1
|
1 <tool id="plant_tribes_gene_family_classifier" name="GeneFamilyClassifier" version="1.0.0">
|
0
|
2 <description>pipeline</description>
|
|
3 <requirements>
|
|
4 <requirement type="package" version="0.2">plant_tribes_gene_family_classifier</requirement>
|
|
5 </requirements>
|
|
6 <stdio>
|
|
7 <!-- Anything other than zero is an error -->
|
|
8 <exit_code range="1:" />
|
|
9 <!-- In case the return code has not been set properly check stderr too -->
|
|
10 <regex match="Error:" />
|
|
11 <regex match="Exception:" />
|
|
12 </stdio>
|
|
13 <command>
|
|
14 <![CDATA[
|
9
|
15 #set create_ortho_sequences = str($options_type.options_type_selector) == 'advanced' and str($options_type.create_orthogroup_cond.create_orthogroup) == 'yes'
|
|
16 #if create_ortho_sequences:
|
8
|
17 #import os
|
9
|
18 #set src_dir = $os.path.join('geneFamilyClassification_dir', 'orthogroups_fasta')
|
|
19 #set dest_dir = $output.extra_files_path
|
|
20 mkdir -p $dest_dir &&
|
4
|
21 #end if
|
0
|
22 GeneFamilyClassifier
|
|
23 --proteins "$input"
|
|
24 --scaffold "$scaffold"
|
|
25 --method $method
|
|
26 --classifier $classifier
|
|
27 #if str($options_type.options_type_selector) == 'advanced':
|
|
28 --super_orthogroups $options_type.super_orthogroups
|
|
29 #if str($options_type.single_copy_cond) == 'taxa':
|
|
30 --single_copy_taxa $options_type.single_copy_cond.single_copy_taxa
|
|
31 --taxa_present $options_type.single_copy_cond.taxa_present
|
|
32 #end if
|
3
|
33 #if str($options_type.create_orthogroup_cond.create_orthogroup) == 'yes':
|
0
|
34 --orthogroup_fasta
|
|
35 --coding_sequences "$options_type.create_orthogroup_cond.coding_sequences"
|
|
36 #end if
|
|
37 #end if
|
2
|
38 --scaffold_dir "${GALAXY_DATA_INDEX_DIR}/plant_tribes/scaffolds"
|
0
|
39 --num_threads \${GALAXY_SLOTS:-4}
|
12
|
40 #if str($classifier) == 'hmmscan' or str($classifier) == 'both':
|
|
41 # Eliminate the hmmscan.log file
|
|
42 && rm $src_dir/*.log
|
|
43 #end if
|
9
|
44 #if create_ortho_sequences:
|
12
|
45 && echo "Sequences classified into pre-computed orthologous plant gene family clusters: `ls $src_dir | wc -l` files" > $output
|
|
46 && mv $src_dir/* $dest_dir
|
4
|
47 #end if
|
0
|
48 ]]>
|
|
49 </command>
|
|
50 <inputs>
|
|
51 <param name="input" format="fasta" type="data" label="Amino acids (proteins) sequences fasta file"/>
|
|
52 <param name="scaffold" type="select" label="Orthogroups or gene families proteins scaffold">
|
|
53 <options from_data_table="plant_tribes_scaffolds" />
|
|
54 <validator type="no_options" message="No PlantTribes scaffolds are available. Use the PlantTribes Scaffolds Download Data Manager tool to install and populate the PlantTribes scaffolds data table."/>
|
|
55 </param>
|
|
56 <param name="method" type="select" label="Protein clustering method">
|
|
57 <option value="gfam" selected="true">GFam</option>
|
|
58 <option value="orthofinder">OrthoFinder</option>
|
|
59 <option value="orthomcl">OrthoMCL</option>
|
|
60 </param>
|
|
61 <param name="classifier" type="select" label="Protein classification method">
|
|
62 <option value="blastp" selected="true">blastp</option>
|
|
63 <option value="hmmscan">HMMScan</option>
|
|
64 <option value="both">Both blastp and HMMScan</option>
|
|
65 </param>
|
|
66 <conditional name="options_type">
|
|
67 <param name="options_type_selector" type="select" label="Options Configuration">
|
|
68 <option value="basic" selected="true">Basic</option>
|
|
69 <option value="advanced">Advanced</option>
|
|
70 </param>
|
|
71 <when value="basic" />
|
|
72 <when value="advanced">
|
|
73 <param name="super_orthogroups" type="select" label="SuperOrthogroups MCL clustering" help="blastp e-value matrix between all pairs of orthogroups">
|
|
74 <option value="min_evalue" selected="true">Minimum e-value</option>
|
|
