| Next changeset 1:74af9ab1a154 (2022-07-26) |
|
Commit message:
"planemo upload for repository https://github.com/jj-umn/galaxytools/tree/master/rmats commit 315f6ba609e9545c3a374f7fd471aee50b135ec8-dirty" |
|
added:
macros.xml rmats.xml test-data/GRCh38.gtf test-data/cancer_small.bam test-data/normal_small.bam test-data/novel/summary.txt test-data/out/summary.txt test-data/rmats_testdata.tar.gz |
| b |
| diff -r 000000000000 -r ff15d6def09b macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Sat Jul 23 21:23:48 2022 +0000 |
| b |
| @@ -0,0 +1,48 @@ +<macros> + <token name="@TOOL_VERSION@">4.1.2</token> + <token name="@VERSION_SUFFIX@">0</token> + <xml name="requirements"> + <requirements> + <requirement type="package" version="@TOOL_VERSION@">rmats</requirement> + <requirement type="package" version="4.0">r-base</requirement> + <yield/> + </requirements> + </xml> + <xml name="citations"> + <citations> + <citation type="doi">10.1073/pnas.1419161111</citation> + <citation type="doi">10.1007/978-1-62703-514-9_10</citation> + <citation type="doi">10.1093/nar/gkr1291</citation> + <yield /> + </citations> + </xml> + <xml name="version_command"> + <version_command>rmats.py --version</version_command> + </xml> + + <token name="@COLNAMES_SUMMARY@">EventType,TotalEventsJC,TotalEventsJCEC,SignificantEventsJC,SigEventsJCSample1HigherInclusion,SigEventsJCSample2HigherInclusion,SignificantEventsJCEC,SigEventsJCECSample1HigherInclusion,SigEventsJCECSample2HigherInclusion</token> + <token name="@SHAREDCOLS@">ID,GeneID,geneSymbol,chr,strand</token> + <token name="@MXECOLS@">1stExonStart_0base,1stExonEnd,2ndExonStart_0base,2ndExonEnd,upstreamES,upstreamEE,downstreamES,downstreamEE</token> + <token name="@SECOLS@">exonStart_0base,exonEnd,upstreamES,upstreamEE,downstreamES,downstreamEE</token> + <token name="@ACOLS@">longExonStart_0base,longExonEnd,shortES,shortEE,flankingES,flankingEE</token> + <token name="@RICOLS@">riExonStart_0base,riExonEnd,upstreamES,upstreamEE,downstreamES,downstreamEE</token> + <token name="@CNTCOLS@">ID,IJC_SAMPLE_1,SJC_SAMPLE_1,IJC_SAMPLE_2,SJC_SAMPLE_2,IncFormLen,SkipFormLen</token> + <token name="@STATCOLS@">PValue,FDR,IncLevel1,IncLevel2,IncLevelDifference</token> + <token name="@SAMPLECOLS@">@CNTCOLS@,@STATCOLS@</token> + <token name="@COLNAMES_MXE_GTF@">@SHAREDCOLS@,@MXECOLS@</token> + <token name="@COLNAMES_MXE@">@SHAREDCOLS@,@MXECOLS@,@SAMPLECOLS@</token> + <token name="@COLNAMES_SE_GTF@">@SHAREDCOLS@,@SECOLS@</token> + <token name="@COLNAMES_SE@">@SHAREDCOLS@,@SECOLS@,@SAMPLECOLS@</token> + <token name="@COLNAMES_A_SS_GTF@">@SHAREDCOLS@,@ACOLS@</token> + <token name="@COLNAMES_A_SS@">@SHAREDCOLS@,@ACOLS@,@SAMPLECOLS@</token> + <token name="@COLNAMES_RI_GTF@">@SHAREDCOLS@,@RICOLS@</token> + <token name="@COLNAMES_RI@">@SHAREDCOLS@,@RICOLS@,@SAMPLECOLS@</token> + + <xml name="output_actions" token_column_names="@COLNAME_SUMMARY@"> + <actions> + <action name="comment_lines" type="metadata" default="1" /> + <action name="column_names" type="metadata" default="@COLUMN_NAMES@" /> + </actions> + </xml> + +</macros> |
| b |
| diff -r 000000000000 -r ff15d6def09b rmats.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rmats.xml Sat Jul 23 21:23:48 2022 +0000 |
| [ |
