<!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>Overlap molQTLs, Opposite Direction</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">Overlap molQTLs, Opposite Direction</h1> <h4 class="author"><em>Briana Mittleman</em></h4> <h4 class="date"><em>10/8/2018</em></h4> </div> <p><strong>Last updated:</strong> 2018-10-09</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/605aa2d05fffa46643d1f447ee9219f19815b6b7" target="_blank">605aa2d</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: KalistoAbundance18486.txt Untracked: analysis/genometrack_figs.Rmd 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/NuclearApaQTLs.txt 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/ensemble_to_genename.txt 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/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/PeakToGeneAssignment.Rmd Modified: analysis/cleanupdtseq.internalpriming.Rmd Modified: analysis/dif.iso.usage.leafcutter.Rmd Modified: analysis/diff_iso_pipeline.Rmd Modified: analysis/explore.filters.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/605aa2d05fffa46643d1f447ee9219f19815b6b7/analysis/overlapMolQTL.opposite.Rmd" target="_blank">605aa2d</a> </td> <td style="text-align:left;"> Briana Mittleman </td> <td style="text-align:left;"> 2018-10-09 </td> <td style="text-align:left;"> plot results </td> </tr> <tr> <td style="text-align:left;"> html </td> <td style="text-align:left;"> <a href="https://cdn.rawgit.com/brimittleman/threeprimeseq/22aa0872ec0621164f376f8225f985be6112e20f/docs/overlapMolQTL.opposite.html" target="_blank">22aa087</a> </td> <td style="text-align:left;"> Briana Mittleman </td> <td style="text-align:left;"> 2018-10-08 </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/11f9dfa2e7e97a7279afc91e4f1a8f2cdb1f856e/analysis/overlapMolQTL.opposite.Rmd" target="_blank">11f9dfa</a> </td> <td style="text-align:left;"> Briana Mittleman </td> <td style="text-align:left;"> 2018-10-08 </td> <td style="text-align:left;"> overlap molQTL opp dir </td> </tr> </tbody> </table> </ul> <p></details></p> <hr /> <p>In the <a href="overlapMolQTL.html">OverlapMolQTL</a> analysis I looked at significant molecular QTLs and asked if they are also significant snp:gene pairs in the ApaQTLs. In this analysis, I will look at the significant ApaQTLs and ask if the snp:gene pairs are significant in the other molecular phenotypes. I expect enrichment of low pvalues in protQTLs but less in RNA.</p> <p>I am going to complete this analysis first for the totalAPA QTLs.</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(reshape2) 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(VennDiagram)</code></pre> <pre><code>Loading required package: grid</code></pre> <pre><code>Loading required package: futile.logger</code></pre> <pre class="r"><code>library(data.table)</code></pre> <pre><code> Attaching package: 'data.table'</code></pre> <pre><code>The following objects are masked from 'package:dplyr': between, first, last</code></pre> <pre><code>The following object is masked from 'package:purrr': transpose</code></pre> <pre><code>The following objects are masked from 'package:reshape2': dcast, melt</code></pre> <pre class="r"><code>library(qvalue) set.seed(327)</code></pre> <div id="molqtl-pvalues-for-total-apaqtls" class="section level2"> <h2>MolQTL pvalues for Total ApaQTLs</h2> <p>sigTotAPAinMolPheno.R</p> <pre class="r"><code>#!