Mercurial > repos > greg > plant_tribes_assembly_post_processor

comparison assembly_post_processor.xml @ 4:b0d9dc3c8535 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author greg
date Mon, 30 Oct 2017 09:51:13 -0400
parents 07ee186ba16e
children 2732db7dd0ef
comparison
equal deleted inserted replaced
3:07ee186ba16e 4:b0d9dc3c8535
1 <tool id="plant_tribes_assembly_post_processor" name="AssemblyPostProcessor" version="@WRAPPER_VERSION@.2"> 1 <tool id="plant_tribes_assembly_post_processor" name="AssemblyPostProcessor" version="@WRAPPER_VERSION@.3.0">
2 <description>post-processes de novo transcriptome assembly</description> 2 <description>post-processes de novo transcriptome assembly</description>
3 <macros> 3 <macros>
4 <import>macros.xml</import> 4 <import>macros.xml</import>
5 </macros> 5 </macros>
6 <expand macro="requirements_assembly_post_processor" /> 6 <requirements>
7 <requirement type="package" version="1.0.3">plant_tribes_assembly_post_processor</requirement>
8 </requirements>
7 <command detect_errors="exit_code"><![CDATA[ 9 <command detect_errors="exit_code"><![CDATA[
8 python '$__tool_directory__/assembly_post_processor.py' 10 #set output_dir = 'assemblyPostProcessing_dir'
11 AssemblyPostProcessor
9 --transcripts '$input' 12 --transcripts '$input'
10 --prediction_method $prediction_method_cond.prediction_method 13 --prediction_method $prediction_method_cond.prediction_method
11 #if str($prediction_method_cond.prediction_method) == 'estscan': 14 #if str($prediction_method_cond.prediction_method) == 'estscan':
12 --score_matrices '$score_matrices' 15 --score_matrices '$score_matrices'
13 #end if 16 #end if
14 #if str($options_type.options_type_selector) == 'advanced': 17 #if str($options_type.options_type_selector) == 'advanced':
15 #set target_gene_family_assembly_cond = $options_type.target_gene_family_assembly_cond 18 #set target_gene_family_assembly_cond = $options_type.target_gene_family_assembly_cond
16 #if str($target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes': 19 #if str($target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes':
17 --gene_family_search '$target_gene_family_assembly_cond.orthogroups' 20 --gene_family_search '$target_gene_family_assembly_cond.orthogroups'
18 --output_pttgf '$output_pttgf'
19 --output_pttgf_dir '$output_pttgf.files_path'
20 --scaffold '$target_gene_family_assembly_cond.scaffold.fields.path' 21 --scaffold '$target_gene_family_assembly_cond.scaffold.fields.path'
21 --method '$target_gene_family_assembly_cond.method' 22 --method '$target_gene_family_assembly_cond.method'
22 --gap_trimming $target_gene_family_assembly_cond.gap_trimming 23 --gap_trimming $target_gene_family_assembly_cond.gap_trimming
24 #if str($target_gene_family_assembly_cond.min_coverage) != '0.0':
25 --min_coverage $target_gene_family_assembly_cond.min_coverage
26 #end if
23 #end if 27 #end if
24 #if str($options_type.strand_specific) == 'yes': 28 #if str($options_type.strand_specific) == 'yes':
25 --strand_specific true 29 --strand_specific
26 #end if 30 #end if
27 #if str($options_type.dereplicate) == 'yes': 31 #if str($options_type.dereplicate) == 'yes':
28 --dereplicate true 32 --dereplicate
29 --output_cleaned_nr_cds '$output_cleaned_nr_cds'
30 --output_cleaned_nr_pep '$output_cleaned_nr_pep'
31 #end if 33 #end if
32 --min_length $options_type.min_length 34 --min_length $options_type.min_length
33 #end if 35 #end if
34 --num_threads \${GALAXY_SLOTS:-4} 36 --num_threads \${GALAXY_SLOTS:-4}
