plinkYRI_LDchr${i}
done</code></pre>
<p>QTLs2GeuSnps.py</p>
<pre class="bash"><code>tot_in=open(&quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Total.txt&quot;, &quot;r&quot;)  
nuc_in=open(&quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Nuclear.txt&quot;, &quot;r&quot;)

tot_out=open(&quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Total_GEU.txt&quot;, &quot;w&quot;) 
nuc_out=open(&quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Nuclear_GEU.txt&quot;, &quot;w&quot;) 


def fix_file(fin, fout):
  for ln in fin:
    chrom, pos = ln.split(&quot;:&quot;)
    fout.write(&quot;snp_%s_%s/n&quot;%(chrom,pos))
  fout.close()
  

fix_file(tot_in, tot_out)
fix_file(nuc_in, nuc_out)
</code></pre>
<p>run_QTLs2GeuSnps.sh</p>
<pre class="bash"><code>#!/bin/bash

#SBATCH --job-name=run_QTLs2GeuSnps
#SBATCH --account=pi-yangili1
#SBATCH --time=36:00:00
#SBATCH --output=run_QTLs2GeuSnps.out
#SBATCH --error=run_QTLs2GeuSnps.err
#SBATCH --partition=broadwl
#SBATCH --mem=30G
#SBATCH --mail-type=END


module load Anaconda3
source activate three-prime-env


python QTLs2GeuSnps.py</code></pre>
<p>Update the python selection script for geu results.<br />
subset_plink4QTLs_geu.py</p>
<pre class="bash"><code>
    
def main(genFile, qtlFile, outFile):
  #convert snp file to a list: 
  def file_to_list(file):
    snp_list=[]
    for ln in file:
      snp=ln.strip()
      snp_list.append(snp)
    return(snp_list)

  gen=open(genFile,&quot;r&quot;)
  fout=open(outFile, &quot;w&quot;)
  qtls=open(qtlFile, &quot;r&quot;)
  qtl_list=file_to_list(qtls)
  for ln in gen:
      snp=ln.split()[2]
      if snp in qtl_list:
          fout.write(ln)
  fout.close()
    

if __name__ == &quot;__main__&quot;:
    import sys
    chrom=sys.argv[1]
    fraction=sys.argv[2]
    genFile = &quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/geu_plinkYRI_LDchr%s.ld&quot;%(chrom)
    outFile= &quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/%sApaQTL_LD_geu/chr%s.%sQTL.LD.geno.ld&quot;%(fraction,chrom,fraction)
    qtlFile= &quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_%s_GEU.txt&quot;%(fraction)
    main(genFile, qtlFile, outFile) 
    
    
    </code></pre>
<p>run_subset_plink4QTLs_geu.sh</p>
<pre class="bash"><code>#!/bin/bash

#SBATCH --job-name=run_subset_plink4QTLs_geu
#SBATCH --account=pi-yangili1
#SBATCH --time=36:00:00
#SBATCH --output=run_subset_plink4QTLs_geu.out
#SBATCH --error=run_subset_plink4QTLs_geu.err
#SBATCH --partition=broadwl
#SBATCH --mem=30G
#SBATCH --mail-type=END


module load Anaconda3
source activate three-prime-env


for i  in {1..22};
do
python subset_plink4QTLs_geu.py ${i} &quot;Total&quot;
done

for i  in {1..22};
do
python subset_plink4QTLs_geu.py ${i} &quot;Nuclear&quot;
done</code></pre>
<p>This add 1228 for total and 10251 for nuclear. This is better. I will use these for the GWAS overlap.</p>
<p>I want to make a sorted bed file with all of these snps (total and nuclear together) to overlap with the gwas catelog. I will have the snp name include if it was a from the total or nuclear. I can do all of this in python then sort the bed file after.</p>
<p>The LD files include indels. I will not include there. There are 8 in the total file and 108 in nuclear, I can remove these with the following.</p>
<pre class="bash"><code>grep -v indel /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/NuclearApaQTL_LD_geu/allChr.NuclearQTL.LD.gene.ld &gt; /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/NuclearApaQTL_LD_geu/allChr.NuclearQTL.LD.gene.ld_noIndel


grep -v indel /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/TotalApaQTL_LD_geu/allChr.TotalQTL.GD.geno.ld &gt; /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/TotalApaQTL_LD_geu/allChr.TotalQTL.GD.geno.ld_noIndel</code></pre>
<ul>
<li>/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Total_GEU.txt</li>
<li>/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Nuclear_GEU.txt</li>
<li>/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/NuclearApaQTL_LD_geu/allChr.NuclearQTL.LD.gene.ld_noIndel</li>
<li>/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/TotalApaQTL_LD_geu/allChr.TotalQTL.GD.geno.ld_noIndel</li>
</ul>
<p>makeAlloverlapbed.py</p>
<pre class="bash"><code>
#load files:  

