comparison assembly_post_processor.xml @ 10:4d73965d99a2 draft default tip

"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/phylogenetics/plant_tribes/assembly_post_processor commit 71ba0e157346927bf42b788f552b95a71556b28a"

9:9c72c91d291f

    <code file="get_clustering_methods.py"/>
    <command detect_errors="exit_code"><![CDATA[
#set output_dir = 'assemblyPostProcessing_dir'
AssemblyPostProcessor
--transcripts '$input'
--prediction_method $prediction_method_cond.prediction_method
#if str($prediction_method_cond.prediction_method) == 'estscan':
    --score_matrices '$score_matrices'
#end if
#if str($options_type.options_type_selector) == 'advanced':
    #set target_gene_family_assembly_cond = $options_type.target_gene_family_assembly_cond
    #if str($target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes':
        --gene_family_search '$target_gene_family_assembly_cond.orthogroups'
        --scaffold '$target_gene_family_assembly_cond.scaffold.fields.path'

        #end if
    #end if
fi]]></command>
    <inputs>
        <param name="input" format="fasta" type="data" label="Transcriptome assembly fasta file"/>
        <conditional name="prediction_method_cond">
            <param name="prediction_method" type="select" label="Coding regions prediction method">
                <option value="transdecoder" selected="true">TransDecoder</option>
                <option value="estscan">ESTScan</option>
            </param>
            <when value="transdecoder" />
            <when value="estscan">
                <param name="score_matrices" format="smat" type="data" label="Scores matrices"/>
            </when>
        </conditional>
        <conditional name="options_type">
            <param name="options_type_selector" type="select" label="Options configuration">
                <option value="basic" selected="true">Basic</option>
                <option value="advanced">Advanced</option>
            </param>

        <data name="output_cds" format="fasta" label="transcripts.cds: ${tool.name} on ${on_string}"/>
    </outputs>
    <tests>
        <test>
            <param name="input" value="assembly.fasta" ftype="fasta"/>
            <param name="prediction_method" value="transdecoder"/>
            <output name="output_cds" file="transcripts.cds" ftype="fasta"/>
            <output name="output_cleaned_cds" file="transcripts.cleaned.cds" ftype="fasta"/>
            <output name="output_cleaned_pep" file="transcripts.cleaned.pep" ftype="fasta"/>
            <output name="output_pep" file="transcripts.pep" ftype="fasta"/>
        </test>
        <test>
            <param name="input" value="assembly.fasta" ftype="fasta"/>
            <param name="prediction_method" value="estscan"/>
            <param name="score_matrices" value="arabidopsis_thaliana.smat" ftype="smat"/>
            <param name="options_type_selector" value="advanced"/>
            <param name="dereplicate" value="yes"/>
            <output name="output_cds" file="transcripts2.cds" ftype="fasta"/>
            <output name="output_cleaned_cds" file="transcripts.cleaned.nr.cds" ftype="fasta"/>
            <output name="output_cleaned_nr_cds" file="transcripts.cleaned.nr.cds" ftype="fasta"/>
            <output name="output_cleaned_nr_pep" file="transcripts.cleaned.nr.pep" ftype="fasta"/>
            <output name="output_cleaned_pep" file="transcripts.cleaned.nr.pep" ftype="fasta"/>
            <output name="output_pep" file="transcripts2.pep" ftype="fasta"/>
        </test>
        <test>
            <param name="input" value="assembly_tgf.fasta" ftype="fasta"/>
            <param name="prediction_method" value="transdecoder"/>
            <param name="options_type_selector" value="advanced"/>
            <param name="target_gene_family_assembly" value="yes"/>
            <param name="orthogroups" value="target_orthos.ids"/>
            <param name="scaffold" value="22Gv1.1"/>
            <param name="method" value="orthomcl"/>
            <param name="dereplicate" value="yes"/>
            <output_collection name="output_targeted_gene_families" type="list">
            </output_collection>
            <output name="output_targeted_gene_families_stats" file="output_targeted_gene_families_stats.tabular" ftype="tabular"/>

**Required options**

 * **Transcriptome assembly fasta file** - either de novo or reference-guided transcriptome assembly fasta file selected from your history.
 * **Coding regions prediction method** - method for finding coding regions within transcripts.  Available methods are TransDecoder[3] and ESTScan[4].
 * **Scores matrices** - scores matrices, based on a related species, are required when ESTScan is used to find coding regions.  Details of how to create species-specific scores matrices can be found on the ESTScan website (http://estscan.sourceforge.net).  Matrices of some organisms are also available to download.

