| Previous changeset 0:58ef4507ce5a (2018-05-24) Next changeset 2:cb133602cd9b (2018-05-30) |
|
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/chipseeker commit 3419a5a5e19a93369c8c20a39babe5636a309292 |
|
modified:
chipseeker.xml test-data/out.pdf |
|
added:
chipseeker.R test-data/cached_locally/gene_sets.loc test-data/cached_locally/ref.gtf test-data/in.bed test-data/in.gtf test-data/in.interval test-data/out.int test-data/outflank.tab test-data/outint.int test-data/outint.tab test-data/outtss.tab tool-data/gene_sets.loc.sample tool_data_table_conf.xml.sample tool_data_table_conf.xml.test |
|
removed:
test-data/in.diffbind test-data/out.tab |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 chipseeker.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/chipseeker.R Tue May 29 15:08:04 2018 -0400 |
| [ |
| @@ -0,0 +1,69 @@ +options( show.error.messages=F, error = function () { cat( geterrmessage(), file=stderr() ); q( "no", 1, F ) } ) + +# we need that to not crash galaxy with an UTF8 error on German LC settings. +loc <- Sys.setlocale("LC_MESSAGES", "en_US.UTF-8") + +suppressPackageStartupMessages({ + library(ChIPseeker) + library(GenomicFeatures) + library(optparse) +}) + +option_list <- list( + make_option(c("-i","--infile"), type="character", help="Peaks file to be annotated"), + make_option(c("-G","--gtf"), type="character", help="GTF to create TxDb."), + make_option(c("-u","--upstream"), type="integer", help="TSS upstream region"), + make_option(c("-d","--downstream"), type="integer", help="TSS downstream region"), + make_option(c("-F","--flankgeneinfo"), type="logical", help="Add flanking gene info"), + make_option(c("-D","--flankgenedist"), type="integer", help="Flanking gene distance"), + make_option(c("-f","--format"), type="character", help="Output format (interval or tabular)."), + make_option(c("-p","--plots"), type="character", help="PDF of plots.") + ) + +parser <- OptionParser(usage = "%prog [options] file", option_list=option_list) +args = parse_args(parser) + +peaks = args$infile +gtf = args$gtf +up = args$upstream +down = args$downstream +format = args$format +plots = args$plots + +peaks <- readPeakFile(peaks) + +# Make TxDb from GTF +txdb <- makeTxDbFromGFF(gtf, format="gtf") +if (!is.null(args$flankgeneinfo)) { + peakAnno <- annotatePeak(peaks, TxDb=txdb, tssRegion=c(-up, down), addFlankGeneInfo=args$flankgeneinfo, flankDistance=args$flankgenedist) +} else { + peakAnno <- annotatePeak(peaks, TxDb=txdb, tssRegion=c(-up, down)) +} + +# Convert from 1-based to 0-based format +res <- as.GRanges(peakAnno) +metacols <- mcols(res) +if (format == "interval") { + metacols <- apply(as.data.frame(metacols), 1, function(col) paste(col, collapse="|")) + resout <- data.frame(Chrom=seqnames(res), + Start=start(res) - 1, + End=end(res), + Comment=metacols) +} else { + resout <- data.frame(Chrom=seqnames(res), + Start=start(res) - 1, + End=end(res), + metacols) +} + +write.table(resout, file="out.tab", sep="\t", row.names=FALSE, quote=FALSE) + +if (!is.null(plots)) { + pdf("out.pdf", width=14) + plotAnnoPie(peakAnno) + plotAnnoBar(peakAnno) + vennpie(peakAnno) + upsetplot(peakAnno) + plotDistToTSS(peakAnno, title="Distribution of transcription factor-binding loci\nrelative to TSS") + dev.off() +} \ No newline at end of file |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 chipseeker.xml --- a/chipseeker.xml Thu May 24 18:25:40 2018 -0400 +++ b/chipseeker.xml Tue May 29 15:08:04 2018 -0400 |
| [ |