QTL_total=open(&quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Total_GEU.txt&quot;, &quot;r&quot;)
QTL_nuclear=open(&quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/ApaQTLsigSNPpos_Nuclear_GEU.txt&quot;, &quot;r&quot;)
LD_total=open(&quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/TotalApaQTL_LD_geu/allChr.TotalQTL.GD.geno.ld_noIndel&quot;, &quot;r&quot;)
LD_nuclear=open(&quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/NuclearApaQTL_LD_geu/allChr.NuclearQTL.LD.gene.ld_noIndel&quot;, &quot;r&quot;)
outFile= open(&quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/AllOverlapSnps.bed&quot;, &quot;w&quot;)

#function for qtl to bed format
def qtl2bed(fqtl, fraction, fout=outFile):
    for ln in fqtl:
        snp, chrom, pos = ln.split(&quot;_&quot;)
        start=int(pos)-1
        end= int(pos)
        fout.write(&quot;%s\t%d\t%d\tQTL_%s\n&quot;%(chrom, start, end,fraction))

#function for ld to bed format 
def ld2bed(fLD, fraction, fout=outFile):
    for ln in fLD:
        snpID=ln.split()[5]
        snp, chrom, pos= snpID.split(&quot;_&quot;)
        start=int(pos)-1
        end=int(pos)
        fout.write(&quot;%s\t%d\t%d\tLD_%s\n&quot;%(chrom, start, end,fraction))


#I will run each of these for both fractions to get all of the snps in the out file. 


qtl2bed(QTL_nuclear, &quot;Nuclear&quot;)
qtl2bed(QTL_total, &quot;Total&quot;)
ld2bed(LD_nuclear, &quot;Nuclear&quot;)
ld2bed(LD_total, &quot;Total&quot;)


outFile.close()</code></pre>
<p>Sort it:</p>
<pre class="bash"><code>sort -k1,1 -k2,2n /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/AllOverlapSnps.bed &gt; /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/AllOverlapSnps_sort.bed</code></pre>
<p>I can now use py bedtools to overlap this.</p>
<p>overlapSNPsGWAS.py</p>
<p>This will take in any lsit of snps and overlap them with the gwas catelog bed file.</p>
<pre class="bash"><code>

def main(infile, outfile):
    gwas_file=open(&quot;/project2/gilad/briana/genome_anotation_data/hg19GwasCatalog.sort.bed&quot;,&quot;r&quot;)
    gwas=pybedtools.BedTool(gwas_file)
    snps_file=open(infile, &quot;r&quot;)
    snps=pybedtools.BedTool(snps_file)
    snpOverGWAS=snps.intersect(gwas, wa=True,wb=True)
    snpOverGWAS.saveas(outfile)

if __name__ == &quot;__main__&quot;:
    import sys
    import pybedtools
    infile=sys.argv[1]
    outfile=sys.argv[2]
    main(infile, outfile) </code></pre>
<p>Call this in bash so i can load the environment</p>
<p>run_overlapSNPsGWAS.sh</p>
<pre class="bash"><code>#!/bin/bash

#SBATCH --job-name=run_overlapSNPsGWAS
#SBATCH --account=pi-yangili1
#SBATCH --time=5:00:00
#SBATCH --output=run_overlapSNPsGWAS.out
#SBATCH --error=run_overlapSNPsGWAS.err
#SBATCH --partition=broadwl
#SBATCH --mem=10G
#SBATCH --mail-type=END


