| Previous changeset 14:eafd5dc95228 (2018-05-04) Next changeset 16:eba36e001f45 (2019-05-03) |
|
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/stringtie commit a834a41c94d184df80e45ffa2339723826a075b1 |
|
modified:
macros.xml stringtie.xml stringtie_merge.xml test-data/stringtie_merge_out1.gtf test-data/stringtie_merge_out2.gtf test-data/stringtie_out1.gtf test-data/stringtie_out2.gtf test-data/stringtie_out3.gtf test-data/stringtie_out4.gtf test-data/stringtie_out5.gtf test-data/stringtie_out6.gtf test-data/stringtie_out8.gtf |
|
removed:
test-data/gene_counts_deseq2.tsv test-data/transcript_counts_deseq2.tsv |
| b |
| diff -r eafd5dc95228 -r dd4df992d93d macros.xml --- a/macros.xml Fri May 04 08:37:37 2018 -0400 +++ b/macros.xml Tue Jul 24 10:23:37 2018 -0400 |
| b |
| @@ -1,8 +1,9 @@ <macros> + <token name="@TOOL_VERSION@">1.3.4</token> <xml name="requirements"> <requirements> - <requirement type="package" version="1.3.3">stringtie</requirement> - <requirement type="package" version="1.6">samtools</requirement> + <requirement type="package" version="@TOOL_VERSION@">stringtie</requirement> + <requirement type="package" version="1.9">samtools</requirement> <yield/> </requirements> </xml> |
| b |
| diff -r eafd5dc95228 -r dd4df992d93d stringtie.xml --- a/stringtie.xml Fri May 04 08:37:37 2018 -0400 +++ b/stringtie.xml Tue Jul 24 10:23:37 2018 -0400 |
| b |
| b'@@ -1,4 +1,4 @@\n-<tool id="stringtie" name="StringTie" version="1.3.3.2">\n+<tool id="stringtie" name="StringTie" version="@TOOL_VERSION@">\n <description>transcript assembly and quantification</description>\n <macros>\n <import>macros.xml</import>\n@@ -95,12 +95,11 @@\n ## Replace commas with tabs\n &&\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/\' > \'$transcript_counts\'\n- #end if\n+ ## Output header\n+ &&\n+ head -n 1 gene_counts.csv | sed -e \'s/sample1/$escaped_element_identifier/\' > \'$gene_counts\'\n+ &&\n+ head -n 1 transcript_counts.csv | sed -e \'s/sample1/$escaped_element_identifier/\' > \'$transcript_counts\'\n ## Sort count files on the first column\n &&\n tail -n +2 gene_counts.csv | sort -t"\\${TAB}" -k1,1 >> \'$gene_counts\'\n@@ -145,7 +144,7 @@\n <conditional name="special_outputs">\n <param name="special_outputs_select" type="select" label="Output files for differential expression?" help="Select to output additional files that can be used with Ballgown or DESeq2/edgeR. See Help section below for more information">\n <option value="ballgown">Ballgown</option>\n- <option value="deseq2">DESeq2/edgeR</option>\n+ <option value="deseq2">DESeq2/edgeR/limma-voom</option>\n <option value="no" selected="True">No additional output</option>\n </param>\n <when value="ballgown" />\n@@ -162,7 +161,6 @@\n <valid initial="string.letters,string.digits"></valid>\n </sanitizer>\n </param>\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@@ -230,13 +228,13 @@\n <!--Ensure default GTF output works -->\n <test expect_num_outputs="1">\n <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />\n- <output name="output_gtf" file="stringtie_out1.gtf" ftype="gtf" lines_diff="2" />\n+ <output name="output_gtf" file="stringtie_out1.gtf" ftype="gtf" lines_diff="4" />\n </test>\n <!--Ensure fraction option works -->\n <test expect_num_outputs="1">\n <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />\n <param name="fraction" value="0.17" />\n- <output name="output_gtf" file="stringtie_out2.gtf" ftype="gtf" lines_diff="2" />\n+ <output name="output_gtf" file="stringtie_out2.gtf" ftype="gtf" lines_diff="4" />\n </test>\n <!