Mercurial > repos > greg > gene_family_integrator
changeset 8:87e2450855c2 draft
Uploaded
author | greg |
---|---|
date | Fri, 28 Apr 2017 09:14:26 -0400 |
parents | 0bf47f620170 |
children | 2457321db163 |
files | .shed.yml gene_family_integrator.xml macros.xml repository_dependencies.xml |
diffstat | 4 files changed, 95 insertions(+), 56 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/.shed.yml Fri Apr 28 09:14:26 2017 -0400 @@ -0,0 +1,14 @@ +name: plant_tribes_gene_family_integrator +owner: greg +description: | + Contains a tool that integrates de novo assembly sequences with scaffold gene family sequences. +homepage_url: https://github.com/dePamphilis/PlantTribes +long_description: | + Contains a tool that 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. This tool integrates classified post processed de novo transcriptome + assembly sequences with the scaffold gene family sequences. +remote_repository_url: https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/plant_tribes/gene_family_integrator +type: unrestricted +categories: +- Phylogenetics
--- a/gene_family_integrator.xml Mon Apr 10 11:32:22 2017 -0400 +++ b/gene_family_integrator.xml Fri Apr 28 09:14:26 2017 -0400 @@ -1,5 +1,5 @@ <tool id="plant_tribes_gene_family_integrator" name="GeneFamilyIntegrator" version="@WRAPPER_VERSION@.0"> - <description>integrates de novo assembly sequences with scaffold gene family sequences</description> + <description>integrates gene models in pre-computed orthologous gene family clusters with classified gene coding sequences</description> <macros> <import>macros.xml</import> </macros> @@ -34,17 +34,21 @@ </command> <inputs> <conditional name="input_format_cond"> - <param name="input_format" type="select" label="Select type of data to sub sample"> - <option value="ptortho">Gene family clusters</option> - <option value="ptorthocs">Gene family clusters with corresponding coding sequences</option> + <param name="input_format" type="select" label="Classified orthogroup fasta files"> + <option value="ptortho">Proteins orthogroup fasta files</option> + <option value="ptorthocs">Protein and coding sequences orthogroup fasta files</option> </param> <when value="ptortho"> - <param name="input_ptortho" format="ptortho" type="data" label="Gene family clusters" /> + <param name="input_ptortho" format="ptortho" type="data" label="Proteins orthogroup fasta files"> + <!-- <validator type="empty_files_path" /> --> + </param> <expand macro="param_scaffold" /> <expand macro="param_method" /> </when> <when value="ptorthocs"> - <param name="input_ptorthocs" format="ptorthocs" type="data" label="Gene family clusters with corresponding coding sequences" /> + <param name="input_ptorthocs" format="ptorthocs" type="data" label="Protein and coding sequences orthogroup fasta files"> + <!-- <validator type="empty_files_path" /> --> + </param> <expand macro="param_scaffold" /> <expand macro="param_method" /> <expand macro="param_orthogroup_fna" /> @@ -67,24 +71,65 @@ </tests> <help> This tool is one of the PlantTribes collection of automated modular analysis pipelines for comparative and evolutionary -analyses of genome-scale gene families and transcriptomes. This tool integrates classified post processed de novo transcriptome -assembly sequence(s) with the scaffold gene family sequences. +analyses of genome-scale gene families and transcriptomes. This tool integrates PlantTribes scaffold orthogroup backbone +gene models with gene coding sequences classified into the scaffold by the GeneFamilyClassifier tool. ----- **Required options** - * **Gene family clusters** - sequences classified into gene family clusters, optionally including corresponding coding sequences. - * **Gene family scaffold** - one of the PlantTribes gene family scaffolds [2-4] installed into Galaxy by the PlantTribes Scaffold Data Manager tool. + * **Classified orthogroup fasta files** - orthogroup fasta files produced by the GeneFamilyClassifier tool selected from your history. Depending on how the GeneFamilyClassifier tool