35 --output_cds '$output_cds' 37 &>proc.log
36 --output_cleaned_cds '$output_cleaned_cds' 38 && mv $output_dir/transcripts.cds '$output_cds'
37 --output_cleaned_pep '$output_cleaned_pep' 39 && mv $output_dir/transcripts.pep '$output_pep'
38 --output_pep '$output_pep' 40 && mv $output_dir/transcripts.cleaned.cds '$output_cleaned_cds'
41 && mv $output_dir/transcripts.cleaned.pep '$output_cleaned_pep'
42 #if str($options_type.options_type_selector) == 'advanced':
43 #if str($target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes':
44 && mv $output_dir/targeted_gene_family_assemblies.stats '$output_targeted_gene_families_stats'
45 #end if
46 #if str($options_type.dereplicate) == 'yes':
47 && mv $output_dir/transcripts.cleaned.nr.cds '$output_cleaned_nr_cds'
48 && mv $output_dir/transcripts.cleaned.nr.pep '$output_cleaned_nr_pep'
49 #end if
50 #end if
39 ]]></command> 51 ]]></command>
40 <inputs> 52 <inputs>
41 <param name="input" format="fasta" type="data" label="Transcriptome assembly fasta file"/> 53 <param name="input" format="fasta" type="data" label="Transcriptome assembly fasta file"/>
42 <conditional name="prediction_method_cond"> 54 <conditional name="prediction_method_cond">
43 <param name="prediction_method" type="select" label="Coding regions prediction method"> 55 <param name="prediction_method" type="select" label="Coding regions prediction method">
72 <option value="gfam" selected="true">GFam</option> 84 <option value="gfam" selected="true">GFam</option>
73 <option value="orthofinder">OrthoFinder</option> 85 <option value="orthofinder">OrthoFinder</option>
74 <option value="orthomcl">OrthoMCL</option> 86 <option value="orthomcl">OrthoMCL</option>
75 </param> 87 </param>
76 <param name="gap_trimming" type="float" value="0.1" min="0" max="1.0" label="Trim alignments"/> 88 <param name="gap_trimming" type="float" value="0.1" min="0" max="1.0" label="Trim alignments"/>
89 <param name="min_coverage" type="float" value="0" min="0" max="1.0" label="Minimum alignment coverage"/>
77 </when> 90 </when>
78 </conditional> 91 </conditional>
79 <param name="strand_specific" type="select" label="Strand-specific assembly?"> 92 <param name="strand_specific" type="select" label="Strand-specific assembly?">
80 <option value="no" selected="true">No</option> 93 <option value="no" selected="true">No</option>
81 <option value="yes">Yes</option> 94 <option value="yes">Yes</option>
87 <param name="min_length" type="integer" value="200" label="Minimum sequence length"/> 100 <param name="min_length" type="integer" value="200" label="Minimum sequence length"/>
88 </when> 101 </when>
89 </conditional> 102 </conditional>
90 </inputs> 103 </inputs>
91 <outputs> 104 <outputs>
92 <data name="output_pttgf" format="pttgf" label="Targeted gene families: ${tool.name} on ${on_string}"> 105 <data name="output_targeted_gene_families_stats" format="tabular" label="Targeted gene families statistics: ${tool.name} on ${on_string}">
93 <filter>options_type['options_type_selector'] == 'advanced' and options_type['target_gene_family_assembly_cond']['target_gene_family_assembly'] == 'yes'</filter> 106 <filter>options_type['options_type_selector'] == 'advanced' and options_type['target_gene_family_assembly_cond']['target_gene_family_assembly'] == 'yes'</filter>
94 </data> 107 </data>
108 <collection name="output_targeted_gene_families" type="list" label="Targeted gene families: ${tool.name} on ${on_string}">