/bin/rscripts #this script creates takes in the permuted APAQTL results for the total fraction and nominal pvalues from the molecular phenotpye molecular phenotype library(dplyr) library(tidyr) library(ggplot2) library(readr) library(optparse) geneNames=read.table("/project2/gilad/briana/genome_anotation_data/ensemble_to_genename.txt", sep="\t", header=T, stringsAsFactors = F) tot_perm=read.table("/project2/gilad/briana/threeprimeseq/data/perm_APAqtl_trans/filtered_APApeaks_merged_allchrom_refseqGenes_pheno_Total_transcript_permResBH.txt", header = T,stringsAsFactors=F) sigSNPgene=tot_perm %>% filter(-log10(bh)>1) %>% separate(pid, into=c("chr", "start", "end", "id"), sep=":") %>% separate(id, into=c("Gene.name", "strand", "peaknum"), sep="_") %>% dplyr::select(Gene.name, sid, bh) %>% group_by(Gene.name) %>% top_n(-1, bh) %>% ungroup() %>% dplyr::select(Gene.name, sid) option_list = list( make_option(c("-M", "--molNom"), action="store", default=NA, type='character', help="molecular Nom results"), make_option(c("-O", "--output"), action="store", default=NA, type='character', help="output file for total APA sig snps in mol qtl") ) opt_parser <- OptionParser(option_list=option_list) opt <- parse_args(opt_parser) if (opt$molNom == "/project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_prot.fixed.nominal.out") { in_file=read.table(opt$molNom, col.names = c("Gene.stable.ID", "sid", "dist", "pval", "slope"),stringsAsFactors=F) file_newNames=in_file %>% inner_join(geneNames, by="Gene.stable.ID") %>% dplyr::select("Gene.name", "sid", "pval") } else { in_file=read.table(opt$molNom, col.names = c("pid", "sid", "dist", "pval", "slope"),stringsAsFactors=F) file_newNames=in_file %>% separate(pid, into=c("Gene.stable.ID", "ver"), sep ="[.]") %>% inner_join(geneNames, by="Gene.stable.ID") %>% dplyr::select("Gene.name", "sid", "pval") } overlap= file_newNames %>% semi_join(sigSNPgene, by=c("Gene.name", "sid")) write.table(overlap, file=opt$output, quote=F, col.names = T, row.names = F)</code></pre> <p>Run this first on the rnaQTLs.</p> <p>run_sigTotAPAinMolPhenoRNA.sh</p> <pre class="bash"><code>#!/bin/bash #SBATCH --job-name=run_sigTotAPAinMolPhenoRNA #SBATCH --account=pi-yangili1 #SBATCH --time=24:00:00 #SBATCH --output=run_sigTotAPAinMolPhenoRNA.out #SBATCH --error=run_sigTotAPAinMolPhenoRNA.err #SBATCH --partition=bigmem2 #SBATCH --mem=64G #SBATCH --mail-type=END module load R Rscript sigTotAPAinMolPheno.R --molNom "/project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_RNAseq_phase2.fixed.nominal.out" --output "/project2/gilad/briana/threeprimeseq/data/molecular_overlap/APA2molTotal/TotAPAqtlsPvalRNA.txt" </code></pre> <p>run_sigTotAPAinMolPhenoProt.sh</p> <pre class="bash"><code>#!/bin/bash #SBATCH --job-name=run_sigTotAPAinMolPhenoProt #SBATCH --account=pi-yangili1 #SBATCH --time=24:00:00 #SBATCH --output=run_sigTotAPAinMolPhenoProt.out #SBATCH --error=run_sigTotAPAinMolPhenoProt.err #SBATCH --partition=bigmem2 #SBATCH --mem=64G #SBATCH --mail-type=END module load R Rscript sigTotAPAinMolPheno.R --molNom "/project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_prot.fixed.nominal.out" --output "/project2/gilad/briana/threeprimeseq/data/molecular_overlap/APA2molTotal/TotAPAqtlsPvalProtein.txt" </code></pre> <p>run_sigTotAPAinMolPhenoProt.sh</p> <pre class="bash"><code>#!