comparison assembly_post_processor.xml @ 84:b1102f939fdd draft

Uploaded
author greg
date Fri, 13 Oct 2017 14:08:02 -0400
parents 8378d126347a
children b5aac0d2c99c
comparison
equal deleted inserted replaced
83:ed2cc7e78e9b 84:b1102f939fdd
18 #if str($target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes': 18 #if str($target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes':
19 --gene_family_search '$target_gene_family_assembly_cond.orthogroups' 19 --gene_family_search '$target_gene_family_assembly_cond.orthogroups'
20 --scaffold '$target_gene_family_assembly_cond.scaffold.fields.path' 20 --scaffold '$target_gene_family_assembly_cond.scaffold.fields.path'
21 --method '$target_gene_family_assembly_cond.method' 21 --method '$target_gene_family_assembly_cond.method'
22 --gap_trimming $target_gene_family_assembly_cond.gap_trimming 22 --gap_trimming $target_gene_family_assembly_cond.gap_trimming
23 --output_targeted_gene_families_stats '$output_targeted_gene_families_stats'
23 #end if 24 #end if
24 #if str($options_type.strand_specific) == 'yes': 25 #if str($options_type.strand_specific) == 'yes':
25 --strand_specific true 26 --strand_specific true
26 #end if 27 #end if
27 #if str($options_type.dereplicate) == 'yes': 28 #if str($options_type.dereplicate) == 'yes':
87 <param name="min_length" type="integer" value="200" label="Minimum sequence length"/> 88 <param name="min_length" type="integer" value="200" label="Minimum sequence length"/>
88 </when> 89 </when>
89 </conditional> 90 </conditional>
90 </inputs> 91 </inputs>
91 <outputs> 92 <outputs>
93 <data name="output_targeted_gene_families_stats" format="tabular" label="Targeted gene families statistics: ${tool.name} on ${on_string}">
94 <filter>options_type['options_type_selector'] == 'advanced' and options_type['target_gene_family_assembly_cond']['target_gene_family_assembly'] == 'yes'</filter>
95 </data>
92 <collection name="output_targeted_gene_families" type="list" label="Targeted gene families: ${tool.name} on ${on_string}"> 96 <collection name="output_targeted_gene_families" type="list" label="Targeted gene families: ${tool.name} on ${on_string}">
93 <discover_datasets pattern="__name__" directory="assemblyPostProcessing_dir/targeted_gene_family_assemblies" format="fasta" /> 97 <discover_datasets pattern="__name__" directory="assemblyPostProcessing_dir/targeted_gene_family_assemblies" format="fasta" />
94 <filter>options_type['options_type_selector'] == 'advanced' and options_type['target_gene_family_assembly_cond']['target_gene_family_assembly'] == 'yes'</filter> 98 <filter>options_type['options_type_selector'] == 'advanced' and options_type['target_gene_family_assembly_cond']['target_gene_family_assembly'] == 'yes'</filter>
95 </collection> 99 </collection>
96 <data name="output_pep" format="fasta" label="transcripts.pep: ${tool.name} on ${on_string}"/> 100 <data name="output_pep" format="fasta" label="transcripts.pep: ${tool.name} on ${on_string}"/>
138 <output_collection name="output_targeted_gene_families" type="list"> 142 <output_collection name="output_targeted_gene_families" type="list">
139 <element name="752.faa" file="752.faa" ftype="fasta"/> 143 <element name="752.faa" file="752.faa" ftype="fasta"/>
140 <element name="752.fasta" file="752.fasta" ftype="fasta"/> 144 <element name="752.fasta" file="752.fasta" ftype="fasta"/>
141 <element name="752.fna" file="752.fna" ftype="fasta"/> 145 <element name="752.fna" file="752.fna" ftype="fasta"/>
142 </output_collection> 146 </output_collection>
147 <output name="output_targeted_gene_families_stats" file="output_targeted_gene_families.stats" ftype="tabular"/>
143 <output name="output_cds" file="transcripts_tgf.cds" ftype="fasta"/> 148 <output name="output_cds" file="transcripts_tgf.cds" ftype="fasta"/>
144 <output name="output_cleaned_cds" file="transcripts.cleaned_tgf.cds" ftype="fasta"/> 149 <output name="output_cleaned_cds" file="transcripts.cleaned_tgf.cds" ftype="fasta"/>
145 <output name="output_cleaned_nr_cds" file="transcripts_tgf.cleaned.nr.cds" ftype="fasta"/> 150 <output name="output_cleaned_nr_cds" file="transcripts_tgf.cleaned.nr.cds" ftype="fasta"/>
146 <output name="output_cleaned_nr_pep" file="transcripts_tgf.cleaned.nr.pep" ftype="fasta"/> 151 <output name="output_cleaned_nr_pep" file="transcripts_tgf.cleaned.nr.pep" ftype="fasta"/>
147 <output name="output_cleaned_pep" file="transcripts.cleaned_tgf.pep" ftype="fasta"/> 152 <output name="output_cleaned_pep" file="transcripts.cleaned_tgf.pep" ftype="fasta"/>
166 171
167 **Other options** 172 **Other options**
168 173
169 * **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]. 174 * **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].
170 175
171 * **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). 176 * **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.
172 * **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. 177 * **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.
173 * **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. 178 * **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.
174 * **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. 179 * **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.
175 180
176 * **Strand-specific assembly?** - select 'Yes' if transcriptome library sequences were strand-specific. If 'Yes" is selected, transcripts from the minority strand (antisense) are removed. 181 * **Strand-specific assembly?** - select 'Yes' if transcriptome library sequences were strand-specific. If 'Yes" is selected, transcripts from the minority strand (antisense) are removed.