view gene_family_integrator.xml @ 6:00f14e3bbe9f draft

Uploaded

<tool id="plant_tribes_gene_family_integrator" name="GeneFamilyIntegrator" version="@WRAPPER_VERSION@.3.0">
    <description>integrates gene models in pre-computed orthologous gene family clusters with classified gene coding sequences</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <requirements>
        <requirement type="package" version="1.0.3">plant_tribes_gene_family_integrator</requirement>
    </requirements>
    <code file="get_clustering_methods.py"/>
    <command detect_errors="exit_code"><![CDATA[
#set input_dir = 'input_dir'
mkdir $input_dir &&
#for $i in $input:
    #set filename = $i.file_name
    #set name = $i.name
    ln -s $filename $input_dir/$name &&
#end for
GeneFamilyIntegrator
--orthogroup_fasta '$input_dir'
--scaffold '$scaffold.fields.path'
--method $method
&>gene_family_integrator_log.txt;
if [[ $? -ne 0 ]]; then
    cp gene_family_integrator_log.txt integratedGeneFamilies_dir;
    exit 1;
fi
    ]]></command>
    <inputs>
        <param name="input" format="fasta" type="data_collection" collection_type="list" label="Classified orthogroup fasta files" />
        <expand macro="param_scaffold" />
        <expand macro="param_method" />
    </inputs>
    <outputs>
        <collection name="output" type="list" label="${tool.name} (integrated gene family clusters) on ${on_string}">
            <discover_datasets pattern="__name__" directory="integratedGeneFamilies_dir" format="fasta" />
        </collection>
    </outputs>
    <tests>
        <test>
            <param name="input">
                <collection type="list">
                    <element name="3722.faa" value="3722.faa"/>
                    <element name="3722.fna" value="3722.fna"/>
                    <element name="38889.faa" value="38889.faa"/>
                    <element name="38889.fna" value="38889.fna"/>
                    <element name="39614.faa" value="39614.faa"/>
                    <element name="39614.fna" value="39614.fna"/>
                </collection>
            </param>
            <param name="scaffold" value="22Gv1.1"/>
            <param name="method" value="orthomcl"/>
            <output_collection name="output" type="list">
                <element name="3722.faa" file="3722_integrated.faa" ftype="fasta"/>
                <element name="3722.fna" file="3722_integrated.fna" ftype="fasta"/>
                <element name="38889.faa" file="38889_integrated.faa" ftype="fasta"/>
                <element name="38889.fna" file="38889_integrated.fna" ftype="fasta"/>
                <element name="39614.faa" file="39614_integrated.faa" ftype="fasta"/>
                <element name="39614.fna" file="39614_integrated.fna" ftype="fasta"/>
            </output_collection>
        </test>
    </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 PlantTribes scaffold orthogroup backbone
gene models with gene coding sequences classified into the scaffold by the GeneFamilyClassifier tool.

-----

**Required options**

 * **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.

 * **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.
    </help>
    <citations>
        <expand macro="citation1" />
        <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>