/bin/bash #SBATCH --job-name=run_sigTotAPAinMolPhenoProt #SBATCH --account=pi-yangili1 #SBATCH --time=24:00:00 #SBATCH --output=run_sigTotAPAinMolPhenoProt.out #SBATCH --error=run_sigTotAPAinMolPhenoProt.err #SBATCH --partition=bigmem2 #SBATCH --mem=64G #SBATCH --mail-type=END module load R Rscript sigTotAPAinMolPheno.R --molNom "/project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_prot.fixed.nominal.out" --output "/project2/gilad/briana/threeprimeseq/data/molecular_overlap/APA2molTotal/TotAPAqtlsPvalProtein.txt" </code></pre> <p>run_sigTotAPAinMolPhenoRNAg.sh</p> <pre class="bash"><code>#!/bin/bash #SBATCH --job-name=run_sigTotAPAinMolPhenoRNAg #SBATCH --account=pi-yangili1 #SBATCH --time=24:00:00 #SBATCH --output=run_sigTotAPAinMolPhenoRNAg.out #SBATCH --error=run_sigTotAPAinMolPhenoRNAg.err #SBATCH --partition=bigmem2 #SBATCH --mem=64G #SBATCH --mail-type=END module load R Rscript sigTotAPAinMolPheno.R --molNom "/project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_RNAseqGeuvadis.fixed.nominal.out" --output "/project2/gilad/briana/threeprimeseq/data/molecular_overlap/APA2molTotal/TotAPAqtlsPvalRNAg.txt" </code></pre> <p>run_sigTotAPAinMolPhenoRibo.sh</p> <pre class="bash"><code>#!/bin/bash #SBATCH --job-name=run_sigTotAPAinMolPhenoRibo #SBATCH --account=pi-yangili1 #SBATCH --time=24:00:00 #SBATCH --output=run_sigTotAPAinMolPhenoRibo.out #SBATCH --error=run_sigTotAPAinMolPhenoRibo.err #SBATCH --partition=bigmem2 #SBATCH --mem=64G #SBATCH --mail-type=END module load R Rscript sigTotAPAinMolPheno.R --molNom "/project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_ribo_phase2.fixed.nominal.out" --output "/project2/gilad/briana/threeprimeseq/data/molecular_overlap/APA2molTotal/TotAPAqtlsPvalribo.txt" </code></pre> <p>run_sigTotAPAinMolPheno4su.sh</p> <pre class="bash"><code>#!/bin/bash #SBATCH --job-name=run_sigTotAPAinMolPheno4su #SBATCH --account=pi-yangili1 #SBATCH --time=24:00:00 #SBATCH --output=run_sigTotAPAinMolPheno4su.out #SBATCH --error=run_sigTotAPAinMolPheno4su.err #SBATCH --partition=bigmem2 #SBATCH --mem=64G #SBATCH --mail-type=END module load R Rscript sigTotAPAinMolPheno.R --molNom "/project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_4su30.fixed.nominal.out" --output "/project2/gilad/briana/threeprimeseq/data/molecular_overlap/APA2molTotal/TotAPAqtlsPval4su30.txt" Rscript sigTotAPAinMolPheno.R --molNom "/project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_4su60.fixed.nominal.out" --output "/project2/gilad/briana/threeprimeseq/data/molecular_overlap/APA2molTotal/TotAPAqtlsPval4su60.txt" </code></pre> </div> <div id="molqtl-pvalues-for-nuclear-apaqtls" class="section level2"> <h2>MolQTL pvalues for Nuclear ApaQTLs</h2> <p>sigNucAPAinMolPheno.R</p> <pre class="r"><code>#!/bin/rscripts #this script creates takes in the permuted APAQTL results for the total fraction and nominal pvalues from the molecular phenotpye molecular phenotype library(dplyr) library(tidyr) library(ggplot2) library(readr) library(optparse) geneNames=read.table("/project2/gilad/briana/genome_anotation_data/ensemble_to_genename.txt", sep="\t", header=T, stringsAsFactors = F) nuc_perm=read.table("/project2/gilad/briana/threeprimeseq/data/perm_APAqtl_trans/filtered_APApeaks_merged_allchrom_refseqGenes_pheno_Nuclear_transcript_permResBH.txt", header = T,stringsAsFactors=F) sigSNPgene=nuc_perm %>% filter(-log10(bh)>1) %>% separate(pid, into=c("chr", "start", "end", "id"), sep=":") %>% separate(id, into=c("Gene.name", "strand", "peaknum"), sep="_") %>% dplyr::select(Gene.name, sid, bh) %>% group_by(Gene.name) %>% top_n(-1, bh) %>% ungroup() %>% dplyr::select(Gene.name, sid) option_list = list( make_option(c("-M", "--molNom"), action="store", default=NA, type='character', help="molecular Nom results"), make_option(c("-O", "--output"), action="store", default=NA, type='character', help="output file for total APA sig snps in mol qtl") ) opt_parser <- OptionParser(option_list=option_list) opt <- parse_args(opt_parser) if (opt$molNom == "/project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_prot.fixed.nominal.out") { in_file=read.table(opt$molNom, col.names = c("Gene.stable.ID", "sid", "dist", "pval", "slope"),stringsAsFactors=F) file_newNames=in_file %>% inner_join(geneNames, by="Gene.stable.ID") %>% dplyr::select("Gene.name", "sid", "pval") } else { in_file=read.table(opt$molNom, col.names = c("pid", "sid", "dist", "pval", "slope"),stringsAsFactors=F) file_newNames=in_file %>% separate(pid, into=c("Gene.stable.ID", "ver"), sep ="[.]") %>% inner_join(geneNames, by="Gene.stable.ID") %>% dplyr::select("Gene.name", "sid", "pval") } overlap= file_newNames %>% semi_join(sigSNPgene, by=c("Gene.name", "sid")) write.table(overlap, file=opt$output, quote=F, col.names = T, row.names = F)</code></pre> <p>1 bash script for all of the phenotypes</p> <p>run_sigNucAPAinMolPheno.sh</p> <pre class="bash"><code>#!/bin/bash #SBATCH --job-name=run_sigNucAPAinMolPheno #SBATCH --account=pi-yangili1 #SBATCH --time=24:00:00 #SBATCH --output=run_sigNucAPAinMolPheno.out #SBATCH --error=run_sigNucAPAinMolPheno.err #SBATCH --partition=broadwl #SBATCH --mem=32G #SBATCH --mail-type=END module load R Rscript sigNucAPAinMolPheno.R --molNom "/project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_RNAseq_phase2.fixed.nominal.out" --output "/project2/gilad/briana/threeprimeseq/data/molecular_overlap/APA2molNuclear/NucAPAqtlsPvalRNA.txt" Rscript sigNucAPAinMolPheno.R --molNom "/project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_prot.fixed.nominal.out" --output "/project2/gilad/briana/threeprimeseq/data/molecular_overlap/APA2molNuclear/NucAPAqtlsPvalProtein.txt" Rscript sigNucAPAinMolPheno.R --molNom "/project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_RNAseqGeuvadis.fixed.nominal.out" --output "/project2/gilad/briana/threeprimeseq/data/molecular_overlap/APA2molNuclear/NucAPAqtlsPvalRNAg.txt" Rscript sigNucAPAinMolPheno.R --molNom "/project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_ribo_phase2.fixed.nominal.out" --output "/project2/gilad/briana/threeprimeseq/data/molecular_overlap/APA2molNuclear/NucAPAqtlsPvalribo.txt" Rscript sigNucAPAinMolPheno.R --molNom "/project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_4su30.fixed.nominal.out" --output "/project2/gilad/briana/threeprimeseq/data/molecular_overlap/APA2molNuclear/NucAPAqtlsPval4su30.txt" Rscript sigNucAPAinMolPheno.R --molNom "/project2/gilad/briana/threeprimeseq/data/molecular_QTLs/nom/fastqtl_qqnorm_4su60.fixed.nominal.out" --output "/project2/gilad/briana/threeprimeseq/data/molecular_overlap/APA2molNuclear/NucAPAqtlsPval4su60.txt" </code></pre> </div> <div id="create-histograms" class="section level2"> <h2>Create Histograms</h2> <div id="total" class="section level3"> <h3>Total</h3> <p>I will next estimate sharing with pi_1 and create histograms of the resulting pvalues.