| b'@@ -1,89 +1,75 @@\n-<tool id="chipseeker" name="ChIPseeker" version="1.14.2">\n+<tool id="chipseeker" name="ChIPseeker" version="1.14.2.1">\n <description>for ChIP peak annotation and visualization</description>\n <requirements>\n <requirement type="package" version="1.14.2">bioconductor-chipseeker</requirement>\n- <requirement type="package" version="3.4.0">bioconductor-txdb.hsapiens.ucsc.hg38.knowngene</requirement>\n- <requirement type="package" version="3.2.2">bioconductor-txdb.hsapiens.ucsc.hg19.knowngene</requirement>\n- <requirement type="package" version="3.4.0">bioconductor-txdb.Mmusculus.UCSC.mm10.knownGene</requirement>\n- <requirement type="package" version="3.5.0">bioconductor-org.hs.eg.db</requirement>\n- <requirement type="package" version="3.5.0">bioconductor-org.mm.eg.db</requirement>\n+ <requirement type="package" version="1.4.4">r-optparse</requirement>\n </requirements>\n <version_command><![CDATA[\n-echo $(R --version | grep version | grep -v GNU)", ChIPseeker version" $(R --vanilla --slave -e "library(ChIPseeker); cat(sessionInfo()\\$otherPkgs\\$ChIPseeker\\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", TxDb.Hsapiens.UCSC.hg38.knownGene version" $(R --vanilla --slave -e "library(TxDb.Hsapiens.UCSC.hg38.knownGene); cat(sessionInfo()\\$otherPkgs\\$TxDb.Hsapiens.UCSC.hg38.knownGene\\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", TxDb.Hsapiens.UCSC.hg19.knownGene version" $(R --vanilla --slave -e "library(TxDb.Hsapiens.UCSC.hg19.knownGene); cat(sessionInfo()\\$otherPkgs\\$TxDb.Hsapiens.UCSC.hg19.knownGene\\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", TxDb.Mmusculus.UCSC.mm10.knownGene version" $(R --vanilla --slave -e "library(TxDb.Mmusculus.UCSC.mm10.knownGene); cat(sessionInfo()\\$otherPkgs\\$TxDb.Mmusculus.UCSC.mm10.knownGene\\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", org.Hs.eg.db version" $(R --vanilla --slave -e "library(org.Hs.eg.db); cat(sessionInfo()\\$otherPkgs\\$org.Hs.eg.db\\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", org.Mm.eg.db version" $(R --vanilla --slave -e "library(org.Mm.eg.db); cat(sessionInfo()\\$otherPkgs\\$org.Mm.eg.db\\$Version)" 2> /dev/null | grep -v -i "WARNING: ")\n+echo $(R --version | grep version | grep -v GNU)", ChIPseeker version" $(R --vanilla --slave -e "library(ChIPseeker); cat(sessionInfo()\\$otherPkgs\\$ChIPseeker\\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", optparse version" $(R --vanilla --slave -e "library(optparse); cat(sessionInfo()\\$otherPkgs\\$optparse\\$Version)" 2> /dev/null | grep -v -i "WARNING: ")\n ]]></version_command>\n <command detect_errors="exit_code"><![CDATA[\n+ #set gtf = "refgtf"\n+ #if $gtf_source.gtf_source_select == "history":\n+ ln -s \'${gtf_source.gtf_hist}\' $gtf &&\n+ #else if $gtf_source.gtf_source_select == "cached":\n+ ln -s \'${gtf_source.gtf_builtin.fields.path}\' $gtf &&\n+ #end if\n+\n #if $rscript:\n- cp \'${chipseeker_script}\' \'${out_rscript}\' &&\n+ cp \'$__tool_directory__/chipseeker.R\' \'$out_rscript\' &&\n #end if\n- Rscript \'${chipseeker_script}\'\n+\n+ Rscript \'$__tool_directory__/chipseeker.R\'\n+\n+ -i \'$peaks\'\n+ -G \'$gtf\'\n+ -u $upstream\n+ -d $downstream\n+ #if $flankgeneinfo:\n+ -F $flankgeneinfo\n+ -D $flankgenedist\n+ #end if\n+ -f $format\n+ -p $pdf\n ]]>\n </command>\n- <configfiles>\n- <configfile name="chipseeker_script"><![CDATA[\n-options( show.error.messages=F, error = function () { cat( geterrmessage(), file=stderr() ); q( "no", 1, F ) } )\n-\n-# we need that to not crash galaxy with an UTF8 error on German LC settings.