**Other options**

 * **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].

            title = {De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis},
            year = {2013},
            volume = {8},
            number = {8},
            pages = {1494-1512},}
        </citation>
        <citation type="bibtex">
            @article{Iseli1999,
            journal = {ISMB},
            author = {4. Iseli C, Jongeneel CV, Bucher P},
            title = {ESTScan: a program for detecting, evaluating, and reconstructing potential coding regions in EST sequences},
            year = {1999},
            volume = {99},
            pages = {138-148},
            url = {http://estscan.sourceforge.net},}
        </citation>
        <citation type="bibtex">
            @article{Huang1999,
            journal = {Genome Research},
            author = {5. Huang X, Madan A},

10:4d73965d99a2

    <code file="get_clustering_methods.py"/>
    <command detect_errors="exit_code"><![CDATA[
#set output_dir = 'assemblyPostProcessing_dir'
AssemblyPostProcessor
--transcripts '$input'
--prediction_method 'transdecoder'
#if str($options_type.options_type_selector) == 'advanced':
    #set target_gene_family_assembly_cond = $options_type.target_gene_family_assembly_cond
    #if str($target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes':
        --gene_family_search '$target_gene_family_assembly_cond.orthogroups'
        --scaffold '$target_gene_family_assembly_cond.scaffold.fields.path'

        #end if
    #end if
fi]]></command>
    <inputs>
        <param name="input" format="fasta" type="data" label="Transcriptome assembly fasta file"/>
        <conditional name="options_type">
            <param name="options_type_selector" type="select" label="Options configuration">
                <option value="basic" selected="true">Basic</option>
                <option value="advanced">Advanced</option>
            </param>

        <data name="output_cds" format="fasta" label="transcripts.cds: ${tool.name} on ${on_string}"/>
    </outputs>
    <tests>
        <test>
            <param name="input" value="assembly.fasta" ftype="fasta"/>
            <output name="output_cds" file="transcripts.cds" ftype="fasta"/>
            <output name="output_cleaned_cds" file="transcripts.cleaned.cds" ftype="fasta"/>
            <output name="output_cleaned_pep" file="transcripts.cleaned.pep" ftype="fasta"/>
            <output name="output_pep" file="transcripts.pep" ftype="fasta"/>
        </test>
        <test>
            <param name="input" value="assembly_tgf.fasta" ftype="fasta"/>
            <param name="options_type_selector" value="advanced"/>
            <param name="target_gene_family_assembly" value="yes"/>
            <param name="orthogroups" value="target_orthos.ids"/>
            <param name="method" value="orthomcl"/>
            <param name="dereplicate" value="yes"/>
            <output_collection name="output_targeted_gene_families" type="list">
            </output_collection>
            <output name="output_targeted_gene_families_stats" file="output_targeted_gene_families_stats.tabular" ftype="tabular"/>

**Required options**

 * **Transcriptome assembly fasta file** - either de novo or reference-guided transcriptome assembly fasta file selected from your history.
 * **Coding regions prediction method** - method for finding coding regions within transcripts.  Available methods are TransDecoder[3] and ESTScan[4].

**Other options**

 * **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].

            title = {De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis},
            year = {2013},
            volume = {8},
            number = {8},
            pages = {1494-1512},}
        </citation>
        <citation type="bibtex">
            @article{Huang1999,
            journal = {Genome Research},
            author = {5. Huang X, Madan A},