comparison gene_family_classifier.xml @ 0:315440c6fb44 draft

Uploaded
author greg
date Fri, 09 Dec 2016 08:45:36 -0500
parents
children 8b5a8a3ca9ee
comparison
equal deleted inserted replaced
-1:000000000000 0:315440c6fb44
1 <tool id="plant_tribes_gene_family_classifier" name="PlantTribes GeneFamilyClassifier" version="1.0.0">
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[
15 GeneFamilyClassifier
16 --proteins "$input"
17 --scaffold "$scaffold"
18 --method $method
19 --classifier $classifier
20 #if str($options_type.options_type_selector) == 'advanced':
21 --super_orthogroups $options_type.super_orthogroups
22 #if str($options_type.single_copy_cond) == 'taxa':
23 --single_copy_taxa $options_type.single_copy_cond.single_copy_taxa
24 --taxa_present $options_type.single_copy_cond.taxa_present
25 #end if
26 #if str($options_type.create_orthogroup_cond) == 'yes':
27 --orthogroup_fasta
28 --coding_sequences "$options_type.create_orthogroup_cond.coding_sequences"
29 #end if
30 #end if
31 --num_threads \${GALAXY_SLOTS:-4}
32 ]]>
33 </command>
34 <inputs>
35 <param name="input" format="fasta" type="data" label="Amino acids (proteins) sequences fasta file"/>
36 <param name="scaffold" type="select" label="Orthogroups or gene families proteins scaffold">
37 <options from_data_table="plant_tribes_scaffolds" />
38 <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."/>
39 </param>
40 <param name="method" type="select" label="Protein clustering method">
41 <option value="gfam" selected="true">GFam</option>
42 <option value="orthofinder">OrthoFinder</option>
43 <option value="orthomcl">OrthoMCL</option>
44 </param>
45 <param name="classifier" type="select" label="Protein classification method">
46 <option value="blastp" selected="true">blastp</option>
47 <option value="hmmscan">HMMScan</option>
48 <option value="both">Both blastp and HMMScan</option>
49 </param>
50 <conditional name="options_type">
51 <param name="options_type_selector" type="select" label="Options Configuration">
52 <option value="basic" selected="true">Basic</option>
53 <option value="advanced">Advanced</option>
54 </param>
55 <when value="basic" />
56 <when value="advanced">
57 <param name="super_orthogroups" type="select" label="SuperOrthogroups MCL clustering" help="blastp e-value matrix between all pairs of orthogroups">
58 <option value="min_evalue" selected="true">Minimum e-value</option>
59 <option value="avg_evalue">Average e-value</option>
60 </param>
61 <conditional name="single_copy_cond">
62 <param name="single_copy" type="select" label="Select single copy configuration">
63 <option value="custom" selected="true">Single copy orthogroup custom</option>
64 <option value="taxa">Minumum single copy taxa required in orthogroup</option>
65 </param>
66 <when value="custom" />
67 <when value="taxa">
68 <param name="single_copy_taxa" type="integer" value="20" label="Minumum single copy taxa required in orthogroup"/>
69 <param name="taxa_present" type="integer" value="21" label="Minumum taxa required in single copy orthogroup"/>
70 </when>
71 </conditional>
72 <conditional name="create_orthogroup_cond">
73 <param name="create_orthogroup" type="select" label="Create orthogroup fasta files?">
74 <option value="no" selected="true">No</option>
75 <option value="yes">Yes</option>
76 </param>
77 <when value="no" />
78 <when value="yes">
79 <param name="coding_sequences" format="fasta" type="data" label="Corresponding coding sequences (CDS) fasta file"/>
80 </when>
81 </conditional>
82 </when>
83 </conditional>
84 </inputs>
85 <outputs>
86 <collection name="transcripts" type="list">
87 <discover_datasets pattern="__name__" directory="assemblyPostProcessing_dir" visible="false" ext="fasta" />
88 </collection>
89 </outputs>
90 <tests>
91 <test>
92 <param name="input" value="" ftype="fasta" />
93 <param name="prediction_method" value="transdecoder"/>
94 <param name="target_gene_family_assembly" value="no"/>
95 <param name="strand_specific" value="yes"/>
96 <param name="dereplicate" value="yes"/>
97 <param name="min_length" value="200"/>
98 <output_collection name="orthos" type="list">
99
100 </output_collection>
101 </test>
102 </tests>
103 <help>
104 This tool is one of the PlantTribes' collection of automated modular analysis pipelines that utilize objective classifications of
105 complete protein sequences from sequenced plant genomes to perform comparative evolutionary studies. It performs Gene family
106 classification of the post processed de novo transcripts using either blastp (faster), HMMScan (slower but more sensitive to remote
107 homologs) or both (more exhaustive).
108
109 -----
110
111 **Options**
112
113 * **Orthogroups or gene families proteins scaffold** - PlantTribes scaffolds data.
114 * **Protein clustering method** - One of GFam, OrthoFinder or OrthoMCL.
115 * **Protein classification method** - One of blastp, HMMScan or both.
116 * **SuperOrthogroups MCL clustering** - blastp e-value matrix between all pairs of orthogroups.
117 * **Minumum single copy taxa required in orthogroup** - Used with "Minumum single copy taxa required in orthogroup" configuration only.
118 * **Minumum taxa required in single copy orthogroup** - Used with "Minumum single copy taxa required in orthogroup" configuration only.
119 * **Corresponding coding sequences (CDS) fasta file** - Used only when selecting "Create orthogroup fasta files?".
120
121 </help>
122 <citations>
123 <citation type="bibtex">
124 @unpublished{None,
125 author = {None},
126 title = {None},
127 year = {None},
128 eprint = {None},
129 url = {None}
130 }</citation>
131 </citations>
132 </tool>