109 <discover_datasets pattern="__name__" directory="assemblyPostProcessing_dir/targeted_gene_family_assemblies" format="fasta" />
110 <filter>options_type['options_type_selector'] == 'advanced' and options_type['target_gene_family_assembly_cond']['target_gene_family_assembly'] == 'yes'</filter>
111 </collection>
95 <data name="output_pep" format="fasta" label="transcripts.pep: ${tool.name} on ${on_string}"/> 112 <data name="output_pep" format="fasta" label="transcripts.pep: ${tool.name} on ${on_string}"/>
96 <data name="output_cleaned_pep" format="fasta" label="transcripts.cleaned.pep: ${tool.name} on ${on_string}"/> 113 <data name="output_cleaned_pep" format="fasta" label="transcripts.cleaned.pep: ${tool.name} on ${on_string}"/>
97 <data name="output_cleaned_nr_pep" format="fasta" label="transcripts.cleaned.nr.pep: ${tool.name} on ${on_string}"> 114 <data name="output_cleaned_nr_pep" format="fasta" label="transcripts.cleaned.nr.pep: ${tool.name} on ${on_string}">
98 <filter>options_type['options_type_selector'] == 'advanced' and options_type['dereplicate'] == 'yes'</filter> 115 <filter>options_type['options_type_selector'] == 'advanced' and options_type['dereplicate'] == 'yes'</filter>
99 </data> 116 </data>
132 <param name="target_gene_family_assembly" value="yes"/> 149 <param name="target_gene_family_assembly" value="yes"/>
133 <param name="orthogroups" value="target_orthos.ids"/> 150 <param name="orthogroups" value="target_orthos.ids"/>
134 <param name="scaffold" value="22Gv1.1"/> 151 <param name="scaffold" value="22Gv1.1"/>
135 <param name="method" value="orthomcl"/> 152 <param name="method" value="orthomcl"/>
136 <param name="dereplicate" value="yes"/> 153 <param name="dereplicate" value="yes"/>
137 <output name="output_pttgf" file="output.pttgf" ftype="pttgf"/> 154 <output_collection name="output_targeted_gene_families" type="list">
155 </output_collection>
156 <output name="output_targeted_gene_families_stats" file="output_targeted_gene_families_stats.tabular" ftype="tabular"/>
138 <output name="output_cds" file="transcripts_tgf.cds" ftype="fasta"/> 157 <output name="output_cds" file="transcripts_tgf.cds" ftype="fasta"/>
139 <output name="output_cleaned_cds" file="transcripts.cleaned_tgf.cds" ftype="fasta"/> 158 <output name="output_cleaned_cds" file="transcripts.cleaned_tgf.cds" ftype="fasta"/>
140 <output name="output_cleaned_nr_cds" file="transcripts_tgf.cleaned.nr.cds" ftype="fasta"/> 159 <output name="output_cleaned_nr_cds" file="transcripts_tgf.cleaned.nr.cds" ftype="fasta"/>
141 <output name="output_cleaned_nr_pep" file="transcripts_tgf.cleaned.nr.pep" ftype="fasta"/> 160 <output name="output_cleaned_nr_pep" file="transcripts_tgf.cleaned.nr.pep" ftype="fasta"/>
142 <output name="output_cleaned_pep" file="transcripts.cleaned_tgf.pep" ftype="fasta"/> 161 <output name="output_cleaned_pep" file="transcripts.cleaned_tgf.pep" ftype="fasta"/>
161 180
162 **Other options** 181 **Other options**
163 182
164 * **Perform targeted gene assembly?** - selecting 'Yes' enables local assembly of one or more targeted gene families in a specific scaffold. Scaffolds are defined in PlantTribes as clusters of paralogous/orthologous sequences from a specified set of proteomes[5-7]. 183 * **Perform targeted gene assembly?** - selecting 'Yes' enables local assembly of one or more targeted gene families in a specific scaffold. Scaffolds are defined in PlantTribes as clusters of paralogous/orthologous sequences from a specified set of proteomes[5-7].