was executed, these could either be proteins or proteins and their corresponding coding sequences. + + - **Proteins orthogroup fasta files** - proteins fasta files. + - **Protein and coding sequences orthogroup fasta files** - proteins and their corresponding coding sequences fasta files. + + * **Gene family scaffold** - one of the PlantTribes gene family scaffolds installed into Galaxy by the PlantTribes Scaffold Data Manager tool. * **Protein clustering method** - gene family scaffold protein clustering method as described in the AssemblyPostProcessor tool. **Other options** - * **Process corresponding gene family classification orthogroups CDS fasta files** - Select 'Yes' top process corresponding gene family classification orthogroups CDS fasta files. + * **Orthogroups coding sequences** - Select 'Yes' to create corresponding coding sequences orthogroups fasta files for the classified protein sequences. </help> <citations> <expand macro="citation1" /> - <expand macro="citations2to4" /> + <citation type="bibtex"> + @article{Wall2008, + journal = {Nucleic Acids Research}, + author = {2. Wall PK, Leebens-Mack J, Muller KF, Field D, Altman NS}, + title = {PlantTribes: a gene and gene family resource for comparative genomics in plants}, + year = {2008}, + volume = {36}, + number = {suppl 1}, + pages = {D970-D976},} + </citation> + <citation type="bibtex"> + @article{Sasidharan2012, + journal = {Nucleic Acids Research}, + author = {3. Sasidharan R, Nepusz T, Swarbreck D, Huala E, Paccanaro A}, + title = {GFam: a platform for automatic annotation of gene families}, + year = {2012}, + pages = {gks631},} + </citation> + <citation type="bibtex"> + @article{Li2003, + journal = {Genome Research} + author = {4. Li L, Stoeckert CJ, Roos DS}, + title = {OrthoMCL: identification of ortholog groups for eukaryotic genomes}, + year = {2003}, + volume = {13}, + number = {9}, + pages = {2178-2189},} + </citation> + <citation type="bibtex"> + @article{Emms2015, + journal = {Genome Biology} + author = {5. Emms DM, Kelly S}, + title = {OrthoFinder: solving fundamental biases in whole genome comparisons dramatically improves orthogroup inference accuracy}, + year = {2015}, + volume = {16}, + number = {1}, + pages = {157},} + </citation> </citations> </tool>
--- a/macros.xml Mon Apr 10 11:32:22 2017 -0400 +++ b/macros.xml Fri Apr 28 09:14:26 2017 -0400 @@ -3,7 +3,7 @@ <token name="@WRAPPER_VERSION@">0.8</token> <xml name="requirements_assembly_post_processor"> <requirements> - <requirement type="package" version="0.4">plant_tribes_assembly_post_processor</requirement> + <requirement type="package" version="0.8">plant_tribes_assembly_post_processor</requirement> </requirements> </xml> <xml name="requirements_gene_family_aligner"> @@ -59,22 +59,28 @@ </param> </xml> <xml name="param_orthogroup_fna"> - <param name="orthogroup_fna" type="select" label="Process corresponding gene family classification orthogroups CDS fasta files?"> + <param name="orthogroup_fna" type="select" label="Orthogroups coding sequences?"> <option value="yes" selected="true">Yes</option> <option value="no">No</option> </param> </xml> <xml name="param_scaffold"> - <param name="scaffold" type="select" label="Orthogroups or gene families proteins scaffold"> + <param name="scaffold" type="select" label="Gene family scaffold"> <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 in Galaxy to install and populate the PlantTribes scaffolds data table." /> </param> </xml> + <xml name="param_sequence_type"> + <param name="sequence_type" type="select" label="Sequence type used in the phylogenetic inference (dna)"> + <option value="protein" selected="true">Amino acid based</option> + <option value="dna">Nucleotide based</option> + </param> + </xml> <xml name="cond_alignment_method"> <conditional name="alignment_method_cond"> - <param name="alignment_method" type="select" force_select="true" label="Select method for multiple sequence alignments"> - <option value="mafft" selected="true">MAFFT algorithm</option> - <option value="pasta">PASTA algorithm</option> + <param name="alignment_method" type="select" force_select="true" label="Multiple sequence alignment method"> + <option value="mafft" selected="true">MAFFT</option> + <option value="pasta">PASTA</option> </param> <when value="mafft" /> <when value="pasta"> @@ -84,31 +90,31 @@ </xml> <xml name="cond_remove_gappy_sequences"> <conditional name="remove_gappy_sequences_cond"> - <param name="remove_gappy_sequences" type="select" label="Remove gappy sequences in alignments?"