Mercurial > repos > iuc > gffcompare

comparison gffcompare.xml @ 2:66f066ca5d60 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gffcompare commit a5352fb7f073b0083b750c5cf7d283ebcc16b30d
author iuc
date Tue, 05 Feb 2019 15:51:05 -0500
parents 77c22296fb8e
children 84845ad0d35c
comparison
equal deleted inserted replaced
1:77c22296fb8e 2:66f066ca5d60
1 <tool id="gffcompare" name="GffCompare" version="0.9.8+galaxy1"> 1 <tool id="gffcompare" name="GffCompare" version="0.10.6">
2 <description>compare assembled transcripts to a reference annotation</description> 2 <description>compare assembled transcripts to a reference annotation</description>
3 <requirements> 3 <requirements>
4 <requirement type="package" version="0.9.8">gffcompare</requirement> 4 <requirement type="package" version="0.10.6">gffcompare</requirement>
5 </requirements> 5 </requirements>
6 <stdio>
7 <exit_code range="1:" />
8 <exit_code range=":-1" />
9 <regex match="Error" />
10 <regex match="Exception" />
11 </stdio>
12 <version_command>gffcompare -v | awk '{print $2}'</version_command> 6 <version_command>gffcompare -v | awk '{print $2}'</version_command>
13 <command><![CDATA[ 7 <command detect_errors="aggressive"><![CDATA[
14 #import re 8 #import re
15 #set escaped_element_identifiers = [re.sub('[^\w\-]', '_', str(_.element_identifier)) for _ in $gffinputs] 9 #set escaped_element_identifiers = [re.sub('[^\w\-]', '_', str(_.element_identifier)) for _ in $gffinputs]
16 #for $input, $escaped_element_identifier in zip($gffinputs, $escaped_element_identifiers): 10 #for $input, $escaped_element_identifier in zip($gffinputs, $escaped_element_identifiers):
17 ln -s '$input' '$escaped_element_identifier' && 11 ln -s '$input' '$escaped_element_identifier' &&
18 #end for 12 #end for
41 #end if 35 #end if
42 36
43 $discard_single_exon 37 $discard_single_exon
44 -e $max_dist_exon 38 -e $max_dist_exon
45 -d $max_dist_group 39 -d $max_dist_group
46 $discard_intron_redundant_transfrags 40 -p '$adv_output.p'
41 $adv_output.A
42 $adv_output.C
43 $adv_output.X
44 $adv_output.K
47 45
48 #for $escaped_element_identifier in $escaped_element_identifiers: 46 #for $escaped_element_identifier in $escaped_element_identifiers:
49 '$escaped_element_identifier' 47 '$escaped_element_identifier'
50 #end for 48 #end for
49
51 ]]></command> 50 ]]></command>
52 <inputs> 51 <inputs>
53 <param format="gtf" name="gffinputs" type="data" label="GTF inputs for comparison" help="" multiple="true" /> 52 <param format="gtf" name="gffinputs" type="data" label="GTF inputs for comparison" help="" multiple="true" />
54 <conditional name="annotation"> 53 <conditional name="annotation">
55 <param label="Use Reference Annotation" name="use_ref_annotation" type="select"> 54 <param label="Use Reference Annotation" name="use_ref_annotation" type="select">
99 <option value="-M">Discard single-exon transfrags and reference transcripts</option> 98 <option value="-M">Discard single-exon transfrags and reference transcripts</option>
100 <option value="-N">Discard single-exon reference transcripts</option> 99 <option value="-N">Discard single-exon reference transcripts</option>
101 </param> 100 </param>
102 <param argument="-e" help="max. distance (range) allowed from free ends of terminal exons of reference transcripts when assessing exon accuracy. Default: 100" label="Max. Distance for assessing exon accuracy" name="max_dist_exon" type="integer" value="100" /> 101 <param argument="-e" help="max. distance (range) allowed from free ends of terminal exons of reference transcripts when assessing exon accuracy. Default: 100" label="Max. Distance for assessing exon accuracy" name="max_dist_exon" type="integer" value="100" />
103 <param argument="-d" help="max. distance (range) for grouping transcript start sites. Default: 100" label="Max distance for transcript grouping" name="max_dist_group" type="integer" value="100" /> 102 <param argument="-d" help="max. distance (range) for grouping transcript start sites. Default: 100" label="Max distance for transcript grouping" name="max_dist_group" type="integer" value="100" />
104 <param argument="-F" help="Discard intron-redundant transfrags if they share the 5' end (if they differ only at the 3' end)" truevalue="-F" falsevalue="" label="discard intron-redundant transfrags sharing 5'" name="discard_intron_redundant_transfrags" type="boolean" /> 103 <section name="adv_output" title="Options for the annotated/combined GTF output file">
104 <param argument="-p" type="text" value="TCONS" label="name prefix for consensus transcripts" help="for combined.gtf (default: 'TCONS')" />
105 <param argument="-C" type="boolean" checked="false" truevalue="-C" falsevalue="" label="discard the 'contained' transfrags" help="i.e. collapse intron-redundant transfrags across all query files" />
106 <param argument="-A" type="boolean" checked="false" truevalue="-A" falsevalue="" label="discard the 'contained' transfrags except intron-redundant transfrags starting with a different 5' exon" help="like -C but does not discard intron-redundant transfrags if they start with a different 5' exon" />
107 <param argument="-X" type="boolean" checked="false" truevalue="-X" falsevalue="" label="discard the 'contained' transfrags also if ends stick out within the container's introns" help="like -C but also discard contained transfrags if transfrag ends stick out within the container's introns" />