| b'@@ -0,0 +1,269 @@\n+<tool id="rmats" name="rMats turbo" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" python_template_version="3.5">\n+ <description>detect differential alternative splicing events from RNA-Seq</description>\n+ <macros>\n+ <import>macros.xml</import>\n+ </macros>\n+ <expand macro="requirements" />\n+ <expand macro="version_command" />\n+ <command detect_errors="exit_code"><![CDATA[\n+ echo $b1 > b1.txt &&\n+ #if $b2\n+ echo $b2 > b2.txt &&\n+ #end if\n+ rmats.py \n+ --b1 b1.txt\n+ #if $b2\n+ --b1 b1.txt\n+ #end if\n+ --gtf \'$gtf\'\n+ #if $novel.novelSS == \'yes\'\n+ --novelSS\n+ #if $novel.mil\n+ --mil $novel.mil\n+ #end if\n+ #if $novel.mel\n+ --mel $novel.mel\n+ #end if\n+ #end if\n+ #if $readLength\n+ --readLength $readLength\n+ #end if\n+ $variable_read_length\n+ #if $libType\n+ --libType "$libType"\n+ #end if\n+ #if $anchorLength\n+ --anchorLength $anchorLength\n+ #end if\n+ #if $cstat\n+ --cstat $cstat\n+ #end if\n+ $paired_stats\n+ --nthread \\${GALAXY_SLOTS:-1}\n+ --tmp tmp\n+ --od outputs\n+ ]]></command>\n+ <inputs>\n+ <param name="b1" type="data" format="bam" multiple="true" label="BAM files for sample_1"/>\n+ <param name="b2" type="data" format="bam" multiple="true" optional="true" label="BAM files for sample_2"/>\n+ <param name="gtf" type="data" format="gtf" label="GTF - annotation of genes and transcripts"/>\n+\n+ <conditional name="novel">\n+ <param name="novelSS" argument="--novelSS" type="select" label="Enable detection of novel splice sites">\n+ <option value="no">No</option>\n+ <option value="yes">Yes</option>\n+ </param>\n+ <when value="no"/>\n+ <when value="yes">\n+ <param argument="--mil" type="integer" value="" optional="true" label="Minimum Intron Length" help=" Default is 50"/>\n+ <param argument="--mel" type="integer" value="" optional="true" label="Maximum Exon Length" help=" Default is 500"/>\n+ </when> \n+ </conditional>\n+ <param argument="--readLength" type="integer" value="150" label="The length of each read"/>\n+ <param name="variable_read_length" argument="--variable-read-length" type="boolean" truevalue="--variable-read-length" falsevalue="" checked="true" label="Allow reads with lengths that differ from --readLength to be processed"/>\n+\n+ <param argument="--libType" type="select" optional="true" label="Library type" \n+ help="Use fr-firststrand or fr-secondstrand for strand-specific data. Default: fr-unstranded">\n+ <option value="fr-unstranded">fr-unstranded</option>\n+ <option value="fr-firststrand">fr-firststrand</option>\n+ <option value="fr-secondstrand">fr-secondstrand</option>\n+ </param>\n+\n+ <param argument="--anchorLength" type="integer" value="" optional="true" label="The anchor length" help=" Default is 1"/>\n+\n+ <param argument="--cstat" type="float" value="" min="0." max="1." optional="true" label="The cutoff splicing difference." help="The cutoff used in the null hypothesis test for differential splicing. The default is 0.0001 for 0.01% difference. Does not apply to the paired stats model"/>\n+ <param name="paired_stats" argument="--paired-stats" type="boolean" truevalue="--paired-stats" falsevalue="" checked="true" label="Enable detection of novel splice sites"/>\n+ \n+ <param name="history_outputs" type="select" multiple="true" label="Select outputs">\n+ <option