Mercurial > repos > devteam > cuffcompare
changeset 3:5aac9b9d6f2a draft
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tool_collections/cufflinks/cuffcompare commit 82ee6fc860c52c531b7a57bbb346ab1a67a434a5
author | devteam |
---|---|
date | Sun, 19 Feb 2017 12:11:14 -0500 |
parents | a5674ddf2ad7 |
children | 806c27c97df7 |
files | cuff_macros.xml cuffcompare_wrapper.py cuffcompare_wrapper.xml tool_dependencies.xml |
diffstat | 4 files changed, 25 insertions(+), 57 deletions(-) [+] |
line wrap: on
line diff
--- a/cuff_macros.xml Tue Feb 07 18:37:50 2017 -0500 +++ b/cuff_macros.xml Sun Feb 19 12:11:14 2017 -0500 @@ -8,14 +8,6 @@ </requirements> </xml> - <xml name="stdio"> - <stdio> - <exit_code range="1:" /> - <exit_code range=":-1" /> - <regex match="Error" /> - <regex match="Exception" /> - </stdio> - </xml> <xml name="condition_inputs"> <!-- DEFAULT : use BAM/SAM files --> <conditional name="in_type">
--- a/cuffcompare_wrapper.py Tue Feb 07 18:37:50 2017 -0500 +++ b/cuffcompare_wrapper.py Sun Feb 19 12:11:14 2017 -0500 @@ -38,23 +38,6 @@ (options, args) = parser.parse_args() - # output version # of tool - try: - with tempfile.NamedTemporaryFile() as tmp_stdout: - returncode = subprocess.call(args='cuffcompare 2>&1', stdout=tmp_stdout, shell=True) - stdout = None - with open(tmp_stdout.name) as tmp_stdout2: - for line in tmp_stdout2: - if line.lower().find('cuffcompare v') >= 0: - stdout = line.strip() - break - if stdout: - sys.stdout.write('%s\n' % stdout) - else: - raise Exception - except: - sys.stdout.write('Could not determine Cuffcompare version\n') - # Set/link to sequence file. if options.use_seq_data: if options.ref_file:
--- a/cuffcompare_wrapper.xml Tue Feb 07 18:37:50 2017 -0500 +++ b/cuffcompare_wrapper.xml Sun Feb 19 12:11:14 2017 -0500 @@ -1,12 +1,11 @@ -<tool id="cuffcompare" name="Cuffcompare" version="2.2.1.0"> +<tool id="cuffcompare" name="Cuffcompare" version="@VERSION@.1"> <description>compare assembled transcripts to a reference annotation and track Cufflinks transcripts across multiple experiments</description> <macros> <import>cuff_macros.xml</import> </macros> <expand macro="requirements" /> - <expand macro="stdio" /> <version_command>cuffcompare 2>&1 | head -n 1</version_command> - <command> + <command detect_errors="aggressive"><![CDATA[ python '$__tool_directory__/cuffcompare_wrapper.py' ## Use annotation reference? #if $annotation.use_ref_annotation == "Yes": @@ -19,7 +18,7 @@ #end if #end if - + ## Use sequence data? #if $seq_data.use_seq_data == "Yes": -s @@ -29,7 +28,7 @@ --index '${seq_data.seq_source.index.fields.path}' #end if #end if - + $discard_single_exon -e $max_dist_exon @@ -37,13 +36,13 @@ #if $discard_intron_redundant_transfrags: -F - #end if + #end if ## Outputs. --combined-transcripts '${transcripts_combined}' @CUFFLINKS_GTF_INPUTS@ - </command> + ]]></command> <inputs> <expand macro="cufflinks_gtf_inputs" /> <conditional name="annotation"> @@ -60,7 +59,7 @@ </when> </conditional> <conditional name="seq_data"> - <param name="use_seq_data" type="select" label="Use Sequence Data" + <param name="use_seq_data" type="select" label="Use Sequence Data" help="Use sequence data for some optional classification functions, including the addition of the p_id attribute required by Cuffdiff."> <option value="Yes">Yes</option> <option value="No">No</option> @@ -91,29 +90,29 @@ <option value="-M">Discard single-exon transfrags and reference transcripts</option> <option value="-N">Discard single-exon reference transcripts</option> </param> - <param type="integer" name="max_dist_exon" value="100" label="Max. Distance for assessing exon accuracy" + <param type="integer" name="max_dist_exon" value="100" label="Max. Distance for assessing exon accuracy" help="max. distance (range) allowed from free ends of terminal exons of reference transcripts when assessing exon accuracy. Default: 100" /> - <param type="integer" name="max_dist_group" value="100" label="Max.Distance for transcript grouping" + <param type="integer" name="max_dist_group" value="100" label="Max.Distance for transcript grouping" help="max. distance (range) for grouping transcript start sites. Default: 100" /> - <param type="boolean" name="discard_intron_redundant_transfrags" label="discard intron-redundant transfrags sharing 5'" + <param type="boolean" name="discard_intron_redundant_transfrags" label="discard intron-redundant transfrags sharing 5'" help="Discard intron-redundant transfrags