> + <param name="remove_gappy_sequences" type="select" label="Alignment post-processing configuration?"> <option value="no" selected="true">No</option> <option value="yes">Yes</option> </param> <when value="no" /> <when value="yes"> <conditional name="trim_type_cond"> - <param name="trim_type" type="select" label="Select process used for gap trimming"> - <option value="gap_trimming" selected="true">Nucleotide based</option> - <option value="automated_trimming">Trim alignments using trimAl's ML heuristic trimming approach</option> + <param name="trim_type" type="select" label="Trimming method"> + <option value="gap_trimming" selected="true">Gap score based trimming</option> + <option value="automated_trimming">Automated heuristic trimming</option> </param> <when value="gap_trimming"> - <param name="gap_trimming" type="float" value="0" min="0" max="1.0" label="Remove sites in alignments with gaps of" help="Zero value has no affect" /> + <param name="gap_trimming" type="float" optional="true" min="0" max="1.0" label="Gap score" /> </when> <when value="automated_trimming" /> </conditional> <conditional name="remove_sequences_with_gaps_cond"> - <param name="remove_sequences_with_gaps" type="select" label="Remove sequences with specified gaps?"> + <param name="remove_sequences_with_gaps" type="select" label="Remove sequences?"> <option value="no" selected="true">No</option> <option value="yes">Yes</option> </param> <when value="no" /> <when value="yes"> - <param name="remove_sequences_with_gaps_of" type="float" value="0" min="0" max="1" label="Remove sequences with gaps of" help="Zero value has no affect" /> - <param name="iterative_realignment" type="integer" value="0" min="0" label="Maximum number of iterations" help="Zero value has no affect"/> + <param name="remove_sequences_with_gaps_of" type="float" optional="true" min="0" max="1" label="Coverage score" /> + <param name="iterative_realignment" type="integer" optional="true" min="0" label="Realignment iteration limit" /> </when> </conditional> </when> @@ -124,34 +130,4 @@ url = {https://github.com/dePamphilis/PlantTribes},} </citation> </xml> - <xml name="citations2to4"> - <citation type="bibtex"> - @article{Sasidharan2012, - journal = {Nucleic Acids Research}, - author = {2. Sasidharan R, Nepusz T, Swarbreck D, Huala E, Paccanaro A}, - title = {GFam: a platform for automatic annotation of gene families}, - year = {2012}, - pages = {gks631},} - </citation> - <citation type="bibtex"> - @article{Li2003, - journal = {Genome Research} - author = {3. Li L, Stoeckert CJ, Roos DS}, - title = {OrthoMCL: identification of ortholog groups for eukaryotic genomes}, - year = {2003}, - volume = {13}, - number = {9}, - pages = {2178-2189},} - </citation> - <citation type="bibtex"> - @article{Emms2015, - journal = {Genome Biology} - author = {4. Emms DM, Kelly S}, - title = {OrthoFinder: solving fundamental biases in whole genome comparisons dramatically improves orthogroup inference accuracy}, - year = {2015}, - volume = {16}, - number = {1}, - pages = {157},} - </citation> - </xml> </macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/repository_dependencies.xml Fri Apr 28 09:14:26 2017 -0400 @@ -0,0 +1,4 @@ +<?xml version="1.0"?> +<repositories description="This tool uses the data installed by the data_manager_plant_tribes_scaffolds_downloader Data Manager tool."> + <repository changeset_revision="8bb32fd5b175" name="data_manager_plant_tribes_scaffolds_downloader" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" /> +</repositories>