value="SE.MATS.JC.txt">SE.MATS.JC.txt</option>\n+ <option value="SE.MATS.JCEC.txt">SE.MATS.JCEC.txt</option>\n+ <option value="MXE.MATS.JC.txt">MXE.MATS.JC.txt</option>\n+'..b' <data name="MXE_MATS_JCEC" format="tabular" label="${tool.name} on ${on_string}: MXE.MATS.JCEC.txt" from_work_dir="outputs/MXE.MATS.JCEC.txt">\n+ <filter>history_outputs and \'MXE.MATS.JCEC.txt\' in history_outputs</filter>\n+ <expand macro="output_actions" column_names="@COLNAMES_MXE@"/>\n+ </data>\n+ <data name="MXE_MATS_JC" format="tabular" label="${tool.name} on ${on_string}: MXE.MATS.JC.txt" from_work_dir="outputs/MXE.MATS.JC.txt">\n+ <filter>history_outputs and \'MXE.MATS.JC.txt\' in history_outputs</filter>\n+ <expand macro="output_actions" column_names="@COLNAMES_MXE@"/>\n+ </data>\n+ <data name="RI_MATS_JCEC" format="tabular" label="${tool.name} on ${on_string}: RI.MATS.JCEC.txt" from_work_dir="outputs/RI.MATS.JCEC.txt">\n+ <filter>history_outputs and \'RI.MATS.JCEC.txt\' in history_outputs</filter>\n+ <expand macro="output_actions" column_names="@COLNAMES_RI@"/>\n+ </data>\n+ <data name="RI_MATS_JC" format="tabular" label="${tool.name} on ${on_string}: RI.MATS.JC.txt" from_work_dir="outputs/RI.MATS.JC.txt">\n+ <filter>history_outputs and \'RI.MATS.JC.txt\' in history_outputs</filter>\n+ <expand macro="output_actions" column_names="@COLNAMES_RI@"/>\n+ </data>\n+ </outputs>\n+ <tests>\n+ <test>\n+ <param name="b1" ftype="bam" value="normal_small.bam"/>\n+ <param name="b2" ftype="bam" value="cancer_small.bam"/>\n+ <param name="gtf" ftype="gtf" value="GRCh38.gtf"/>\n+ <param name="readLength" value="150"/>\n+ <param name="variable_read_length" value="True"/>\n+ <output name="summary" file="out/summary.txt" ftype="tabular"/>\n+ </test>\n+\n+ <test>\n+ <param name="b1" ftype="bam" value="normal_small.bam"/>\n+ <param name="b2" ftype="bam" value="cancer_small.bam"/>\n+ <param name="gtf" ftype="gtf" value="GRCh38.gtf"/>\n+ <param name="readLength" value="150"/>\n+ <param name="variable_read_length" value="True"/>\n+ <conditional name="novel">\n+ <param name="novelSS" value="yes"/>\n+ <param name="mil" value="40"/>\n+ </conditional> \n+ <output name="summary" file="novel/summary.txt" ftype="tabular"/>\n+ </test>\n+\n+ <test>\n+ <param name="b1" ftype="bam" value="normal_small.bam"/>\n+ <param name="b2" ftype="bam" value="cancer_small.bam"/>\n+ <param name="gtf" ftype="gtf" value="GRCh38.gtf"/>\n+ <param name="readLength" value="150"/>\n+ <param name="variable_read_length" value="True"/>\n+ <conditional name="novel">\n+ <param name="novelSS" value="yes"/>\n+ </conditional> \n+ <param name="paired_stats" value="True"/>\n+ <param name="" value="SE.MATS.JC.txt,MXE.MATS.JC.txt"/>\n+ <output name="summary">\n+ <assert_contents>\n+ <has_text_matching expression="EventType"/>\n+ </assert_contents>\n+ </output>\n+ <output name="summary" file="novel/summary.txt" ftype="tabular"/>\n+ </test>\n+\n+ </tests>\n+ <help><![CDATA[\n+** rMATS **\n+\n+RMATS is a computational tool to detect differential alternative splicing events from RNA-Seq data. The statistical model of MATS calculates the P-value and false discovery rate that the difference in the isoform ratio of a gene between two conditions exceeds a given user-defined threshold. From the RNA-Seq data, MATS can automatically detect and analyze alternative splicing events corresponding to all major types of alternative splicing patterns. MATS handles replicate RNA-Seq data from both paired and unpaired study design.\n+\n+https://github.com/Xinglab/rmats-turbo#starting-with-bam-files\n+\n+https://github.com/Xinglab/rmats-turbo#output\n+\n+ ]]></help>\n+ <expand macro="citations" />\n+</tool>\n' |