module load Anaconda3
source activate three-prime-env

python overlapSNPsGWAS.py  &quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/AllOverlapSnps_sort.bed&quot; &quot;/project2/gilad/briana/threeprimeseq/data/GWAS_overlap/AllSnps_GWASoverlapped.txt&quot;</code></pre>
<p>There are 13 overlaps now.</p>
<div id="old-stuff-before-change-to-plink" class="section level4">
<h4>old stuff before change to plink</h4>
<p>Still only get 2 that overlap the catelog. They are in the ITGAL and NCAPG genes. I should check if 16:30482494 (the nuclear QTL) is also a eQTL not how i did before but with my code from the <a href="swarmPlots_QTLs.html">all boxplot analysis</a></p>
<pre class="r"><code>plotQTL_func= function(SNP, peak, gene){
  apaN_file=read.table(paste(&quot;../data/apaExamp/qtlSNP_PeakAPANuclear.&quot;, SNP, peak, &quot;.txt&quot;, sep = &quot;&quot; ), header=T)
  apaT_file=read.table(paste(&quot;../data/apaExamp/qtlSNP_PeakAPATotal.&quot;, SNP, peak, &quot;.txt&quot;, sep = &quot;&quot; ), header=T)
  su30_file=read.table(paste(&quot;../data/apaExamp/qtlSNP_Peak_4su_30_&quot;, SNP, gene, &quot;.txt&quot;, sep=&quot;&quot;), header = T)
  su60_file=read.table(paste(&quot;../data/apaExamp/qtlSNP_Peak_4su_60_&quot;, SNP, gene, &quot;.txt&quot;, sep=&quot;&quot;), header=T)
  RNA_file=read.table(paste(&quot;../data/apaExamp/qtlSNP_Peak_RNAseq_&quot;, SNP, gene, &quot;.txt&quot;, sep=&quot;&quot;),header=T)
  RNAg_file=read.table(paste(&quot;../data/apaExamp/qtlSNP_Peak_RNAseqGeuvadis_&quot;, SNP, gene, &quot;.txt&quot;, sep=&quot;&quot;), header = T)
  ribo_file=read.table(paste(&quot;../data/apaExamp/qtlSNP_Peak_ribo_&quot;, SNP, gene, &quot;.txt&quot;, sep=&quot;&quot;),header=T)
  prot_file=read.table(paste(&quot;../data/apaExamp/qtlSNP_Peak_prot.&quot;, SNP, gene, &quot;.txt&quot;, sep=&quot;&quot;), header=T)
  
  ggplot_func= function(file, molPhen,GENE){
    file = file %&gt;% mutate(genotype=Allele1 + Allele2)
    file$genotype= as.factor(as.character(file$genotype))
    plot=ggplot(file, aes(y=Pheno, x=genotype, by=genotype, fill=genotype)) + geom_boxplot(width=.25) + geom_jitter() + labs(y=&quot;Phenotpye&quot;,title=paste(molPhen, GENE, sep=&quot;: &quot;)) + scale_fill_brewer(palette=&quot;Paired&quot;)
    return(plot)
  }
  
  apaNplot=ggplot_func(apaN_file, &quot;Apa Nuclear&quot;, gene)
  apaTplot=ggplot_func(apaT_file, &quot;Apa Total&quot;, gene)
  su30plot=ggplot_func(su30_file, &quot;4su30&quot;,gene)
  su60plot=ggplot_func(su60_file, &quot;4su60&quot;,gene)
  RNAplot=ggplot_func(RNA_file, &quot;RNA Seq&quot;,gene)
  RNAgPlot=ggplot_func(RNAg_file, &quot;RNA Seq Geuvadis&quot;,gene)
  riboPlot= ggplot_func(ribo_file, &quot;Ribo Seq&quot;,gene)
  protplot=ggplot_func(prot_file, &quot;Protein&quot;,gene)
  
  full_plot= plot_grid(apaNplot,apaTplot, su30plot, su60plot, RNAplot, RNAgPlot, riboPlot, protplot,nrow=2)
  return (full_plot)
}</code></pre>
<p>16:30482494 PPP4C_+_peak122195</p>
<pre class="bash"><code>grep peak122195 /project2/gilad/briana/threeprimeseq/data/perm_APAqtl_trans/filtered_APApeaks_merged_allchrom_refseqGenes_pheno_Nuclear_transcript_permResBH.txt
#gene=PPP4C
grep PPP4C /project2/gilad/briana/genome_anotation_data/ensemble_to_genename.txt
#ensg= ENSG00000149923

python createQTLsnpAPAPhenTable.py 16 16:30482494  peak122195 Total
python createQTLsnpAPAPhenTable.py 16 16:30482494  peak122195 Nuclear


sbatch run_createQTLsnpMolPhenTable.sh &quot;16&quot; &quot;16:30482494&quot; &quot;ENSG00000149923&quot;