\n-loc <- Sys.setlocale("LC_MESSAGES", "en_US.UTF-8")\n-\n-suppressPackageStartupMessages(library(ChIPseeker))\n-\n-genome <- "${genome}"\n-\n-if (genome == "hg38") {\n- suppressPackageStartupMessages({\n- library(TxDb.Hsapiens.UCSC.hg38.knownGene)\n- library(o'..b'===== ====== ====== =====================================================================================================================================================\n+ 18 394599 396513 DiffBind|0|.|Intron (ENST00000400256/ENSG00000158270, intron 1 of 1)|1|346465|400382|53918|2|ENSG00000158270|ENST00000400256| 3869\n+ 18 111566 112005 DiffBind|0|.|Promoter (<=1kb)|1|111568|112005| 438|1|ENSG00000263006|ENST00000608049| 0\n+ 18 346463 347342 DiffBind|0|.|Exon (ENST00000400256/ENSG00000158270, exon 1 of 1)|1|346465|400382|53918|2|ENSG00000158270|ENST00000400256|53040\n+ 18 399013 400382 DiffBind|0|.|Promoter (<=1kb)|1|346465|400382|53918|2|ENSG00000158270|ENST00000400256| 0\n+ 18 371109 372102 DiffBind|0|.|Intron (ENST00000400256/ENSG00000158270, intron 1 of 1)|1|346465|400382|53918|2|ENSG00000158270|ENST00000400256|28280\n+ ===== ====== ====== =====================================================================================================================================================\n+\n+ Columns contain the following data:\n+\n+* **Chrom**: Chromosome name\n+* **Start**: Start position of site\n+* **End**: End position of site\n+* **Comment**: The pipe ("|") separated values in this column correspond to:\n+\n+ * *<Any additional input columns>*\n+ * *annotation* (Promoter, 5\xe2\x80\x99 UTR, 3\xe2\x80\x99 UTR, Exon, Intron, Downstream, Intergenic)\n+ * *geneChr*\n+ * *geneStart*\n+ * *geneEnd*\n+ * *geneLength*\n+ * *geneStrand*\n+ * *geneId*\n+ * *transcriptId*\n+ * *distanceToTSS*\n+\n+Example - **Tabular format**:\n+\n+ ===== ====== ====== ======== ====== ====== =========================================== ======================================================= ======= ========= ======= ========== ========== =============== =============== =============\n+ Chrom Start End Name Score Strand Comment annotation geneChr geneStart geneEnd geneLength geneStrand geneId transcriptId distanceToTSS\n+ ===== ====== ====== ======== ====== ====== =========================================== ======================================================= ======= ========= ======= ========== ========== =============== =============== =============\n+ 18 394599 396513 DiffBind 0 . 1914|7.15|5.55|7.89|-2.35|7.06e-24|9.84e-21 Intron (ENST00000400256/ENSG00000158270, intron 1 of 1) 1 346465 400382 53918 2 ENSG00000158270 ENST00000400256 3869\n+ 18 111566 112005 DiffBind 0 . 439|5.71|6.53|3.63|2.89|1.27e-08|8.88e-06 Promoter (<=1kb) 1 111568 112005 438 1 ENSG00000263006 ENST00000608049 0\n+ 18 346463 347342 DiffBind 0 . 879|5|5.77|3.24|2.52|6.51e-06|0.00303 Exon (ENST00000400256/ENSG00000158270, exon 1 of 1) 1 346465 400382 53918 2 ENSG00000158270 ENST00000400256 53040\n+ 18 399013 400382 DiffBind 0 . 1369|7.62|7|8.05|-1.04|1.04e-05|0.00364 Promoter (<=1kb) 1 346465 400382 53918 2 ENSG00000158270 ENST00000400256 0\n+ 18 371109 372102 DiffBind 0 . 993|4.63|3.07|5.36|-2.3|8.1e-05|0.0226 Intron (ENST00000400256/ENSG00000158270, intron 1 of 1) 1 346465 400382 53918 2 ENSG00000158270 ENST00000400256 28280\n+ ===== ====== ====== ======== ====== ====== =========================================== ======================================================= ======= ========= ======= ========== ========== =============== =============== =============\n+\n .. _ChIPseeker: https://bioconductor.org/packages/release/bioc/html/ChIPseeker.html\n .. _`ChIPseeker vignette`: http://bioconductor.org/packages/release/bioc/vignettes/ChIPseeker/inst/doc/ChIPseeker.html\n \n' |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 test-data/cached_locally/gene_sets.loc --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/cached_locally/gene_sets.loc Tue May 29 15:08:04 2018 -0400 |