--Ensure guide option works -->\n <test expect_num_outputs="1">\n@@ -244,7 +242,7 @@\n <param name="use_guide" value="yes" />\n <param name="guide_gff_select" value="history" />\n <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />\n- <output name="output_gtf" file="stringtie_out3.gtf" ftype="gtf" lines_diff="2" />\n+ <output name="output_gtf" file="stringtie_out3.gtf" ftype="gtf" lines_diff="4" />\n </test>\n <!--Ensure guide with fraction works -->\n <test expect_num_outputs="1">\n@@ -253,7 +251,7 @@\n <param name="guide_gff_select" value="history" />\n <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />\n <param name="fraction" value="0.17" />\n- <output name="output_gtf" file="stringti'..b'ngTie can be used for estimating differential expression across multiple RNA-Seq samples and generating plots and differential expression tables as described in our `protocol paper`_ and shown in a diagram in the `StringTie manual here`_.\n \n Our recommended workflow includes the following steps:\n \n@@ -477,9 +458,9 @@\n \n 3. Run the separate **StringTie merge** tool in order to generate a non-redundant set of transcripts observed in all the RNA-Seq samples assembled previously. ``StringTie merge`` takes as input a list of all the assembled transcripts files (in GTF format) previously obtained for each sample, as well as a reference annotation file (-G option) if available.\n \n- 4. For each RNA-Seq sample, run this StringTie tool selecting to output files for Ballgown (or DESeq2/edgeR), which will generate tables of transcript and gene estimated abundances (count files). The option -e (*Use Reference transcripts only*) is not required but is recommended for this run in order to produce more accurate abundance estimations of the input transcripts. Each StringTie run in this step will take as input the sorted read alignments (BAM file) obtained in step 1 for the corresponding sample and the -G option with the merged transcripts (GTF file) generated by ``stringtie merge`` in step 3. Please note that this is the only case where the -G option is not used with a reference annotation, but with the global, merged set of transcripts as observed across all samples. (This step is the equivalent of the *Tablemaker* step described in the original Ballgown pipeline.)\n+ 4. For each RNA-Seq sample, run this StringTie tool selecting to output files for Ballgown (or DESeq2/edgeR/limma-voom), which will generate tables of transcript and gene estimated abundances (count files). The option -e (*Use Reference transcripts only*) is not required but is recommended for this run in order to produce more accurate abundance estimations of the input transcripts. Each StringTie run in this step will take as input the sorted read alignments (BAM file) obtained in step 1 for the corresponding sample and the -G option with the merged transcripts (GTF file) generated by ``stringtie merge`` in step 3. Please note that this is the only case where the -G option is not used with a reference annotation, but with the global, merged set of transcripts as observed across all samples. (This step is the equivalent of the *Tablemaker* step described in the original Ballgown pipeline.)\n \n- 5. Ballgown (or DESeq2/edgeR) can now be used to load the coverage tables generated in the previous step and perform various statistical analyses for differential expression, generate plots etc.\n+ 5. Ballgown (or DESeq2/edgeR/limma-voom) can now be used to load the coverage tables generated in the previous step and perform various statistical analyses for differential expression, generate plots etc.