0
|
1 <tool id="pangenome_cog_analysis" name="Pangenome COG Analysis" version="1.0">
|
|
2 <description>Provide statistics from pangenome matrix and COG annotations </description>
|
|
3 <!-- <requirements>
|
|
4 <requirement type="package" version=""></requirement>
|
|
5 </requirements> -->
|
|
6 <command detect_errors="aggressive"><![CDATA[
|
|
7 #import re
|
|
8
|
|
9 ## Creates symlinks for each input file based on the Galaxy 'element_identifier'
|
|
10 ## Used so that a human-readable name appears in the output table (instead of 'dataset_xyz.dat')
|
|
11 #set $named_input_files = ''
|
|
12 #for $input_file in $input_files
|
|
13 ## Add single quotes around each input file identifier
|
|
14 #set $_input_file = "'{}'".format($input_file.element_identifier)
|
7
|
15 ##ln -s '${input_file}' ${_input_file} &&
|
0
|
16 #set $named_input_files = $named_input_files + ',' + $_input_file
|
|
17 #end for
|
|
18
|
15
|
19 perl ${__tool_directory__}/pangenomeCogAnalysis_V1.pl $input $input2 $input_files $named_input_files $gff_files $output $output2 $output3 $output4 $output8 $output9
|
3
|
20
|
0
|
21 ]]></command>
|
|
22
|
|
23
|
|
24
|
|
25 <inputs>
|
|
26 <param format="tabular" name="input" type="data" label="Pangenome Matrix" help="Headers must be: Cluster,genes_strain1,genes_strain2..."/>
|
|
27 <param format="tabular" name="input2" type="data" label="Strains group file (example species information)" help="Headers must be: strain1,groupinfo"/>
|
|
28 <param type="data" name="input_files" format="txt" multiple="true" label="Collection of COG files" help="Each files must be named with the same strain name as defined in Strain group file. Headers must be Gene,COG,COGcategory"/>
|
|
29 <param type="data" name="gff_files" format="gff3" multiple="true" label="Collection of GFF files for preparing Circos track" help="Not necessarily annotations from all strains, only those that you want to be represented as Circos tracks"/>
|
|
30 <!--<param format="tabular" name="input_files" type="data" multiple="true" label="Annotation files"/>-->
|
|
31 </inputs>
|
|
32
|
|
33 <outputs>
|
|
34 <data format="txt" name="output" label="List of group-specific clusters"/>
|
|
35 <data format="tabular" name="output2" label="COG category count average per group"/>
|
|
36 <data format="tabular" name="output3" label="Detailed COG category count values per group"/>
|
|
37 <data format="tabular" name="output4" label="COG category count average"/>
|
3
|
38 <!--<data format="tabular" name="output5" label="Core-genes coordinates"/>-->
|
|
39 <collection name="output5" type="list" label="Core-genes coordinates">
|
9
|
40 <discover_datasets pattern="__name_and_ext__" directory="Core" />
|
3
|
41 </collection>
|
9
|
42 <collection name="output6" type="list" label="Group specific genes coordinates">
|
11
|
43 <discover_datasets pattern="__name_and_ext__" directory="GroupSpecific" />
|
|
44 </collection>
|
|
45 <collection name="output7" type="list" label="Strain specific genes coordinates">
|
|
46 <discover_datasets pattern="__name_and_ext__" directory="StrainSpecific" />
|
|
47 </collection>
|
15
|
48 <data format="txt" name="output8" label="Odds ratio for core/accessory/unique"/>
|
|
49 <data format="txt" name="output9" label="Odds ratio comparison between groups"/>
|
0
|
50 </outputs>
|
|
51
|
|
52 </tool>
|