if they share the 5' end (if they differ only at the 3' end)" /> </inputs> <outputs> - <data format="txt" name="transcripts_accuracy" label="${tool.name} on ${on_string}: transcript accuracy" + <data format="txt" name="transcripts_accuracy" label="${tool.name} on ${on_string}: transcript accuracy" from_work_dir="cc_output.stats" /> <data format="tabular" name="input1_tmap" label="${tool.name} on ${on_string}: data ${inputs[0].hid} tmap file" from_work_dir="cc_output.input1.tmap" /> - <data format="tabular" name="input1_refmap" - label="${tool.name} on ${on_string}: data ${inputs[0].hid} refmap file" + <data format="tabular" name="input1_refmap" + label="${tool.name} on ${on_string}: data ${inputs[0].hid} refmap file" from_work_dir="cc_output.input1.refmap"> <filter>annotation['use_ref_annotation'] == 'Yes'</filter> </data> <data format="tabular" name="input2_tmap" label="${tool.name} on ${on_string}: data ${inputs[1].hid} tmap file" from_work_dir="cc_output.input2.tmap"> <filter>@HAS_MULTIPLE_INPUTS@</filter> </data> - <data format="tabular" name="input2_refmap" - label="${tool.name} on ${on_string}: data ${inputs[1].hid} refmap file" + <data format="tabular" name="input2_refmap" + label="${tool.name} on ${on_string}: data ${inputs[1].hid} refmap file" from_work_dir="cc_output.input2.refmap"> <filter>annotation['use_ref_annotation'] == 'Yes' and @HAS_MULTIPLE_INPUTS@</filter> </data> @@ -124,7 +123,7 @@ </outputs> <tests> - <!-- + <!-- cuffcompare -r cuffcompare_in3.gtf -R cuffcompare_in1.gtf cuffcompare_in2.gtf --> <test> @@ -173,7 +172,7 @@ Cuffcompare takes Cufflinks' GTF output as input, and optionally can take a "reference" annotation (such as from Ensembl_) -.. _Ensembl: http://www.ensembl.org +.. _Ensembl: http://www.ensembl.org ------ @@ -187,7 +186,7 @@ Transcripts Combined File: -Cuffcompare reports a GTF file containing the "union" of all transfrags in each sample. If a transfrag is present in both samples, it is thus reported once in the combined gtf. +Cuffcompare reports a GTF file containing the "union" of all transfrags in each sample. If a transfrag is present in both samples, it is thus reported once in the combined gtf. Transcripts Tracking File: @@ -209,7 +208,7 @@ 3 Reference gene id Tcea The gene_name attribute of the reference GTF record for this transcript, or '-' if no reference transcript overlaps this Cufflinks transcript 4 Reference transcript id uc007afj.1 The transcript_id attribute of the reference GTF record for this transcript, or '-' if no reference transcript overlaps this Cufflinks transcript 5 Class code c The type of match between the Cufflinks transcripts in column 6 and the reference transcript. See class codes - + Each of the columns after the fifth have the following format: qJ:gene_id|transcript_id|FMI|FPKM|conf_lo|conf_hi @@ -222,18 +221,18 @@ Priority Code Description --------------------------------- 1 = Match - 2 c Contained - 3 j New isoform - 4 e A single exon transcript overlapping a reference exon and at least 10 bp of a reference intron, indicating a possible pre-mRNA fragment. + 2 c Contained + 3 j New isoform + 4 e A single exon transcript overlapping a reference exon and at least 10 bp of a reference intron, indicating a possible pre-mRNA fragment. 5 i A single exon transcript falling entirely with a reference intron 6 o Generic exonic overlap with a reference transcript - 7 p Possible polymerase run-on fragment - 8 r Repeat. Currently determined by looking at the soft-masked reference sequence and applied to transcripts where at least 50% of the bases are lower case + 7 p Possible polymerase run-on fragment + 8 r Repeat. Currently determined by looking at the soft-masked reference sequence and applied to transcripts where at least 50% of the bases are lower case 9 u Unknown, intergenic transcript 10 x Exonic overlap with reference on the opposite strand 11 s An intron of the transfrag overlaps a reference intron on the opposite strand (likely due to read mapping errors) 12 . (.tracking file only, indicates multiple classifications) - + ------- **Settings**
--- a/tool_dependencies.xml Tue Feb 07 18:37:50 2017 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,6 +0,0 @@ -<?xml version="1.0"?> -<tool_dependency> - <package name="cufflinks" version="2.2.1"> - <repository changeset_revision="87f239da61af" name="package_cufflinks_2_2_1" owner="devteam" toolshed="https://testtoolshed.g2.bx.psu.edu" /> - </package> -</tool_dependency>