\n \n An alternate, faster differential expression analysis workflow can be pursued if there is no interest in novel isoforms (i.e. assembled transcripts present in the samples but missing from the reference annotation), or if only a well known set of transcripts of interest are targeted by the analysis. This simplified protocol has only 3 steps (depicted in the `StringTie manual here`_) as it bypasses the individual assembly of each RNA-Seq sample and the "transcript merge" step. This simplified workflow attempts to directly estimate and analyze the expression of a known set of transcripts as given in the reference annotation file.\n \n@@ -488,6 +469,7 @@\n .. _Cuffdiff: http://cole-trapnell-lab.github.io/cufflinks/cuffdiff/\n .. _DESeq2: https://bioconductor.org/packages/release/bioc/html/DESeq2.html\n .. _edgeR: https://bioconductor.org/packages/release/bioc/html/edgeR.html\n+.. _limma: https://bioconductor.org/packages/release/bioc/html/limma.html\n .. _Bioconductor: https://www.bioconductor.org/\n .. _SAM: http://samtools.github.io/hts-specs/SAMv1.pdf\n .. _HISAT2: http://ccb.jhu.edu/software/hisat2\n' |
| b |
| diff -r eafd5dc95228 -r dd4df992d93d stringtie_merge.xml --- a/stringtie_merge.xml Fri May 04 08:37:37 2018 -0400 +++ b/stringtie_merge.xml Tue Jul 24 10:23:37 2018 -0400 |
| b |
| @@ -1,4 +1,4 @@ -<tool id="stringtie_merge" name="StringTie merge" version="1.3.3"> +<tool id="stringtie_merge" name="StringTie merge" version="@TOOL_VERSION@"> <description>transcripts</description> <macros> <import>macros.xml</import> @@ -40,12 +40,12 @@ <test> <param name="input_gtf" ftype="gtf" value="stringtie_out1.gtf,stringtie_out2.gtf,stringtie_out3.gtf,stringtie_out4.gtf" /> <param name="guide_gff" ftype="gtf" value="stringtie_in.gtf" /> - <output name="out_gtf" file="stringtie_merge_out1.gtf" ftype="gtf" lines_diff="2" /> + <output name="out_gtf" file="stringtie_merge_out1.gtf" ftype="gtf" lines_diff="4" /> </test> <test> <param name="input_gtf" ftype="gtf" value="stringtie_merge_in1.gtf,stringtie_merge_in2.gtf" /> <param name="guide_gff" ftype="gtf" value="stringtie_merge_in3.gtf" /> - <output name="out_gtf" file="stringtie_merge_out2.gtf" ftype="gtf" lines_diff="2" /> + <output name="out_gtf" file="stringtie_merge_out2.gtf" ftype="gtf" lines_diff="4" /> </test> <test> <param name="input_gtf" ftype="gtf" value="stringtie_merge_in1.gtf,stringtie_merge_in2.gtf" /> |
| b |
| diff -r eafd5dc95228 -r dd4df992d93d test-data/gene_counts_deseq2.tsv --- a/test-data/gene_counts_deseq2.tsv Fri May 04 08:37:37 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,1 +0,0 @@ -CUFF.1 182 |
| b |
| diff -r eafd5dc95228 -r dd4df992d93d test-data/stringtie_merge_out1.gtf --- a/test-data/stringtie_merge_out1.gtf Fri May 04 08:37:37 2018 -0400 +++ b/test-data/stringtie_merge_out1.gtf Tue Jul 24 10:23:37 2018 -0400 |
| b |
| @@ -1,5 +1,5 @@ # stringtie --merge -p 1 -G /tmp/tmpJfKWNy/files/000/dataset_42.dat -m 50 -c 0 -F 1.0 -T 1.0 -f 0.01 -g 250 -o /tmp/tmpJfKWNy/files/000/dataset_43.dat /tmp/tmpJfKWNy/files/000/dataset_38.dat /tmp/tmpJfKWNy/files/000/dataset_39.dat /tmp/tmpJfKWNy/files/000/dataset_40.dat /tmp/tmpJfKWNy/files/000/dataset_41.dat -# StringTie version 1.3.3 +# StringTie version 1.3.4d test_chromosome StringTie transcript 53 550 1000 + . gene_id "MSTRG.1"; transcript_id "CUFF.1.1"; ref_gene_id "CUFF.1"; test_chromosome StringTie exon 53 250 1000 + . gene_id "MSTRG.1"; transcript_id "CUFF.1.1"; exon_number "1"; ref_gene_id "CUFF.1"; test_chromosome StringTie exon 351 400 1000 + . gene_id "MSTRG.1"; transcript_id "CUFF.1.1"; exon_number "2"; ref_gene_id "CUFF.1"; |
| b |
| diff -r eafd5dc95228 -r dd4df992d93d test-data/stringtie_merge_out2.gtf --- a/test-data/stringtie_merge_out2.gtf Fri May 04 08:37:37 2018 -0400 +++ b/test-data/stringtie_merge_out2.gtf Tue Jul 24 10:23:37 2018 -0400 |
| b |
