5
|
1 <tool id="plant_tribes_assembly_post_processor" name="Postprocess de novo assembly transcripts" version="0.3">
|
|
2 <description>into putative coding sequences</description>
|
0
|
3 <requirements>
|
5
|
4 <requirement type="package" version="0.3">plant_tribes_assembly_post_processor</requirement>
|
0
|
5 </requirements>
|
|
6 <stdio>
|
|
7 <!-- Anything other than zero is an error -->
|
|
8 <exit_code range="1:" />
|
6
|
9 <exit_code range=":-1" />
|
|
10 <!-- In case the return code has not been set propery check stderr too -->
|
0
|
11 <regex match="Error:" />
|
|
12 <regex match="Exception:" />
|
|
13 </stdio>
|
|
14 <command>
|
|
15 <![CDATA[
|
10
|
16 #import os
|
0
|
17 AssemblyPostProcesser
|
8
|
18 --transcripts '$input'
|
0
|
19 --prediction_method $prediction_method_cond.prediction_method
|
|
20 #if str($prediction_method_cond.prediction_method) == 'estscan':
|
8
|
21 --score_matrices '$score_matrices'
|
0
|
22 #end if
|
|
23 #if str($options_type.options_type_selector) == 'advanced':
|
|
24 #if str($options_type.target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes':
|
10
|
25 #set scaffold_path = '$options_type.target_gene_family_assembly_cond.scaffold.path'
|
|
26 #set scaffold_dir = os.path.split($scaffold_path)[0]
|
|
27 #set scaffold = os.path.split($scaffold_path)[1]
|
8
|
28 --gene_family_search '$options_type.target_gene_family_assembly_cond.orthogroups'
|
10
|
29 --scaffold_dir $scaffold_dir
|
|
30 --scaffold $scaffold
|
8
|
31 --method '$options_type.target_gene_family_assembly_cond.method'
|
0
|
32 #end if
|
|
33 --gap_trimming $options_type.gap_trimming
|
|
34 #if str($options_type.strand_specific) == 'yes':
|
|
35 --strand_specific
|
|
36 #end if
|
|
37 #if str($options_type.dereplicate) == 'yes':
|
|
38 --dereplicate
|
|
39 #end if
|
|
40 --min_length $options_type.min_length
|
|
41 #end if
|
|
42 --num_threads \${GALAXY_SLOTS:-4}
|
|
43 ]]>
|
|
44 </command>
|
|
45 <inputs>
|
|
46 <param name="input" format="fasta" type="data" label="De novo transcriptome assembly fasta file"/>
|
|
47 <conditional name="prediction_method_cond">
|
|
48 <param name="prediction_method" type="select" label="Prediction method for coding regions">
|
|
49 <option value="transdecoder" selected="true">TransDecoder</option>
|
|
50 <option value="estscan">ESTScan</option>
|
|
51 </param>
|
|
52 <when value="transdecoder" />
|
|
53 <when value="estscan">
|
|
54 <param name="score_matrices" format="smat" type="data" label="Scores matrices"/>
|
|
55 </when>
|
|
56 </conditional>
|
|
57 <conditional name="options_type">
|
|
58 <param name="options_type_selector" type="select" label="Options Configuration">
|
|
59 <option value="basic" selected="true">Basic</option>
|
|
60 <option value="advanced">Advanced</option>
|
|
61 </param>
|
|
62 <when value="basic" />
|
|
63 <when value="advanced">
|
|
64 <conditional name="target_gene_family_assembly_cond">
|
|
65 <param name="target_gene_family_assembly" type="select" label="Target gene family assembly?">
|
|
66 <option value="no" selected="true">No</option>
|
|
67 <option value="yes">Yes</option>
|
|
68 </param>
|
|
69 <when value="no" />
|
|
70 <when value="yes">
|
|
71 <param name="orthogroups" format="tabular" type="data" label="List of orthogroup identifiers for target gene families to assemble"/>
|
|
72 <param name="scaffold" type="select" label="Orthogroups or gene families proteins scaffold">
|
|
73 <options from_data_table="plant_tribes_scaffolds" />
|
10
|
74 <validator type="no_options" message="No PlantTribes scaffolds are available. Use the PlantTribes Scaffolds Download Data Manager tool in Galaxy to install and populate the PlantTribes scaffolds data table."/>
|
0
|
75 </param>
|
|
76 <param name="method" type="select" label="Protein clustering method">
|
|
77 <option value="gfam" selected="true">GFam</option>
|
|
78 <option value="orthofinder">OrthoFinder</option>
|
|
79 <option value="orthomcl">OrthoMCL</option>
|
|
80 </param>
|
|
81 </when>
|
|
82 </conditional>
|
3
|
83 <param name="gap_trimming" type="float" value="0.1" min="0" max="1.0" label="Remove sites in alignments with gaps of" help="0.1 removes sites with 90% gaps"/>
|
0
|
84 <param name="strand_specific" type="select" label="De novo transcriptome assembly was performed with strand-specific library?">
|
|
85 <option value="no" selected="true">No</option>
|
|
86 <option value="yes">Yes</option>
|
|
87 </param>
|
|
88 <param name="dereplicate" type="select" label="Remove repeated sequences in predicted coding regions?">
|
|
89 <option value="no" selected="true">No</option>
|
|
90 <option value="yes">Yes</option>
|
|
91 </param>
|
|
92 <param name="min_length" type="integer" value="200" label="Minimum sequence length of predicted coding regions"/>