| b |
| diff -r 000000000000 -r ff15d6def09b test-data/GRCh38.gtf --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/GRCh38.gtf Sat Jul 23 21:23:48 2022 +0000 |
| b |
| b'@@ -0,0 +1,26027 @@\n+#!genome-build GRCh38.p13\n+#!genome-version GRCh38\n+#!genome-date 2013-12\n+#!genome-build-accession GCA_000001405.28\n+#!genebuild-last-updated 2021-11\n+19\tensembl_havana\tgene\t48332356\t48364059\t.\t-\t.\tgene_id "ENSG00000161558"; gene_version "11"; gene_name "TMEM143"; gene_source "ensembl_havana"; gene_biotype "protein_coding";\n+19\tensembl_havana\ttranscript\t48332356\t48363940\t.\t-\t.\tgene_id "ENSG00000161558"; gene_version "11"; transcript_id "ENST00000293261"; transcript_version "8"; gene_name "TMEM143"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "TMEM143-201"; transcript_source "ensembl_havana"; transcript_biotype "protein_coding"; tag "CCDS"; ccds_id "CCDS12716"; tag "basic"; transcript_support_level "1 (assigned to previous version 7)";\n+19\tensembl_havana\texon\t48363898\t48363940\t.\t-\t.\tgene_id "ENSG00000161558"; gene_version "11"; transcript_id "ENST00000293261"; transcript_version "8"; exon_number "1"; gene_name "TMEM143"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "TMEM143-201"; transcript_source "ensembl_havana"; transcript_biotype "protein_coding"; tag "CCDS"; ccds_id "CCDS12716"; exon_id "ENSE00003224298"; exon_version "2"; tag "basic"; transcript_support_level "1 (assigned to previous version 7)";\n+19\tensembl_havana\tCDS\t48363898\t48363920\t.\t-\t0\tgene_id "ENSG00000161558"; gene_version "11"; transcript_id "ENST00000293261"; transcript_version "8"; exon_number "1"; gene_name "TMEM143"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "TMEM143-201"; transcript_source "ensembl_havana"; transcript_biotype "protein_coding"; tag "CCDS"; ccds_id "CCDS12716"; protein_id "ENSP00000293261"; protein_version "2"; tag "basic"; transcript_support_level "1 (assigned to previous version 7)";\n+19\tensembl_havana\tstart_codon\t48363918\t48363920\t.\t-\t0\tgene_id "ENSG00000161558"; gene_version "11"; transcript_id "ENST00000293261"; transcript_version "8"; exon_number "1"; gene_name "TMEM143"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "TMEM143-201"; transcript_source "ensembl_havana"; transcript_biotype "protein_coding"; tag "CCDS"; ccds_id "CCDS12716"; tag "basic"; transcript_support_level "1 (assigned to previous version 7)";\n+19\tensembl_havana\texon\t48363291\t48363531\t.\t-\t.\tgene_id "ENSG00000161558"; gene_version "11"; transcript_id "ENST00000293261"; transcript_version "8"; exon_number "2"; gene_name "TMEM143"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "TMEM143-201"; transcript_source "ensembl_havana"; transcript_biotype "protein_coding"; tag "CCDS"; ccds_id "CCDS12716"; exon_id "ENSE00003517521"; exon_version "1"; tag "basic"; transcript_support_level "1 (assigned to previous version 7)";\n+19\tensembl_havana\tCDS\t48363291\t48363531\t.