| b |
| @@ -0,0 +1,1 @@ +hg38 hg38 hg38GTF ${__HERE__}/ref.gtf |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 test-data/cached_locally/ref.gtf --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/cached_locally/ref.gtf Tue May 29 15:08:04 2018 -0400 |
| b |
| @@ -0,0 +1,17 @@ +18 pseudogene gene 111568 112005 . + . gene_id "ENSG00000263006"; gene_name "ROCK1P1"; gene_source "havana"; gene_biotype "pseudogene"; +18 processed_transcript transcript 111568 112005 . + . gene_id "ENSG00000263006"; transcript_id "ENST00000608049"; gene_name "ROCK1P1"; gene_source "havana"; gene_biotype "pseudogene"; transcript_name "ROCK1P1-003"; transcript_source "havana"; +18 protein_coding gene 346465 347342 . - . gene_id "ENSG00000158270"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; +18 protein_coding gene 371111 372102 . - . gene_id "ENSG00000158270"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; +18 protein_coding gene 394601 396513 . - . gene_id "ENSG00000158270"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; +18 protein_coding gene 399015 400382 . - . gene_id "ENSG00000158270"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; +18 protein_coding transcript 346465 347342 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000400256"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-001"; transcript_source "ensembl_havana"; tag "CCDS"; ccds_id "CCDS32782"; +18 protein_coding transcript 371111 372102 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000400256"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-001"; transcript_source "ensembl_havana"; tag "CCDS"; ccds_id "CCDS32782"; +18 protein_coding transcript 394601 396513 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000400256"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-001"; transcript_source "ensembl_havana"; tag "CCDS"; ccds_id "CCDS32782"; +18 protein_coding transcript 399015 400382 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000400256"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-001"; transcript_source "ensembl_havana"; tag "CCDS"; ccds_id "CCDS32782"; +18 protein_coding exon 346465 347341 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000400256"; exon_number "5"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-001"; transcript_source "ensembl_havana"; tag "CCDS"; ccds_id "CCDS32782"; exon_id "ENSE00003544566"; +18 protein_coding CDS 346465 347341 . - 2 gene_id "ENSG00000158270"; transcript_id "ENST00000400256"; exon_number "5"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-001"; transcript_source "ensembl_havana"; tag "CCDS"; ccds_id "CCDS32782"; protein_id "ENSP00000383115"; +18 retained_intron transcript 346465 347342 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000582147"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-002"; transcript_source "havana"; +18 retained_intron transcript 371111 372102 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000582147"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-002"; transcript_source "havana"; +18 retained_intron transcript 394601 396513 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000582147"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-002"; transcript_source "havana"; +18 retained_intron transcript 399015 400382 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000582147"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-002"; transcript_source "havana"; +18 retained_intron exon 346465 347341 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000582147"; exon_number "5"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-002"; transcript_source "havana"; exon_id "ENSE00003660294"; |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 test-data/in.bed --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/in.bed Tue May 29 15:08:04 2018 -0400 |