</p> <ul> <li>Protein</li> </ul> <pre class="r"><code>totAPAinProt=read.table("../data/mol_overlap/APA2molTotal/TotAPAqtlsPvalProtein.txt", header = T, stringsAsFactors = F) qval_prot=pi0est(totAPAinProt$pval, pi0.method = "bootstrap")</code></pre> <ul> <li>RNA</li> </ul> <pre class="r"><code>totAPAinRNA=read.table("../data/mol_overlap/APA2molTotal/TotAPAqtlsPvalRNA.txt", header = T, stringsAsFactors = F) qval_RNA=pi0est(totAPAinRNA$pval, pi0.method = "bootstrap")</code></pre> <ul> <li>RNA Geuvadis</li> </ul> <pre class="r"><code>totAPAinRNAg=read.table("../data/mol_overlap/APA2molTotal/TotAPAqtlsPvalRNAg.txt", header = T, stringsAsFactors = F) qval_RNAg=pi0est(totAPAinRNAg$pval, pi0.method = "bootstrap")</code></pre> <p>*Ribo</p> <pre class="r"><code>totAPAinRibo=read.table("../data/mol_overlap/APA2molTotal/TotAPAqtlsPvalribo.txt", header = T, stringsAsFactors = F) qval_Ribo=pi0est(totAPAinRibo$pval, pi0.method = "bootstrap")</code></pre> <ul> <li>4su30</li> </ul> <pre class="r"><code>totAPAinsu30=read.table("../data/mol_overlap/APA2molTotal/TotAPAqtlsPval4su30.txt", header = T, stringsAsFactors = F) qval_su30=pi0est(totAPAinsu30$pval, pi0.method = "bootstrap")</code></pre> <ul> <li>4su60</li> </ul> <pre class="r"><code>totAPAinsu60=read.table("../data/mol_overlap/APA2molTotal/TotAPAqtlsPval4su60.txt", header = T, stringsAsFactors = F) qval_su60=pi0est(totAPAinsu60$pval, pi0.method = "bootstrap")</code></pre> <p>All plots:</p> <pre class="r"><code>par(mfrow=c(2,3)) hist(totAPAinsu30$pval, xlab="4su30 Pvalue", main="Significant Total APA QTLs \n 4su30") text(.6,15, paste("pi_1=", round((1-qval_su30$pi0), digit=3), sep=" ")) hist(totAPAinsu60$pval, xlab="4su60 Pvalue", main="Significant Total APA QTLs \n 4su60") text(.6,15, paste("pi_1=", round((1-qval_su60$pi0), digit=3), sep=" ")) hist(totAPAinRNA$pval, xlab="RNAPvalue", main="Significant Total APA QTLs \n RNA") text(.6,18, paste("pi_1=", round((1-qval_RNA$pi0), digit=3), sep=" ")) hist(totAPAinRNAg$pval, xlab="RNA Guevadis Pvalue", main="Significant Total APA QTLs \n RNA Geuvadis") text(.6,18, paste("pi_1=", round((1-qval_RNAg$pi0), digit=3), sep=" ")) hist(totAPAinRibo$pval, xlab="Ribo (Translation) Pvalue", main="Significant Total APA QTLs \n Ribo") text(.6,15, paste("pi_1=", round((1-qval_Ribo$pi0), digit=3), sep=" ")) hist(totAPAinProt$pval, xlab="Protein Pvalue", main="Significant Total APA QTLs \n Protein") text(.6,10, paste("pi_1=", round((1-qval_prot$pi0), digit=3), sep=" "))</code></pre> <p><img src="figure/overlapMolQTL.opposite.Rmd/unnamed-chunk-17-1.png" width="672" style="display: block; margin: auto;" /></p> </div> </div> <div id="nuclear" class="section level2"> <h2>Nuclear</h2> <p>I will next estimate sharing with pi_1 and create histograms of the resulting pvalues.</p> <ul> <li>Protein</li> </ul> <pre class="r"><code>NucAPAinProt=read.table("../data/mol_overlap/APA2molNuclear/NucAPAqtlsPvalProtein.txt", header = T, stringsAsFactors = F) qval_protN=pi0est(NucAPAinProt$pval, pi0.method = "bootstrap")</code></pre> <ul> <li>RNA</li> </ul> <pre class="r"><code>NucAPAinRNA=read.table("../data/mol_overlap/APA2molNuclear/NucAPAqtlsPvalRNA.txt", header = T, stringsAsFactors = F) qval_RNAN=pi0est(NucAPAinRNA$pval, pi0.method = "bootstrap")</code></pre> <ul> <li>RNA Geuvadis</li> </ul> <pre