|
|
93 </when>
|
|
94 </conditional>
|
|
95 </inputs>
|
|
96 <outputs>
|
|
97 <collection name="transcripts" type="list">
|
1
|
98 <discover_datasets pattern="__name__" directory="assemblyPostProcessing_dir" visible="true" ext="fasta" />
|
0
|
99 </collection>
|
|
100 </outputs>
|
|
101 <tests>
|
|
102 <test>
|
|
103 <param name="input" value="assembly.fasta" ftype="fasta" />
|
|
104 <param name="prediction_method" value="transdecoder" />
|
6
|
105 <output_collection name="transcripts" type="list">
|
8
|
106 <element name="transcripts.cds" file="transcripts.cds" ftype="fasta"/>
|
|
107 <element name="transcripts.cleaned.cds" file="transcripts.cleaned.cds" ftype="fasta"/>
|
|
108 <element name="transcripts.cleaned.pep" file="transcripts.cleaned.pep1" ftype="fasta"/>
|
|
109 <element name="transcripts.pep" file="transcripts.pep" ftype="fasta"/>
|
6
|
110 </output_collection>
|
|
111 </test>
|
|
112 <test>
|
|
113 <param name="input" value="assembly.fasta" ftype="fasta" />
|
|
114 <param name="prediction_method" value="transdecoder" />
|
0
|
115 <param name="options_type_selector" value="advanced" />
|
7
|
116 <param name="gap_trimming" value="0.1" />
|
0
|
117 <param name="dereplicate" value="yes" />
|
7
|
118 <param name="min_length" value="200" />
|
0
|
119 <output_collection name="transcripts" type="list">
|
7
|
120 <element name="transcripts.cds" file="transcripts.cds" ftype="fasta" compare="contains"/>
|
|
121 <element name="transcripts.cleaned.cds" file="transcripts.cleaned.cds" ftype="fasta" compare="contains"/>
|
8
|
122 <element name="transcripts.cleaned.nr.cds" file="transcripts.cleaned.nr.cds" ftype="fasta" compare="contains"/>
|
|
123 <element name="transcripts.cleaned.nr.pep" file="transcripts.cleaned.nr.pep" ftype="fasta" compare="contains"/>
|
7
|
124 <element name="transcripts.cleaned.pep" file="transcripts.cleaned.pep2" ftype="fasta" compare="contains"/>
|
|
125 <element name="transcripts.pep" file="transcripts.pep" ftype="fasta" compare="contains"/>
|
0
|
126 </output_collection>
|
|
127 </test>
|
|
128 </tests>
|
|
129 <help>
|
|
130 This tool is one of the PlantTribes' collection of automated modular analysis pipelines that utilize objective classifications of
|
5
|
131 complete protein sequences from sequenced plant genomes to perform comparative evolutionary studies. It postprocesses de novo assembly
|
|
132 transcripts into putative coding sequences and their corresponding amino acid translations, locally assembling targeted gene families.
|
0
|
133
|
|
134 -----
|
|
135
|
|
136 **Options**
|
|
137
|
|
138 * **Prediction method for coding regions** - The prediction method for coding regions; one of ESTScan or TransDecoder.
|
|
139 * **Scores matrices** - Scores matrices that reflect the codons preferences in the studied organisms.
|
5
|
140 * **Target gene family assembly?** - Select 'Yes' to target gene families to assemble.
|
|
141 * **List of orthogroup identifiers for target gene families to assemble** - History item with a list of orthogroup identifiers for target gene families to assemble.
|
0
|
142 * **Orthogroups or gene families proteins scaffold** - PlantTribes scaffolds data.
|
5
|
143 * **Protein clustering method** - One of GFam (domain architecture based clustering), OrthoFinder (broadly defined clusters) or OrthoMCL (narrowly defined clusters).
|
|
144 * **Remove sites in alignments with gaps of** - Removes gappy sites in alignments (i.e. 0.1 removes sites with 90% gaps): [0.0 to 1.0]
|
|
145 * **De novo transcriptome assembly was performed with strand-specific library?** - Select 'Yes' if de novo transcriptome assembly was performed with strand-specific library.
|
0
|
146 * **Remove repeated sequences in predicted coding regions?** - Select yes to remove repeated sequences in predicted coding regions.
|
|
147 * **Minimum sequence length of predicted coding regions** - Set the minimum sequence length of predicted coding regions.
|
|
148
|
|
149 </help>
|
|
150 <citations>
|
|
151 <citation type="bibtex">
|
|
152 @unpublished{None,
|
5
|
153 author = {Eric Wafula},
|
0
|
154 title = {None},
|
|
155 year = {None},
|
10
|
156 url = {https://github.com/dePamphilis/PlantTribes}
|
0
|
157 }</citation>
|
8
|
158 <citation type="bibtex">
|
|
159 @published{Proc Int Conf Intell Syst Mol Biol,
|
|
160 author = {Iseli C, Jongeneel CV, Bucher P.},
|
|
161 title = {ESTScan: a program for detecting, evaluating, and reconstructing potential coding regions in EST sequences.},
|
|
162 year = {1999},
|
10
|
163 url = {http://estscan.sourceforge.net/}
|
8
|
164 }</citation>
|
|
165 <citation type="doi">10.1038/nprot.2013.084</citation>
|
10
|
166 <citation type="doi">10.1109/tcbb.2013.68</citation>
|
0
|
167 </citations>
|
|
168 </tool>
|