Mercurial > repos > greg > plant_tribes_assembly_post_processor
changeset 13:6655e5f6736b draft
Uploaded
| author | greg |
|---|---|
| date | Tue, 29 Nov 2016 13:38:32 -0500 |
| parents | 32ade191a090 |
| children | e4a7b2070ea8 |
| files | plant_tribes_assembly_post_processor.xml |
| diffstat | 1 files changed, 41 insertions(+), 8 deletions(-) [+] |
line wrap: on
line diff
--- a/plant_tribes_assembly_post_processor.xml Tue Nov 29 09:09:12 2016 -0500 +++ b/plant_tribes_assembly_post_processor.xml Tue Nov 29 13:38:32 2016 -0500 @@ -1,5 +1,5 @@ -<tool id="plant_tribes_assembly_post_processor" name="PlantTribes Assembly Post Processor" version="1.0.0"> - <description></description> +<tool id="plant_tribes_assembly_post_processor" name="PlantTribes AssemblyPostProcessor" version="1.0.0"> + <description>pipeline</description> <requirements> <requirement type="package" version="0.2">plant_tribes_assembly_post_processor</requirement> </requirements> @@ -13,7 +13,7 @@ <command> <![CDATA[ AssemblyPostProcesser - --transcripts "$input1" + --transcripts "$input" --prediction_method $prediction_method_cond.prediction_method #if str($prediction_method_cond.prediction_method) == 'estscan': --score_matrices "$score_matrices" @@ -37,7 +37,7 @@ ]]> </command> <inputs> - <param name="input1" format="fasta" type="data" label="De novo transcriptome assembly fasta file"/> + <param name="input" format="fasta" type="data" label="De novo transcriptome assembly fasta file"/> <conditional name="prediction_method_cond"> <param name="prediction_method" type="select" label="Prediction method for coding regions"> <option value="transdecoder" selected="true">TransDecoder</option> @@ -45,6 +45,7 @@ </param> <when value="transdecoder" /> <when value="estscan"> + <!-- TODO: this may require support for a new "smat" datatype --> <param name="score_matrices" format="tabular" type="data" label="Scores matrices which reflect the codons preferences in the studied organisms"/> </when> </conditional> @@ -62,10 +63,9 @@ </param> <when value="no" /> <when value="yes"> - <!-- TODO: this may require support for a new "smat" datatype --> <param name="orthogroups" format="tabular" type="data" label="List of orthogroup identifiers for target gene families to assemble"/> <param name="scaffold" type="select" label="Orthogroups or gene families proteins scaffold"> - <options from_data_table="plant_tribes_scaffolds" column="2" /> + <options from_data_table="plant_tribes_scaffolds" /> <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."/> </param> <param name="method" type="select" label="Protein clustering method"> @@ -90,13 +90,46 @@ </inputs> <outputs> <collection name="transcripts" type="list"> - <discover_datasets pattern="__name__" directory="assemblyPostProcessing_dir" visible="false" /> + <discover_datasets pattern="__name__" directory="assemblyPostProcessing_dir" visible="false" format="fasta"/> </collection> </outputs> <tests> + <test> + <param name="input" value="assembly.fasta" ftype="fasta" /> + <param name="prediction_method" value="transdecoder"/> + <param name="target_gene_family_assembly" value="no"/> + <param name="strand_specific" value="yes"/> + <param name="dereplicate" value="yes"/> + <param name="min_length" value="200"/> + <output_collection name="transcripts" type="list"> + <element name="transcripts.cds" file="transcripts.cds" ftype="fasta" /> + <element name="transcripts.cleaned.cds" file="transcripts.cleaned.cds" ftype="fasta" /> + <element name="transcripts.cleaned.nr.cds" file="transcripts.cleaned.nr.cds" ftype="fasta" /> + <element name="transcripts.cleaned.nr.pep" file="transcripts.cleaned.nr.pep" ftype="fasta" /> + <element name="transcripts.cleaned.pep" file="transcripts.cleaned.pep" ftype="fasta" /> + <element name="transcripts.pep" file="transcripts.pep" ftype="fasta" /> + </output_collection> + </test> </tests> <help> -Assemblyr Post Processor pipeline +This tool is one of the PlantTribes' collection of automated modular analysis pipelines that utilize objective classifications of +complete protein sequences from sequenced plant genomes to perform comparative evolutionary studies. It post-processes de novo assembly +transcripts into putative coding sequences and their corresponding amino acid translations. + +----- + +**Options** + + * **Prediction method for coding regions** - The prediction method for coding regions; one of ESTScan or TransDecoder. + * **Target gene family assembly?** - Select yes to target gene families to assemble. + * **List of orthogroup identifiers for target gene families to assemble** - History item with a list of orthogroup identifiers for target gene families to assemble. The next version of this tool will use a dynamic select list for this feature. + * **Orthogroups or gene families proteins scaffold** - PlantTribes scaffolds data. + * **Protein clustering method** - One of GFam, OrthoFinder or OrthoMCL. + * **Remove gappy sites in alignments** - Removes gappy sites in alignments (i.e. 0.1 removes sites with 90% gaps): [0.0 to 1.0] + * **De novo transcriptome assembly was performed with strand-specific library?** - Select yes if de novo transcriptome assembly was performed with strand-specific library. + * **Remove repeated sequences in predicted coding regions?** - Select yes to remove repeated sequences in predicted coding regions. + * **Minimum sequence length of predicted coding regions** - Set the minimum sequence length of predicted coding regions. + </help> <citations> <citation type="bibtex">