Previous changeset 12:76d290331481 (2017-11-09) Next changeset 14:eafd5dc95228 (2018-05-04) |
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/stringtie commit e811a7887db870f4f94f620f52bce656c8d5ba23 |
modified:
stringtie.xml |
added:
test-data/gene_counts_deseq2.tsv test-data/gene_counts_edger.tsv test-data/legend.tsv test-data/transcript_counts_deseq2.tsv test-data/transcript_counts_edger.tsv |
removed:
test-data/deseq2/gene_counts.tsv test-data/deseq2/legend.tsv test-data/deseq2/transcript_counts.tsv |
b |
diff -r 76d290331481 -r a305d75e13f2 stringtie.xml --- a/stringtie.xml Thu Nov 09 11:17:32 2017 -0500 +++ b/stringtie.xml Thu Apr 12 17:30:07 2018 -0400 |
[ |
b'@@ -1,4 +1,4 @@\n-<tool id="stringtie" name="StringTie" version="1.3.3.1">\n+<tool id="stringtie" name="StringTie" version="1.3.3.2">\n <description>transcript assembly and quantification</description>\n <macros>\n <import>macros.xml</import>\n@@ -7,6 +7,7 @@\n <expand macro="stdio" />\n <expand macro="version_command" />\n <command><![CDATA[\n+#import re\n mkdir -p ./special_de_output/sample1/ &&\n \n ## Get Guide GTF/GFF if selected\n@@ -62,40 +63,49 @@\n \n #if str($guide.use_guide) == \'yes\':\n #if $guide.special_outputs.special_outputs_select == \'deseq2\':\n+ #set escaped_element_identifier = re.sub(\'[^\\w\\-]\', \'_\', str($input_bam.element_identifier))\n &&\n ln -s \'$output_gtf\' ./special_de_output/sample1/output.gtf\n &&\n+ TAB=\\$(printf \'\\t\')\n+ &&\n+ CR=\\$(printf \'\\r\')\n+ &&\n prepDE.py\n- -i ./special_de_output/\n- -g \'$gene_counts\'\n- -t \'$transcript_counts\'\n- -l $guide.special_outputs.read_length\n- #if $guide.special_outputs.string:\n- -s \'$guide.special_outputs.string\'\n+ -i ./special_de_output/\n+ -g gene_counts.csv\n+ -t transcript_counts.csv\n+ -l $guide.special_outputs.read_length\n+ #if $guide.special_outputs.string:\n+ -s \'$guide.special_outputs.string\'\n+ #end if\n+ #if $guide.special_outputs.clustering:\n+ -c\n+ #if $guide.special_outputs.key:\n+ -k \'$guide.special_outputs.key\'\n #end if\n- #if $guide.special_outputs.clustering:\n- -c\n- #if $guide.special_outputs.key:\n- -k \'$guide.special_outputs.key\'\n- #end if\n- --legend \'$legend\'\n- > /dev/null\n- &&\n- sed -i.bak \'s/,/\\t/g\' \'$legend\'\n- &&\n- sed -i.bak \'s/\\r//g\' \'$legend\'\n- #end if\n+ --legend \'$legend\'\n+ > /dev/null\n+ &&\n+ sed -i.bak -e "s/,/\\${TAB}/g" -e "s/\\${CR}//g" \'$legend\'\n+ #else\n+ > /dev/null\n+ #end if\n \n- > /dev/null\n-\n- &&\n- sed -i.bak \'s/,/\\t/g\' \'$transcript_counts\'\n+ ## Replace commas with tabs\n &&\n- sed -i.bak \'s/\\r//g\' \'$transcript_counts\'\n+ sed -i.bak -e "s/,/\\${TAB}/g" -e "s/\\${CR}//g" gene_counts.csv transcript_counts.csv\n+ #if $guide.special_outputs.keep_header:\n+ &&\n+ head -n 1 gene_counts.csv | sed -e \'s/sample1/$escaped_element_identifier/\' > \'$gene_counts\'\n+ &&\n+ head -n 1 transcript_counts.csv | sed -e \'s/sample1/$escaped_element_identifier/\' > \'$transcript_counts\'\n+ #end if\n+ ## Sort count files on the first column\n &&\n- sed -i.bak \'s/,/\\t/g\' \'$gene_counts\'\n+ tail -n +2 gene_counts.csv | sort -t"\\${TAB}" -k1 >> \'$gene_counts\'\n &&\n- sed -i.bak \'s/\\r//g\' \'$gene_counts\'\n+ tail -n +2 transcript_counts.csv | sort -t"\\${TAB}" -k1 >> \'$transcript_counts\'\n #end if\n #end if\n ]]></command>\n@@ -141,7 +151,7 @@\n <when value="ballgown" />\n <when value="deseq2">\n <param name="read_length" argument="--length" type="integer" min="0" value="75" label="Specify the average read length" help="Default: 75" />\n- <param name="clustering" argument="--cluster" type="boolean" truevalue="--cluster" falsevalue="" checked="False" label="Cluster overlapping genes" help="Choose whether to cluster genes with different gene IDs that overlap. Transcripts containing the geneID prefix will be ignored. Default: No" />\n+ <param name="clustering" argument="--cluster" type="boolean" truevalue="--cluster" falsevalue="" checked="false" label="Cluster overlapping genes" help="Choose whether to cluster genes with different gene IDs that ov'..b'aram>\n+ <param name="keep_header" type="boolean" checked="true" label="Output header line?" help="Keep the header line for edgeR, remove it for DESeq2" />\n </when>\n <when value="no" />\n </conditional>\n- <param name="coverage_file" argument="-C" type="boolean" truevalue="-C" falsevalue="" checked="False" label="Output coverage file?" help="If StringTie is run with this option (requires -G), it returns a file with all the transcripts in the