165 184
166 * **Targeted gene families** - select a history item containing a list of targeted orthogroup identifiers corresponding to the gene family classification from a specified scaffold. Gene family identifiers can be obtained from the function annotation table ("Orthogroup ID" field of .summary file) of scaffold data installed into Galaxy via the PlantTribes Scaffolds Download Data Manager tool, and also available at the PlantTribes github repository (https://github.com/dePamphilis/PlantTribes/tree/master/config). 185 * **Targeted gene families** - select a history item containing a list of targeted orthogroup identifiers corresponding to the gene family classification from a specified scaffold. Gene family identifiers can be obtained from the function annotation table ("Orthogroup ID" field of .summary file) of scaffold data installed into Galaxy via the PlantTribes Scaffolds Download Data Manager tool, and are also available in the PlantTribes "annotation" directory of the scaffold data download.
167 * **Gene family scaffold** - one of the PlantTribes gene family scaffolds (installed into Galaxy by the PlantTribes Scaffolds Download Data Manager tool) whose orthogroup(s) are targeted for the localized assembly. 186 * **Gene family scaffold** - one of the PlantTribes gene family scaffolds (installed into Galaxy by the PlantTribes Scaffolds Download Data Manager tool) whose orthogroup(s) are targeted for the localized assembly.
168 * **Protein clustering method** - gene family scaffold protein clustering method. Each PlantTribes scaffold data has up to three sets of clusters - GFam[8] (clusters of consensus domain architecture), OrthoFinder[9] (broadly defined clusters) or OrthoMCL[10] (narrowly defined clusters). You can also install your own data scaffold created using a different clustering method as long as it conforms to the PlantTribes scaffold data format. 187 * **Protein clustering method** - gene family scaffold protein clustering method. Each PlantTribes scaffold data has up to three sets of clusters - GFam[8] (clusters of consensus domain architecture), OrthoFinder[9] (broadly defined clusters) or OrthoMCL[10] (narrowly defined clusters). You can also install your own data scaffold created using a different clustering method as long as it conforms to the PlantTribes scaffold data format.
169 * **Trim alignments** - trim gene family multiple sequence alignments that include scaffold backbone genes and locally assembled transcripts to remove non-conserved regions (gappy sites)[11]. The trimmed alignments are used in assigning scores to locally assembled transcripts to determine how well they compare to the backbone gene models. The default setting of 0.1 removes sites that have gaps in 90% or more of the sequences in the multiple sequence alignment. This option is restricted to the range 0.0 - 1.0. 188 * **Trim alignments** - trim gene family multiple sequence alignments that include scaffold backbone genes and locally assembled transcripts to remove non-conserved regions (gappy sites)[11]. The trimmed alignments are used in assigning scores to locally assembled transcripts to determine how well they compare to the backbone gene models. The default setting of 0.1 removes sites that have gaps in 90% or more of the sequences in the multiple sequence alignment. This option is restricted to the range 0.0 - 1.0.
189 * **Minimum alignment coverage** - allowable sequence coverage in the orthogroup trimmed protein multiple sequence alignments. Selecting transcripts with coverage of at least the average of the backbone orthogroup gene models is recommended. Details are shown in the targeted gene family assembly statistics history item.
170 190
171 * **Strand-specific assembly?** - select 'Yes' if transcriptome library sequences were strand-specific. If 'Yes" is selected, transcripts from the minority strand (antisense) are removed. 191 * **Strand-specific assembly?** - select 'Yes' if transcriptome library sequences were strand-specific. If 'Yes" is selected, transcripts from the minority strand (antisense) are removed.
172 * **Remove duplicate sequences?** - select 'Yes' to remove duplicated and exact subsequences[12]. 192 * **Remove duplicate sequences?** - select 'Yes' to remove duplicated and exact subsequences[12].
173 * **Minimum sequence length** - set the minimum sequence length of predicted coding regions. The default is 200 bp. 193 * **Minimum sequence length** - set the minimum sequence length of predicted coding regions. The default is 200 bp.
174 194