75 <option value="avg_evalue">Average e-value</option>
|
|
76 </param>
|
|
77 <conditional name="single_copy_cond">
|
|
78 <param name="single_copy" type="select" label="Select single copy configuration">
|
|
79 <option value="custom" selected="true">Single copy orthogroup custom</option>
|
|
80 <option value="taxa">Minumum single copy taxa required in orthogroup</option>
|
|
81 </param>
|
|
82 <when value="custom" />
|
|
83 <when value="taxa">
|
|
84 <param name="single_copy_taxa" type="integer" value="20" label="Minumum single copy taxa required in orthogroup"/>
|
|
85 <param name="taxa_present" type="integer" value="21" label="Minumum taxa required in single copy orthogroup"/>
|
|
86 </when>
|
|
87 </conditional>
|
|
88 <conditional name="create_orthogroup_cond">
|
|
89 <param name="create_orthogroup" type="select" label="Create orthogroup fasta files?">
|
|
90 <option value="no" selected="true">No</option>
|
|
91 <option value="yes">Yes</option>
|
|
92 </param>
|
|
93 <when value="no" />
|
|
94 <when value="yes">
|
|
95 <param name="coding_sequences" format="fasta" type="data" label="Corresponding coding sequences (CDS) fasta file"/>
|
|
96 </when>
|
|
97 </conditional>
|
|
98 </when>
|
|
99 </conditional>
|
|
100 </inputs>
|
|
101 <outputs>
|
9
|
102 <data name="output" format="txt" label="Sequences classified into gene family clusters on ${on_string}">
|
|
103 <filter>options_type['options_type_selector'] == 'advanced' and options_type['create_orthogroup_cond']['create_orthogroup'] == 'yes'</filter>
|
|
104 </data>
|
0
|
105 <collection name="transcripts" type="list">
|
12
|
106 <discover_datasets pattern="__name__" directory="geneFamilyClassification_dir" visible="false" ext="tabular" />
|
0
|
107 </collection>
|
|
108 </outputs>
|
|
109 <tests>
|
|
110 <test>
|
|
111 <param name="input" value="" ftype="fasta" />
|
|
112 <param name="prediction_method" value="transdecoder"/>
|
|
113 <param name="target_gene_family_assembly" value="no"/>
|
|
114 <param name="strand_specific" value="yes"/>
|
|
115 <param name="dereplicate" value="yes"/>
|
|
116 <param name="min_length" value="200"/>
|
|
117 <output_collection name="orthos" type="list">
|
|
118
|
|
119 </output_collection>
|
|
120 </test>
|
|
121 </tests>
|
|
122 <help>
|
|
123 This tool is one of the PlantTribes' collection of automated modular analysis pipelines that utilize objective classifications of
|
9
|
124 complete protein sequences from sequenced plant genomes to perform comparative evolutionary studies. It performs gene family
|
0
|
125 classification of the post processed de novo transcripts using either blastp (faster), HMMScan (slower but more sensitive to remote
|
|
126 homologs) or both (more exhaustive).
|
|
127
|
|
128 -----
|
|
129
|
|
130 **Options**
|
|
131
|
|
132 * **Orthogroups or gene families proteins scaffold** - PlantTribes scaffolds data.
|
|
133 * **Protein clustering method** - One of GFam, OrthoFinder or OrthoMCL.
|
|
134 * **Protein classification method** - One of blastp, HMMScan or both.
|
|
135 * **SuperOrthogroups MCL clustering** - blastp e-value matrix between all pairs of orthogroups.
|
|
136 * **Minumum single copy taxa required in orthogroup** - Used with "Minumum single copy taxa required in orthogroup" configuration only.
|
|
137 * **Minumum taxa required in single copy orthogroup** - Used with "Minumum single copy taxa required in orthogroup" configuration only.
|
|
138 * **Corresponding coding sequences (CDS) fasta file** - Used only when selecting "Create orthogroup fasta files?".
|
|
139
|
|
140 </help>
|
|
141 <citations>
|
|
142 <citation type="bibtex">
|
|
143 @unpublished{None,
|
|
144 author = {None},
|
|
145 title = {None},
|
|
146 year = {None},
|
|
147 eprint = {None},
|
|
148 url = {None}
|
|
149 }</citation>
|
|
150 </citations>
|
|
151 </tool>
|