class="r"><code>NucAPAinRNAg=read.table("../data/mol_overlap/APA2molNuclear/NucAPAqtlsPvalRNAg.txt", header = T, stringsAsFactors = F) qval_RNAgN=pi0est(NucAPAinRNAg$pval, pi0.method = "bootstrap")</code></pre> <p>*Ribo</p> <pre class="r"><code>NucAPAinRibo=read.table("../data/mol_overlap/APA2molNuclear/NucAPAqtlsPvalribo.txt", header = T, stringsAsFactors = F) qval_RiboN=pi0est(NucAPAinRibo$pval, pi0.method = "bootstrap")</code></pre> <ul> <li>4su30</li> </ul> <pre class="r"><code>NucAPAinsu30=read.table("../data/mol_overlap/APA2molNuclear/NucAPAqtlsPval4su30.txt", header = T, stringsAsFactors = F) qval_su30N=pi0est(NucAPAinsu30$pval, pi0.method = "bootstrap")</code></pre> <ul> <li>4su60</li> </ul> <pre class="r"><code>NucAPAinsu60=read.table("../data/mol_overlap/APA2molNuclear/NucAPAqtlsPval4su60.txt", header = T, stringsAsFactors = F) qval_su60N=pi0est(NucAPAinsu60$pval, pi0.method = "bootstrap")</code></pre> <p>All plots:</p> <pre class="r"><code>par(mfrow=c(2,3)) hist(NucAPAinsu30$pval, xlab="4su30 Pvalue", main="Significant nuclear APA QTLs \n 4su30") text(.6,80, paste("pi_1=", round((1-qval_su30N$pi0), digit=3), sep=" ")) hist(NucAPAinsu60$pval,xlab="4su60 Pvalue",main="Significant nuclear APA QTLs \n 4su60") text(.6,90, paste("pi_1=", round((1-qval_su60N$pi0), digit=3), sep=" ")) hist(NucAPAinRNA$pval, xlab="RNA Pvalue",main="Significant nuclear APA QTLs \n RNA") text(.6,100, paste("pi_1=", round((1-qval_RNAN$pi0), digit=3), sep=" ")) hist(NucAPAinRNAg$pval, xlab="RNA Guevadis Pvalue",main="Significant nuclear APA QTLs \n RNA Geuvadis") text(.6,100, paste("pi_1=", round((1-qval_RNAgN$pi0), digit=3), sep=" ")) hist(NucAPAinRibo$pval, xlab="Ribo (translation) Pvalue",main="Significant nuclear APA QTLs \n Ribo") text(.6,100, paste("pi_1=", round((1-qval_RiboN$pi0), digit=3), sep=" ")) hist(NucAPAinProt$pval, xlab="Protein Pvalue", main="Significant nuclear APA QTLs \n Protein") text(.6,40, paste("pi_1=", round((1-qval_protN$pi0), digit=3), sep=" "))</code></pre> <p><img src="figure/overlapMolQTL.opposite.Rmd/unnamed-chunk-24-1.png" width="672" style="display: block; margin: auto;" /></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] grid stats graphics grDevices utils datasets methods [8] base other attached packages: [1] qvalue_2.12.0 data.table_1.11.8 VennDiagram_1.6.20 [4] futile.logger_1.4.3 forcats_0.3.0 stringr_1.3.1 [7] dplyr_0.7.6 purrr_0.2.5 readr_1.1.1 [10] tidyr_0.8.1 tibble_1.4.2 ggplot2_3.0.0 [13] tidyverse_1.2.1 reshape2_1.4.3 workflowr_1.1.1 loaded via a namespace (and not attached): [1] tidyselect_0.2.4 splines_3.5.1 haven_1.1.2 [4] lattice_0.20-35 colorspace_1.3-2 htmltools_0.3.6 [7] yaml_2.2.0 rlang_0.2.2 R.oo_1.22.0 [10] pillar_1.3.0 glue_1.3.0 withr_2.1.2 [13] R.utils_2.7.0 lambda.r_1.2.3 modelr_0.1.2 [16] readxl_1.1.0 bindrcpp_0.2.2 bindr_0.1.1 [19] plyr_1.8.4 munsell_0.5.0 gtable_0.2.0 [22] cellranger_1.1.0 rvest_0.3.2 R.methodsS3_1.7.1 [25] evaluate_0.11 knitr_1.20 broom_0.5.0 [28] Rcpp_0.12.19 formatR_1.5 backports_1.1.2 [31] scales_1.0.0 jsonlite_1.5 hms_0.4.2 [34] digest_0.6.17 stringi_1.2.4 rprojroot_1.3-2 [37] cli_1.0.1 tools_3.5.1 magrittr_1.5 [40] lazyeval_0.2.1 futile.options_1.0.1 crayon_1.3.4 [43] whisker_0.3-2 pkgconfig_2.0.2 xml2_1.2.0 [46] lubridate_1.7.4 assertthat_0.2.0 rmarkdown_1.10 [49] httr_1.3.1 rstudioapi_0.8 R6_2.3.0 [52] nlme_3.1-137 git2r_0.23.0 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>