\t-\t1\tgene_id "ENSG00000161558"; gene_version "11"; transcript_id "ENST00000293261"; transcript_version "8"; exon_number "2"; gene_name "TMEM143"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "TMEM143-201"; transcript_source "ensembl_havana"; transcript_biotype "protein_coding"; tag "CCDS"; ccds_id "CCDS12716"; protein_id "ENSP00000293261"; protein_version "2"; tag "basic"; transcript_support_level "1 (assigned to previous version 7)";\n+19\tensembl_havana\texon\t48360072\t48360176\t.\t-\t.\tgene_id "ENSG00000161558"; gene_version "11"; transcript_id "ENST00000293261"; transcript_version "8"; exon_number "3"; gene_name "TMEM143"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "TMEM143-201"; transcript_source "ensembl_havana"; transcript_biotype "protein_coding"; tag "CCDS"; ccds_id "CCDS12716"; exon_id "ENSE00003524788"; exon_version "1"; tag "basic"; transcript_support_level "1 (assigned to previous version 7)";\n+19\tensembl_havana\tCDS\t48360072\t48360176\t.\t-\t0\tgene_id "ENSG00000161558"; gene_version "11"; transcript_id "ENST00000293261"; transcript_version "8"; exon_number "3"; gene_name "T'..b'"; tag "CCDS"; ccds_id "CCDS12669"; tag "basic"; transcript_support_level "1 (assigned to previous version 4)";\n+19\tensembl_havana\tstop_codon\t45590778\t45590780\t.\t-\t0\tgene_id "ENSG00000177464"; gene_version "5"; transcript_id "ENST00000323040"; transcript_version "5"; exon_number "2"; gene_name "GPR4"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "GPR4-201"; transcript_source "ensembl_havana"; transcript_biotype "protein_coding"; tag "CCDS"; ccds_id "CCDS12669"; tag "basic"; transcript_support_level "1 (assigned to previous version 4)";\n+19\tensembl_havana\tfive_prime_utr\t45602095\t45602212\t.\t-\t.\tgene_id "ENSG00000177464"; gene_version "5"; transcript_id "ENST00000323040"; transcript_version "5"; gene_name "GPR4"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "GPR4-201"; transcript_source "ensembl_havana"; transcript_biotype "protein_coding"; tag "CCDS"; ccds_id "CCDS12669"; tag "basic"; transcript_support_level "1 (assigned to previous version 4)";\n+19\tensembl_havana\tfive_prime_utr\t45591867\t45592697\t.\t-\t.\tgene_id "ENSG00000177464"; gene_version "5"; transcript_id "ENST00000323040"; transcript_version "5"; gene_name "GPR4"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "GPR4-201"; transcript_source "ensembl_havana"; transcript_biotype "protein_coding"; tag "CCDS"; ccds_id "CCDS12669"; tag "basic"; transcript_support_level "1 (assigned to previous version 4)";\n+19\tensembl_havana\tthree_prime_utr\t45589764\t45590777\t.\t-\t.\tgene_id "ENSG00000177464"; gene_version "5"; transcript_id "ENST00000323040"; transcript_version "5"; gene_name "GPR4"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "GPR4-201"; transcript_source "ensembl_havana"; transcript_biotype "protein_coding"; tag "CCDS"; ccds_id "CCDS12669"; tag "basic"; transcript_support_level "1 (assigned to previous version 4)";\n+19\thavana\ttranscript\t45592233\t45599753\t.\t-\t.\tgene_id "ENSG00000177464"; gene_version "5"; transcript_id "ENST00000591614"; transcript_version "1"; gene_name "GPR4"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "GPR4-202"; transcript_source "havana"; transcript_biotype "processed_transcript"; transcript_support_level "4";\n+19\thavana\texon\t45599657\t45599753\t.