| b |
| @@ -0,0 +1,6 @@ +Chrom Start End Name Score Strand +18 394599 396513 DiffBind 0 . +18 111566 112005 DiffBind 0 . +18 346463 347342 DiffBind 0 . +18 399013 400382 DiffBind 0 . +18 371109 372102 DiffBind 0 . |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 test-data/in.diffbind --- a/test-data/in.diffbind Thu May 24 18:25:40 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,6 +0,0 @@ -seqnames start end width strand Conc Conc_Responsive Conc_Resistant Fold p.value FDR -chr18 394600 396513 1914 * 7.15 5.55 7.89 -2.35 7.06e-24 9.84e-21 -chr18 111567 112005 439 * 5.71 6.53 3.63 2.89 1.27e-08 8.88e-06 -chr18 346464 347342 879 * 5 5.77 3.24 2.52 6.51e-06 0.00303 -chr18 399014 400382 1369 * 7.62 7 8.05 -1.04 1.04e-05 0.00364 -chr18 371110 372102 993 * 4.63 3.07 5.36 -2.3 8.1e-05 0.0226 |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 test-data/in.gtf --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/in.gtf Tue May 29 15:08:04 2018 -0400 |
| b |
| @@ -0,0 +1,17 @@ +18 pseudogene gene 111568 112005 . + . gene_id "ENSG00000263006"; gene_name "ROCK1P1"; gene_source "havana"; gene_biotype "pseudogene"; +18 processed_transcript transcript 111568 112005 . + . gene_id "ENSG00000263006"; transcript_id "ENST00000608049"; gene_name "ROCK1P1"; gene_source "havana"; gene_biotype "pseudogene"; transcript_name "ROCK1P1-003"; transcript_source "havana"; +18 protein_coding gene 346465 347342 . - . gene_id "ENSG00000158270"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; +18 protein_coding gene 371111 372102 . - . gene_id "ENSG00000158270"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; +18 protein_coding gene 394601 396513 . - . gene_id "ENSG00000158270"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; +18 protein_coding gene 399015 400382 . - . gene_id "ENSG00000158270"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; +18 protein_coding transcript 346465 347342 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000400256"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-001"; transcript_source "ensembl_havana"; tag "CCDS"; ccds_id "CCDS32782"; +18 protein_coding transcript 371111 372102 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000400256"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-001"; transcript_source "ensembl_havana"; tag "CCDS"; ccds_id "CCDS32782"; +18 protein_coding transcript 394601 396513 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000400256"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-001"; transcript_source "ensembl_havana"; tag "CCDS"; ccds_id "CCDS32782"; +18 protein_coding transcript 399015 400382 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000400256"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-001"; transcript_source "ensembl_havana"; tag "CCDS"; ccds_id "CCDS32782"; +18 protein_coding exon 346465 347341 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000400256"; exon_number "5"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-001"; transcript_source "ensembl_havana"; tag "CCDS"; ccds_id "CCDS32782"; exon_id "ENSE00003544566"; +18 protein_coding CDS 346465 347341 . - 2 gene_id "ENSG00000158270"; transcript_id "ENST00000400256"; exon_number "5"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-001"; transcript_source "ensembl_havana"; tag "CCDS"; ccds_id "CCDS32782"; protein_id "ENSP00000383115"; +18 retained_intron transcript 346465 347342 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000582147"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-002"; transcript_source "havana"; +18 retained_intron transcript 371111 372102 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000582147"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-002"; transcript_source "havana"; +18 retained_intron transcript 394601 396513 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000582147"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-002"; transcript_source "havana"; +18 retained_intron transcript 399015 400382 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000582147"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-002"; transcript_source "havana"; +18 retained_intron exon 346465 347341 . - . gene_id "ENSG00000158270"; transcript_id "ENST00000582147"; exon_number "5"; gene_name "COLEC12"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "COLEC12-002"; transcript_source "havana"; exon_id "ENSE00003660294"; |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 test-data/in.interval --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/in.interval Tue May 29 15:08:04 2018 -0400 |
| b |
| @@ -0,0 +1,6 @@ +Chrom Start End Name Score Strand Comment +18 394599 396513 DiffBind 0 . 1914|7.15|5.55|7.89|-2.35|7.06e-24|9.84e-21 +18 111566 112005 DiffBind 0 . 439|5.71|6.53|3.63|2.89|1.27e-08|8.88e-06 +18 346463 347342 DiffBind 0 . 879|5|5.77|3.24|2.52|6.51e-06|0.00303 +18 399013 400382 DiffBind 0 . 1369|7.62|7|8.05|-1.04|1.04e-05|0.00364 +18 371109 372102 DiffBind 0 . 993|4.63|3.07|5.36|-2.3|8.1e-05|0.0226 |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 test-data/out.int --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/out.int Tue May 29 15:08:04 2018 -0400 |
| b |
| @@ -0,0 +1,6 @@ +Chrom Start End Comment +18 394599 396513 DiffBind|0|.|Intron (ENST00000400256/ENSG00000158270, intron 1 of 1)|1|346465|400382|53918|2|ENSG00000158270|ENST00000400256| 3869 +18 111566 112005 DiffBind|0|.|Promoter (<=1kb)|1|111568|112005| 438|1|ENSG00000263006|ENST00000608049| 0 +18 346463 347342 DiffBind|0|.|Exon (ENST00000400256/ENSG00000158270, exon 1 of 1)|1|346465|400382|53918|2|ENSG00000158270|ENST00000400256|53040 +18 399013 400382 DiffBind|0|.|Promoter (<=1kb)|1|346465|400382|53918|2|ENSG00000158270|ENST00000400256| 0 +18 371109 372102 DiffBind|0|.|Intron (ENST00000400256/ENSG00000158270, intron 1 of 1)|1|346465|400382|53918|2|ENSG00000158270|ENST00000400256|28280 |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 test-data/out.pdf |
| b |
| Binary file test-data/out.pdf has changed |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 test-data/out.tab --- a/test-data/out.tab Thu May 24 18:25:40 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,6 +0,0 @@ -seqnames start end width strand width.1 strand.1 Conc Conc_Responsive Conc_Resistant Fold p.value FDR annotation geneChr geneStart geneEnd geneLength geneStrand geneId transcriptId distanceToTSS ENSEMBL SYMBOL GENENAME -chr18 394601 396513 1913 * 1914 * 7.15 5.55 7.89 -2.35 7.06e-24 9.84e-21 Intron (uc002kkm.3/81035, intron 2 of 9) 18 319355 500729 181375 2 81035 uc002kkm.3 104216 ENSG00000158270 COLEC12 collectin subfamily member 12 -chr18 111568 112005 438 * 439 * 5.71 6.53 3.63 2.89 1.27e-08 8.88e-06 Promoter (2-3kb) 18 109065 122222 13158 1 727758 uc002kke.3 2503 ENSG00000263006 ROCK1P1 Rho associated coiled-coil containing protein kinase 1 pseudogene 1 -chr18 346465 347342 878 * 879 * 5 5.77 3.24 2.52 6.51e-06 0.00303 Exon (uc002kkm.3/81035, exon 5 of 10) 18 225089 268059 42971 2 9984 uc002kkl.2 -78406 ENSG00000079134 THOC1 THO complex 1 -chr18 399015 400382 1368 * 1369 * 7.62 7 8.05 -1.04 1.04e-05 0.00364 Intron (uc002kkm.3/81035, intron 2 of 9) 18 319355 500729 181375 2 81035 uc002kkm.3 100347 ENSG00000158270 COLEC12 collectin subfamily member 12 -chr18 371111 372102 992 * 993 * 4.63 3.07 5.36 -2.3 8.1e-05 0.0226 Intron (uc002kkm.3/81035, intron 2 of 9) 18 225089 268059 42971 2 9984 uc002kkl.2 -103052 ENSG00000079134 THOC1 THO complex 1 |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 test-data/outflank.tab --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/outflank.tab Tue May 29 15:08:04 2018 -0400 |
| b |
| @@ -0,0 +1,6 @@ +Chrom Start End Name Score Strand Comment annotation geneChr geneStart geneEnd geneLength geneStrand geneId transcriptId distanceToTSS flank_txIds flank_geneIds flank_gene_distances +18 394599 396513 DiffBind 0 . 1914|7.15|5.55|7.89|-2.35|7.06e-24|9.84e-21 Intron (ENST00000400256/ENSG00000158270, intron 1 of 1) 1 346465 400382 53918 2 ENSG00000158270 ENST00000400256 3869 ENST00000400256;ENST00000582147 ENSG00000158270;ENSG00000158270 0;0 +18 111566 112005 DiffBind 0 . 439|5.71|6.53|3.63|2.89|1.27e-08|8.88e-06 Promoter (<=1kb) 1 111568 112005 438 1 ENSG00000263006 ENST00000608049 0 ENST00000608049 ENSG00000263006 0 +18 346463 347342 DiffBind 0 . 879|5|5.77|3.24|2.52|6.51e-06|0.00303 Exon (ENST00000400256/ENSG00000158270, exon 1 of 1) 1 346465 400382 53918 2 ENSG00000158270 ENST00000400256 53040 ENST00000400256;ENST00000582147 ENSG00000158270;ENSG00000158270 0;0 +18 399013 400382 DiffBind 0 . 1369|7.62|7|8.05|-1.04|1.04e-05|0.00364 Promoter (<=1kb) 1 346465 400382 53918 2 ENSG00000158270 ENST00000400256 0 ENST00000400256;ENST00000582147 ENSG00000158270;ENSG00000158270 0;0 +18 371109 372102 DiffBind 0 . 993|4.63|3.07|5.36|-2.3|8.1e-05|0.0226 Intron (ENST00000400256/ENSG00000158270, intron 1 of 1) 1 346465 400382 53918 2 ENSG00000158270 ENST00000400256 28280 ENST00000400256;ENST00000582147 ENSG00000158270;ENSG00000158270 0;0 |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 test-data/outint.int --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/outint.int Tue May 29 15:08:04 2018 -0400 |
| b |
| @@ -0,0 +1,6 @@ +Chrom Start End Comment +18 394599 396513 DiffBind|0|.|1914|7.15|5.55|7.89|-2.35|7.06e-24|9.84e-21|Intron (ENST00000400256/ENSG00000158270, intron 1 of 1)|1|346465|400382|53918|2|ENSG00000158270|ENST00000400256| 3869 +18 111566 112005 DiffBind|0|.|439|5.71|6.53|3.63|2.89|1.27e-08|8.88e-06|Promoter (<=1kb)|1|111568|112005| 438|1|ENSG00000263006|ENST00000608049| 0 +18 346463 347342 DiffBind|0|.|879|5|5.77|3.24|2.52|6.51e-06|0.00303|Exon (ENST00000400256/ENSG00000158270, exon 1 of 1)|1|346465|400382|53918|2|ENSG00000158270|ENST00000400256|53040 +18 399013 400382 DiffBind|0|.|1369|7.62|7|8.05|-1.04|1.04e-05|0.00364|Promoter (<=1kb)|1|346465|400382|53918|2|ENSG00000158270|ENST00000400256| 0 +18 371109 372102 DiffBind|0|.|993|4.63|3.07|5.36|-2.3|8.1e-05|0.0226|Intron (ENST00000400256/ENSG00000158270, intron 1 of 1)|1|346465|400382|53918|2|ENSG00000158270|ENST00000400256|28280 |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 test-data/outint.tab --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/outint.tab Tue May 29 15:08:04 2018 -0400 |
| b |