scp brimittleman@midway2.rcc.uchicago.edu:/project2/gilad/briana/threeprimeseq/data/ApaQTL_examples/*16:30482494* /Users/bmittleman1/Documents/Gilad_lab/threeprimeseq/data/apaExamp</code></pre>
<pre class="r"><code>plotQTL_func(SNP=&quot;16:30482494&quot;, peak=&quot;peak122195&quot;, gene=&quot;ENSG00000149923&quot;)</code></pre>
<pre><code>Warning: Removed 2 rows containing non-finite values (stat_boxplot).</code></pre>
<pre><code>Warning: Removed 2 rows containing missing values (geom_point).</code></pre>
<p><img src="figure/apaQTLoverlapGWAS.Rmd/unnamed-chunk-29-1.png" width="672" style="display: block; margin: auto;" /></p>
<details> <summary><em>Expand here to see past versions of unnamed-chunk-29-1.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/4a4b5c7261b220189f8f2bc433f79618ec4c2bab/docs/figure/apaQTLoverlapGWAS.Rmd/unnamed-chunk-29-1.png" target="_blank">4a4b5c7</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-11-12
</td>
</tr>
</tbody>
</table>
<p></details></p>
<p>This is in a GWAS for Ulcerative colitis.</p>
<p>I can look at the LD snp as well. I just need to check the ld snps and see which snp it corresponds to in my QTLs.</p>
<p>4:17797966</p>
<pre class="bash"><code>grep snp_4_17797966 /project2/gilad/briana/threeprimeseq/data/GWAS_overlap/NuclearApaQTL_LD_geu/allChr.NuclearQTL.LD.gene.ld_noIndel
</code></pre>
<p>In my analysis the snp is 4:17797455 DCAF16_-_peak236311: This is also a different gene.</p>
<pre class="bash"><code>grep peak236311 /project2/gilad/briana/threeprimeseq/data/perm_APAqtl_trans/filtered_APApeaks_merged_allchrom_refseqGenes_pheno_Nuclear_transcript_permResBH.txt
#gene=PPP4C
grep DCAF16 /project2/gilad/briana/genome_anotation_data/ensemble_to_genename.txt
#ensg=ENSG00000163257

python createQTLsnpAPAPhenTable.py 4 4:17797455  peak236311 Total
python createQTLsnpAPAPhenTable.py 4 4:17797455  peak236311 Nuclear


sbatch run_createQTLsnpMolPhenTable.sh &quot;4&quot; &quot;4:17797455&quot; &quot;ENSG00000163257&quot;

scp brimittleman@midway2.rcc.uchicago.edu:/project2/gilad/briana/threeprimeseq/data/ApaQTL_examples/*4:17797455* /Users/bmittleman1/Documents/Gilad_lab/threeprimeseq/data/apaExamp</code></pre>
<pre class="r"><code>plotQTL_func(SNP=&quot;4:17797455&quot;, peak=&quot;peak236311&quot;, gene=&quot;ENSG00000163257&quot;)</code></pre>
<p><img src="figure/apaQTLoverlapGWAS.Rmd/unnamed-chunk-32-1.png" width="672" style="display: block; margin: auto;" /></p>
<details> <summary><em>Expand here to see past versions of unnamed-chunk-32-1.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/4a4b5c7261b220189f8f2bc433f79618ec4c2bab/docs/figure/apaQTLoverlapGWAS.Rmd/unnamed-chunk-32-1.png" target="_blank">4a4b5c7</a>
</td>
<td style="text-align:left;">
Briana Mittleman
</td>
<td style="text-align:left;">
2018-11-12
</td>
</tr>
</tbody>
</table>
<p></details></p>
<p>This example is a GWAS hit for height .</p>
</div>
</div>
<div id="yangs-script" class="section level2">
<h2>Yangs script</h2>
<p>–ld-window-kb 1000 –ld-window 99999 –ld-window-r2 0.8</p>
</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     

other attached packages:
 [1] bindrcpp_0.2.2  cowplot_0.9.3   forcats_0.3.0   stringr_1.3.1  
 [5] dplyr_0.7.6     purrr_0.2.5     readr_1.1.1     tidyr_0.8.1    
 [9] tibble_1.4.2    ggplot2_3.0.0   tidyverse_1.2.1 workflowr_1.1.1

loaded via a namespace (and not attached):
 [1] tidyselect_0.2.4   haven_1.1.2        lattice_0.20-35   
 [4] colorspace_1.3-2   htmltools_0.3.6    yaml_2.2.0        
 [7] rlang_0.2.2        R.oo_1.22.0        pillar_1.3.0      
[10] glue_1.3.0         withr_2.1.2        R.utils_2.7.0     
[13] RColorBrewer_1.1-2 modelr_0.1.2       readxl_1.1.0      
[16] bindr_0.1.1        plyr_1.8.4         munsell_0.5.0     
[19] gtable_0.2.0       cellranger_1.1.0   rvest_0.3.2       
[22] R.methodsS3_1.7.1  evaluate_0.11      labeling_0.3      
[25] knitr_1.20         broom_0.5.0        Rcpp_0.12.19      
[28] scales_1.0.0       backports_1.1.2    jsonlite_1.5      
[31] hms_0.4.2          digest_0.6.17      stringi_1.2.4     
[34] grid_3.5.1         rprojroot_1.3-2    cli_1.0.1         
[37] tools_3.5.1        magrittr_1.5       lazyeval_0.2.1    
[40] crayon_1.3.4       whisker_0.3-2      pkgconfig_2.0.2   
[43] xml2_1.2.0         lubridate_1.7.4    assertthat_0.2.0  
[46] rmarkdown_1.10     httr_1.3.1         rstudioapi_0.8    
[49] R6_2.3.0           nlme_3.1-137       git2r_0.23.0      
[52] compiler_3.5.1    </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>