reference annotation that are fully covered, end to end, by reads. The output format is a GTF file as described below. Each line of the GTF is corresponds to a gene or transcript in the reference annotation. Default: No"/>\n+ <param name="coverage_file" argument="-C" type="boolean" truevalue="-C" falsevalue="" checked="False" label="Output coverage file?" help="If StringTie is run with this option (requires -G), it returns a file with all the transcripts in the reference annotation that are fully covered, end to end, by reads. The output format is a GTF file as described below. Each line of the GTF is corresponds to a gene or transcript in the reference annotation. Default: No"/>\n </when>\n </conditional>\n <section name="adv" title="Advanced Options">\n@@ -260,7 +271,7 @@\n <output name="output_gtf" file="stringtie_out5.gtf" ftype="gtf" lines_diff="2" />\n <output name="coverage" file="stringtie_out_coverage.gtf" ftype="gtf" />\n </test>\n- <!--Ensure output for DESeq2/edgeR works -->\n+ <!--Ensure output for edgeR works -->\n <test expect_num_outputs="5">\n <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />\n <param name="use_guide" value="yes" />\n@@ -270,9 +281,26 @@\n <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />\n <param name="coverage_file" value="True" />\n <param name="clustering" value="True" />\n- <output name="gene_counts" file="./deseq2/gene_counts.tsv" ftype="tabular" />\n- <output name="transcript_counts" file="./deseq2/transcript_counts.tsv" ftype="tabular" />\n- <output name="legend" file="./deseq2/legend.tsv" ftype="tabular" />\n+ <output name="gene_counts" file="gene_counts_edger.tsv" ftype="tabular" />\n+ <output name="transcript_counts" file="transcript_counts_edger.tsv" ftype="tabular" />\n+ <output name="legend" file="legend.tsv" ftype="tabular" />\n+ <output name="output_gtf" file="stringtie_out6.gtf" ftype="gtf" lines_diff="2" />\n+ <output name="coverage" file="stringtie_out_coverage.gtf" ftype="gtf" />\n+ </test>\n+ <!--Ensure output for DESeq2 works -->\n+ <test expect_num_outputs="5">\n+ <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />\n+ <param name="use_guide" value="yes" />\n+ <param name="special_outputs_select" value="deseq2" />\n+ <param name="keep_header" value="False" />\n+ <param name="input_estimation" value="True" />\n+ <param name="guide_gff_select" value="history" />\n+ <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />\n+ <param name="coverage_file" value="True" />\n+ <param name="clustering" value="True" />\n+ <output name="gene_counts" file="gene_counts_deseq2.tsv" ftype="tabular" />\n+ <output name="transcript_counts" file="transcript_counts_deseq2.tsv" ftype="tabular" />\n+ <output name="legend" file="legend.tsv" ftype="tabular" />\n <output name="output_gtf" file="stringtie_out6.gtf" ftype="gtf" lines_diff="2" />\n <output name="coverage" file="stringtie_out_coverage.gtf" ftype="gtf" />\n </test>\n@@ -474,4 +502,4 @@\n \n ]]></help>\n <expand macro="citations" />\n-</tool>\n\\ No newline at end of file\n+</tool>\n' |
b |
diff -r 76d290331481 -r a305d75e13f2 test-data/deseq2/gene_counts.tsv --- a/test-data/deseq2/gene_counts.tsv Thu Nov 09 11:17:32 2017 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
b |
@@ -1,2 +0,0 @@ -gene_id sample1 -CUFF.1 182 |
b |
diff -r 76d290331481 -r a305d75e13f2 test-data/deseq2/transcript_counts.tsv --- a/test-data/deseq2/transcript_counts.tsv Thu Nov 09 11:17:32 2017 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
b |
@@ -1,2 +0,0 @@ -transcript_id sample1 -CUFF.1.1 182 |
b |
diff -r 76d290331481 -r a305d75e13f2 test-data/gene_counts_deseq2.tsv --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/gene_counts_deseq2.tsv Thu Apr 12 17:30:07 2018 -0400 |
b |
@@ -0,0 +1,1 @@ +CUFF.1 182 |
b |
diff -r 76d290331481 -r a305d75e13f2 test-data/gene_counts_edger.tsv --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/gene_counts_edger.tsv Thu Apr 12 17:30:07 2018 -0400 |
b |
@@ -0,0 +1,2 @@ +gene_id stringtie_in1_bam +CUFF.1 182 |
b |
diff -r 76d290331481 -r a305d75e13f2 test-data/transcript_counts_deseq2.tsv --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/transcript_counts_deseq2.tsv Thu Apr 12 17:30:07 2018 -0400 |
b |
@@ -0,0 +1,1 @@ +CUFF.1.1 182 |
b |
diff -r 76d290331481 -r a305d75e13f2 test-data/transcript_counts_edger.tsv --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/transcript_counts_edger.tsv Thu Apr 12 17:30:07 2018 -0400 |
b |
@@ -0,0 +1,2 @@ +transcript_id stringtie_in1_bam +CUFF.1.1 182 |