| @@ -0,0 +1,6 @@ +Chrom Start End Name Score Strand Comment annotation geneChr geneStart geneEnd geneLength geneStrand geneId transcriptId distanceToTSS +18 394599 396513 DiffBind 0 . 1914|7.15|5.55|7.89|-2.35|7.06e-24|9.84e-21 Intron (ENST00000400256/ENSG00000158270, intron 1 of 1) 1 346465 400382 53918 2 ENSG00000158270 ENST00000400256 3869 +18 111566 112005 DiffBind 0 . 439|5.71|6.53|3.63|2.89|1.27e-08|8.88e-06 Promoter (<=1kb) 1 111568 112005 438 1 ENSG00000263006 ENST00000608049 0 +18 346463 347342 DiffBind 0 . 879|5|5.77|3.24|2.52|6.51e-06|0.00303 Exon (ENST00000400256/ENSG00000158270, exon 1 of 1) 1 346465 400382 53918 2 ENSG00000158270 ENST00000400256 53040 +18 399013 400382 DiffBind 0 . 1369|7.62|7|8.05|-1.04|1.04e-05|0.00364 Promoter (<=1kb) 1 346465 400382 53918 2 ENSG00000158270 ENST00000400256 0 +18 371109 372102 DiffBind 0 . 993|4.63|3.07|5.36|-2.3|8.1e-05|0.0226 Intron (ENST00000400256/ENSG00000158270, intron 1 of 1) 1 346465 400382 53918 2 ENSG00000158270 ENST00000400256 28280 |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 test-data/outtss.tab --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/outtss.tab Tue May 29 15:08:04 2018 -0400 |
| b |
| @@ -0,0 +1,6 @@ +Chrom Start End Name Score Strand Comment annotation geneChr geneStart geneEnd geneLength geneStrand geneId transcriptId distanceToTSS +18 394599 396513 DiffBind 0 . 1914|7.15|5.55|7.89|-2.35|7.06e-24|9.84e-21 Intron (ENST00000400256/ENSG00000158270, intron 1 of 1) 1 346465 400382 53918 2 ENSG00000158270 ENST00000400256 3869 +18 111566 112005 DiffBind 0 . 439|5.71|6.53|3.63|2.89|1.27e-08|8.88e-06 Promoter 1 111568 112005 438 1 ENSG00000263006 ENST00000608049 0 +18 346463 347342 DiffBind 0 . 879|5|5.77|3.24|2.52|6.51e-06|0.00303 Exon (ENST00000400256/ENSG00000158270, exon 1 of 1) 1 346465 400382 53918 2 ENSG00000158270 ENST00000400256 53040 +18 399013 400382 DiffBind 0 . 1369|7.62|7|8.05|-1.04|1.04e-05|0.00364 Promoter 1 346465 400382 53918 2 ENSG00000158270 ENST00000400256 0 +18 371109 372102 DiffBind 0 . 993|4.63|3.07|5.36|-2.3|8.1e-05|0.0226 Intron (ENST00000400256/ENSG00000158270, intron 1 of 1) 1 346465 400382 53918 2 ENSG00000158270 ENST00000400256 28280 |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 tool-data/gene_sets.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/gene_sets.loc.sample Tue May 29 15:08:04 2018 -0400 |
| b |
| @@ -0,0 +1,15 @@ +# This is a sample file distributed with featureCounts that enables it and other# tools to use gene/exon annotations in the GFF/GTF format. +# +# The gene_sets.loc file syntax is: +#<unique_build_id> <dbkey> <display_name> <path> +# +# Please ensure that the above fields are tab separated. +# +# In case you have TWO or MORE providers PER dbkey, the one mentioned +# first in the file, should have the "default" priority. +# +#Example: +# +#Homo_sapiens.GRCh38.90 hg38 GRCh38 (hg38) annotation from Ensembl, release 90 /depot/data2/galaxy/hg38/gene_sets/Homo_sapiens.GRCh38.90.gtf +#Homo_sapiens.GRCh37.87 hg19 GRCh37 (hg19) annotation from Ensembl, release 87 /depot/data2/galaxy/hg19/gene_sets/Homo_sapiens.GRCh37.87.gtf + |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 tool_data_table_conf.xml.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Tue May 29 15:08:04 2018 -0400 |
| b |
| @@ -0,0 +1,7 @@ +<tables> + <!-- Locations of all gtf files with annotations of genome builds --> + <table name="gene_sets" comment_char="#" allow_duplicate_entries="False"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/gene_sets.loc" /> + </table> +</tables> |
| b |
| diff -r 58ef4507ce5a -r 95f779f4adb7 tool_data_table_conf.xml.test --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.test Tue May 29 15:08:04 2018 -0400 |
| b |
| @@ -0,0 +1,6 @@ +<tables> + <table name="gene_sets" comment_char="#"> + <columns>value, dbkey, name, path</columns> + <file path="${__HERE__}/test-data/cached_locally/gene_sets.loc" /> + </table> +</tables> |