108 <param argument="-K" type="boolean" checked="false" truevalue="-A" falsevalue="" label="do NOT discard any redundant transfrag matching a reference" help="for -C/-A/-X" />
109 </section>
105 </inputs> 110 </inputs>
106 <outputs> 111 <outputs>
107 <data format="txt" from_work_dir="gffcmp.stats" label="${tool.name} on ${on_string}: transcript accuracy" name="transcripts_stats" /> 112 <data format="txt" from_work_dir="gffcmp.stats" label="${tool.name} on ${on_string}: transcript accuracy" name="transcripts_stats" />
108 <data format="tabular" from_work_dir="gffcmp.loci" label="${tool.name} on ${on_string}: loci" name="transcripts_loci" /> 113 <data format="tabular" from_work_dir="gffcmp.loci" label="${tool.name} on ${on_string}: loci" name="transcripts_loci" />
109 <data format="tabular" from_work_dir="gffcmp.tracking" label="${tool.name} on ${on_string}: data ${gffinputs[0].hid} tracking file" name="transcripts_tracking" /> 114 <data format="tabular" from_work_dir="gffcmp.tracking" label="${tool.name} on ${on_string}: data ${gffinputs[0].hid} tracking file" name="transcripts_tracking" />
133 </conditional> 138 </conditional>
134 <param name="use_seq_data" value="No" /> 139 <param name="use_seq_data" value="No" />
135 <param name="discard_single_exon" value="" /> 140 <param name="discard_single_exon" value="" />
136 <param name="max_dist_exon" value="100" /> 141 <param name="max_dist_exon" value="100" />
137 <param name="max_dist_group" value="100" /> 142 <param name="max_dist_group" value="100" />
138 <param name="discard_intron_redundant_transfrags" value="No" />
139 <output file="gffcompare_out1.stats" name="transcripts_stats" lines_diff="6" /> 143 <output file="gffcompare_out1.stats" name="transcripts_stats" lines_diff="6" />
140 <output file="gffcompare_out1.loci" name="transcripts_loci" lines_diff="2" /> 144 <output file="gffcompare_out1.loci" name="transcripts_loci" lines_diff="2" />
141 <output file="gffcompare_out1.tracking" name="transcripts_tracking" /> 145 <output file="gffcompare_out1.tracking" name="transcripts_tracking" />
142 <output file="gffcompare_out1.gtf" name="transcripts_combined" /> 146 <output file="gffcompare_out1.gtf" name="transcripts_combined" />
143 <output_collection name="refmap_output" type="list" count="2"> 147 <output_collection name="refmap_output" type="list" count="2">
160 </conditional> 164 </conditional>
161 <param name="use_seq_data" value="No" /> 165 <param name="use_seq_data" value="No" />
162 <param name="discard_single_exon" value="" /> 166 <param name="discard_single_exon" value="" />
163 <param name="max_dist_exon" value="100" /> 167 <param name="max_dist_exon" value="100" />
164 <param name="max_dist_group" value="100" /> 168 <param name="max_dist_group" value="100" />
165 <param name="discard_intron_redundant_transfrags" value="No" />
166 <output file="gffcompare_out2.stats" name="transcripts_stats" lines_diff="6" /> 169 <output file="gffcompare_out2.stats" name="transcripts_stats" lines_diff="6" />
167 <output file="gffcompare_out2.loci" name="transcripts_loci" /> 170 <output file="gffcompare_out2.loci" name="transcripts_loci" />
168 <output file="gffcompare_out2.tracking" name="transcripts_tracking" /> 171 <output file="gffcompare_out2.tracking" name="transcripts_tracking" />
169 <output file="gffcompare_out2.gtf" name="transcripts_annotated" /> 172 <output file="gffcompare_out2.gtf" name="transcripts_annotated" />
170 </test> 173 </test>
181 184
182 The original form of this program is also distributed as part of the Cufflinks suite, under the name "CuffCompare" 185 The original form of this program is also distributed as part of the Cufflinks suite, under the name "CuffCompare"
183 (see manual: http://cole-trapnell-lab.github.io/cufflinks/cuffcompare/). Most of the options and parameters of CuffCompare 186 (see manual: http://cole-trapnell-lab.github.io/cufflinks/cuffcompare/). Most of the options and parameters of CuffCompare
184 are supported by GffCompare, while new features will likely be added to GffCompare in the future. 187 are supported by GffCompare, while new features will likely be added to GffCompare in the future.
185 188
186 A notable difference from GffCompare is that when a single query GTF/GFF file is given as input, along with a reference annotation (-r option), 189 A notable difference of GffCompare is that when a single query GTF/GFF file is given as input, along with a reference annotation (-r option),
187 gffcompare switches into "annotation mode" and it generates a .annotated.gtf file instead of the .merged.gtf produced by CuffCompare with the 190 gffcompare switches into "annotation mode" and it generates a .annotated.gtf file instead of the .merged.gtf produced by CuffCompare with the
188 same parameters. This file has the same general format as CuffCompare's .merged.gtf file (with "class codes" assigned to transcripts as per 191 same parameters. This file has the same general format as CuffCompare's .merged.gtf file (with "class codes" assigned to transcripts as per
189 their relationship with the matching/overlapping reference transcript), but the original transcript IDs are preserved, so gffcompare can thus 192 their relationship with the matching/overlapping reference transcript), but the original transcript IDs are preserved, so gffcompare can thus
190 be used as a simple way of annotating a set of transcripts. 193 be used as a simple way of annotating a set of transcripts.
191 194