| @@ -1,5 +1,5 @@ # stringtie --merge -p 1 -G /tmp/tmpJfKWNy/files/000/dataset_46.dat -m 50 -c 0 -F 1.0 -T 1.0 -f 0.01 -g 250 -o /tmp/tmpJfKWNy/files/000/dataset_47.dat /tmp/tmpJfKWNy/files/000/dataset_44.dat /tmp/tmpJfKWNy/files/000/dataset_45.dat -# StringTie version 1.3.3 +# StringTie version 1.3.4d chr1 StringTie transcript 3189811 3193042 1000 . . gene_id "MSTRG.1"; transcript_id "MSTRG.1.1"; chr1 StringTie exon 3189811 3193042 1000 . . gene_id "MSTRG.1"; transcript_id "MSTRG.1.1"; exon_number "1"; chr1 StringTie transcript 3200023 3200191 1000 . . gene_id "MSTRG.2"; transcript_id "MSTRG.2.1"; |
| b |
| diff -r eafd5dc95228 -r dd4df992d93d test-data/stringtie_out1.gtf --- a/test-data/stringtie_out1.gtf Fri May 04 08:37:37 2018 -0400 +++ b/test-data/stringtie_out1.gtf Tue Jul 24 10:23:37 2018 -0400 |
| b |
| @@ -1,5 +1,5 @@ # stringtie /tmp/tmpJfKWNy/files/000/dataset_1.dat -o /tmp/tmpJfKWNy/files/000/dataset_2.dat -p 1 -# StringTie version 1.3.3 +# StringTie version 1.3.4d test_chromosome StringTie transcript 53 550 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; cov "44.060520"; FPKM "3227877.000000"; TPM "962189.250000"; test_chromosome StringTie exon 53 250 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "1"; cov "48.012157"; test_chromosome StringTie exon 351 400 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "2"; cov "51.382565"; |
| b |
| diff -r eafd5dc95228 -r dd4df992d93d test-data/stringtie_out2.gtf --- a/test-data/stringtie_out2.gtf Fri May 04 08:37:37 2018 -0400 +++ b/test-data/stringtie_out2.gtf Tue Jul 24 10:23:37 2018 -0400 |
| b |
| @@ -1,5 +1,5 @@ # stringtie /tmp/tmpJfKWNy/files/000/dataset_3.dat -o /tmp/tmpJfKWNy/files/000/dataset_4.dat -p 1 -l STRG -f 0.17 -m 200 -a 10 -j 1 -c 2 -g 50 -M 0.95 -# StringTie version 1.3.3 +# StringTie version 1.3.4d test_chromosome StringTie transcript 53 550 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; cov "44.060520"; FPKM "3227877.000000"; TPM "962189.250000"; test_chromosome StringTie exon 53 250 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "1"; cov "48.012157"; test_chromosome StringTie exon 351 400 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "2"; cov "51.382565"; |
| b |
| diff -r eafd5dc95228 -r dd4df992d93d test-data/stringtie_out3.gtf --- a/test-data/stringtie_out3.gtf Fri May 04 08:37:37 2018 -0400 +++ b/test-data/stringtie_out3.gtf Tue Jul 24 10:23:37 2018 -0400 |
| b |
| @@ -1,5 +1,5 @@ # stringtie /tmp/tmpJfKWNy/files/000/dataset_5.dat -o /tmp/tmpJfKWNy/files/000/dataset_7.dat -p 1 -C /tmp/tmpJfKWNy/files/000/dataset_8.dat -G /tmp/tmpJfKWNy/files/000/dataset_6.dat -b ./special_de_output/sample1/ -# StringTie version 1.3.3 +# StringTie version 1.3.4d test_chromosome StringTie transcript 53 550 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; reference_id "CUFF.1.1"; ref_gene_id "CUFF.1"; cov "44.070122"; FPKM "3228580.250000"; TPM "962398.937500"; test_chromosome StringTie exon 53 250 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "1"; reference_id "CUFF.1.1"; ref_gene_id "CUFF.1"; cov "48.005386"; test_chromosome StringTie exon 351 400 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "2"; reference_id "CUFF.1.1"; ref_gene_id "CUFF.1"; cov "51.452003"; |
| b |
| diff -r eafd5dc95228 -r dd4df992d93d test-data/stringtie_out4.gtf --- a/test-data/stringtie_out4.gtf Fri May 04 08:37:37 2018 -0400 +++ b/test-data/stringtie_out4.gtf Tue Jul 24 10:23:37 2018 -0400 |
| b |
| @@ -1,5 +1,5 @@ # stringtie /tmp/tmpJfKWNy/files/000/dataset_28.dat -o /tmp/tmpJfKWNy/files/000/dataset_30.dat -p 1 -C /tmp/tmpJfKWNy/files/000/dataset_32.dat -G /tmp/tmpJfKWNy/files/000/dataset_29.dat -b ./special_de_output/sample1/ -l STRG -f 0.17 -m 200 -a 10 -j 1 -c 2 -g 50 -M 0.95 -A /tmp/tmpJfKWNy/files/000/dataset_31.dat -# StringTie version 1.3.3 +# StringTie version 1.3.4d test_chromosome StringTie transcript 53 550 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; reference_id "CUFF.1.1"; ref_gene_id "CUFF.1"; cov "44.070122"; FPKM "3228580.250000"; TPM "962398.937500"; test_chromosome StringTie exon 53 250 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "1"; reference_id "CUFF.1.1"; ref_gene_id "CUFF.1"; cov "48.005386"; test_chromosome StringTie exon 351 400 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "2"; reference_id "CUFF.1.1"; ref_gene_id "CUFF.1"; cov "51.452003"; |