\t-\t.\tgene_id "ENSG00000177464"; gene_version "5"; transcript_id "ENST00000591614"; transcript_version "1"; exon_number "1"; gene_name "GPR4"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "GPR4-202"; transcript_source "havana"; transcript_biotype "processed_transcript"; exon_id "ENSE00002877850"; exon_version "1"; transcript_support_level "4";\n+19\thavana\texon\t45592233\t45592697\t.\t-\t.\tgene_id "ENSG00000177464"; gene_version "5"; transcript_id "ENST00000591614"; transcript_version "1"; exon_number "2"; gene_name "GPR4"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "GPR4-202"; transcript_source "havana"; transcript_biotype "processed_transcript"; exon_id "ENSE00002883183"; exon_version "1"; transcript_support_level "4";\n+19\tmirbase\tgene\t45638994\t45639087\t.\t-\t.\tgene_id "ENSG00000284544"; gene_version "1"; gene_name "MIR330"; gene_source "mirbase"; gene_biotype "miRNA";\n+19\tmirbase\ttranscript\t45638994\t45639087\t.\t-\t.\tgene_id "ENSG00000284544"; gene_version "1"; transcript_id "ENST00000362196"; transcript_version "1"; gene_name "MIR330"; gene_source "mirbase"; gene_biotype "miRNA"; transcript_name "MIR330-201"; transcript_source "mirbase"; transcript_biotype "miRNA"; tag "basic"; transcript_support_level "NA";\n+19\tmirbase\texon\t45638994\t45639087\t.\t-\t.\tgene_id "ENSG00000284544"; gene_version "1"; transcript_id "ENST00000362196"; transcript_version "1"; exon_number "1"; gene_name "MIR330"; gene_source "mirbase"; gene_biotype "miRNA"; transcript_name "MIR330-201"; transcript_source "mirbase"; transcript_biotype "miRNA"; exon_id "ENSE00001436959"; exon_version "1"; tag "basic"; transcript_support_level "NA";\n' |
| b |
| diff -r 000000000000 -r ff15d6def09b test-data/cancer_small.bam |
| b |
| Binary file test-data/cancer_small.bam has changed |
| b |
| diff -r 000000000000 -r ff15d6def09b test-data/normal_small.bam |
| b |
| Binary file test-data/normal_small.bam has changed |
| b |
| diff -r 000000000000 -r ff15d6def09b test-data/novel/summary.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/novel/summary.txt Sat Jul 23 21:23:48 2022 +0000 |
| b |
| @@ -0,0 +1,6 @@ +EventType TotalEventsJC TotalEventsJCEC SignificantEventsJC SigEventsJCSample1HigherInclusion SigEventsJCSample2HigherInclusion SignificantEventsJCEC SigEventsJCECSample1HigherInclusion SigEventsJCECSample2HigherInclusion +SE 425 425 0 0 0 0 0 0 +A5SS 91 91 0 0 0 0 0 0 +A3SS 129 129 0 0 0 0 0 0 +MXE 31 31 0 0 0 0 0 0 +RI 94 94 0 0 0 0 0 0 |
| b |
| diff -r 000000000000 -r ff15d6def09b test-data/out/summary.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/out/summary.txt Sat Jul 23 21:23:48 2022 +0000 |
| b |
| @@ -0,0 +1,6 @@ +EventType TotalEventsJC TotalEventsJCEC SignificantEventsJC SigEventsJCSample1HigherInclusion SigEventsJCSample2HigherInclusion SignificantEventsJCEC SigEventsJCECSample1HigherInclusion SigEventsJCECSample2HigherInclusion +SE 424 424 0 0 0 0 0 0 +A5SS 89 89 0 0 0 0 0 0 +A3SS 119 119 0 0 0 0 0 0 +MXE 31 31 0 0 0 0 0 0 +RI 91 91 0 0 0 0 0 0 |
| b |
| diff -r 000000000000 -r ff15d6def09b test-data/rmats_testdata.tar.gz |
| b |
| Binary file test-data/rmats_testdata.tar.gz has changed |