| b |
| diff -r eafd5dc95228 -r dd4df992d93d test-data/stringtie_out5.gtf --- a/test-data/stringtie_out5.gtf Fri May 04 08:37:37 2018 -0400 +++ b/test-data/stringtie_out5.gtf Tue Jul 24 10:23:37 2018 -0400 |
| b |
| @@ -1,5 +1,5 @@ # stringtie /tmp/tmpJfKWNy/files/000/dataset_13.dat -o /tmp/tmpJfKWNy/files/000/dataset_15.dat -p 1 -C /tmp/tmpJfKWNy/files/000/dataset_16.dat -G /tmp/tmpJfKWNy/files/000/dataset_14.dat -b ./special_de_output/sample1/ -# StringTie version 1.3.3 +# StringTie version 1.3.4d test_chromosome StringTie transcript 53 550 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; reference_id "CUFF.1.1"; ref_gene_id "CUFF.1"; cov "44.070122"; FPKM "3228580.250000"; TPM "962398.937500"; test_chromosome StringTie exon 53 250 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "1"; reference_id "CUFF.1.1"; ref_gene_id "CUFF.1"; cov "48.005386"; test_chromosome StringTie exon 351 400 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "2"; reference_id "CUFF.1.1"; ref_gene_id "CUFF.1"; cov "51.452003"; |
| b |
| diff -r eafd5dc95228 -r dd4df992d93d test-data/stringtie_out6.gtf --- a/test-data/stringtie_out6.gtf Fri May 04 08:37:37 2018 -0400 +++ b/test-data/stringtie_out6.gtf Tue Jul 24 10:23:37 2018 -0400 |
| b |
| @@ -1,5 +1,5 @@ # stringtie /tmp/tmpSoPTYX/files/000/dataset_1.dat -o /tmp/tmpSoPTYX/files/000/dataset_3.dat -p 1 -G guide.gff -C /tmp/tmpSoPTYX/files/000/dataset_4.dat -e -b ./special_de_output/sample1/ -f 0.15 -m 200 -a 10 -j 1 -c 2 -g 50 -M 0.95 -# StringTie version 1.3.3 +# StringTie version 1.3.4d test_chromosome StringTie transcript 53 550 1000 + . gene_id "CUFF.1"; transcript_id "CUFF.1.1"; cov "45.795296"; FPKM "3354966.750000"; TPM "1000000.000000"; test_chromosome StringTie exon 53 250 1000 + . gene_id "CUFF.1"; transcript_id "CUFF.1.1"; exon_number "1"; cov "49.777779"; test_chromosome StringTie exon 351 400 1000 + . gene_id "CUFF.1"; transcript_id "CUFF.1.1"; exon_number "2"; cov "54.160004"; |
| b |
| diff -r eafd5dc95228 -r dd4df992d93d test-data/stringtie_out8.gtf --- a/test-data/stringtie_out8.gtf Fri May 04 08:37:37 2018 -0400 +++ b/test-data/stringtie_out8.gtf Tue Jul 24 10:23:37 2018 -0400 |
| b |
| @@ -1,5 +1,5 @@ # stringtie /tmp/tmpJfKWNy/files/000/dataset_34.dat -o /tmp/tmpJfKWNy/files/000/dataset_36.dat -p 1 -C /tmp/tmpJfKWNy/files/000/dataset_37.dat -G /tmp/tmpJfKWNy/files/000/dataset_35.dat -b ./special_de_output/sample1/ -l STRG -f 0.15 -m 200 -a 10 -j 1 -c 2 -g 50 -M 0.95 -# StringTie version 1.3.3 +# StringTie version 1.3.4d test_chromosome StringTie transcript 53 550 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; reference_id "CUFF.1.1"; ref_gene_id "CUFF.1"; cov "44.070122"; FPKM "3228580.250000"; TPM "962398.937500"; test_chromosome StringTie exon 53 250 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "1"; reference_id "CUFF.1.1"; ref_gene_id "CUFF.1"; cov "48.005386"; test_chromosome StringTie exon 351 400 1000 + . gene_id "STRG.1"; transcript_id "STRG.1.1"; exon_number "2"; reference_id "CUFF.1.1"; ref_gene_id "CUFF.1"; cov "51.452003"; |
| b |
| diff -r eafd5dc95228 -r dd4df992d93d test-data/transcript_counts_deseq2.tsv --- a/test-data/transcript_counts_deseq2.tsv Fri May 04 08:37:37 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,1 +0,0 @@ -CUFF.1.1 182 |