comparison assembly_post_processor.xml @ 39:b0ea1e985a38 draft

Uploaded

38:9b5baf12bdbe

<tool id="plant_tribes_assembly_post_processor" name="AssemblyPostProcessor" version="0.4.0">
    <description>post-processes de novo transcriptome assembly</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements_assembly_post_processor" />

            #if str($options_type.options_type_selector) == 'advanced':
                #if str($options_type.target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes':
                    --gene_family_search '$options_type.target_gene_family_assembly_cond.orthogroups'
                    --scaffold '$options_type.target_gene_family_assembly_cond.scaffold.fields.path'
                    --method '$options_type.target_gene_family_assembly_cond.method'
                #end if
                --gap_trimming $options_type.gap_trimming
                #if str($options_type.strand_specific) == 'yes':
                    --strand_specific
                #end if
                #if str($options_type.dereplicate) == 'yes':
                    --dereplicate

                        <param name="method" type="select" label="Protein clustering method">
                            <option value="gfam" selected="true">GFam</option>
                            <option value="orthofinder">OrthoFinder</option>
                            <option value="orthomcl">OrthoMCL</option>
                        </param>
                    </when>
                </conditional>
                <param name="gap_trimming" type="float" value="0.1" min="0" max="1.0" label="Trim alignments"/>
                <param name="strand_specific" type="select" label="Strand-specific assembly?">
                    <option value="no" selected="true">No</option>
                    <option value="yes">Yes</option>
                </param>
                <param name="dereplicate" type="select" label="Remove duplicate sequences?">

**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].

   * **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 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).
   * **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.
   * **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.

 * **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% of the sequences in the multiple sequence alignment.  This option is restricted to the range 0.0 - 1.0.
 * **Strand-specific assembly?** - select 'Yes' if transcriptome library sequences were strand-specific.  If 'Yes" is selected, transcripts from the minority strand (antisense) are removed.
 * **Remove duplicate sequences?** - select 'Yes' to remove duplicated and exact subsequences[12].
 * **Minimum sequence length** - set the minimum sequence length of predicted coding regions. The default is 200 bp.

    </help>

39:b0ea1e985a38

<tool id="plant_tribes_assembly_post_processor" name="AssemblyPostProcessor" version="@WRAPPER_VERSION@.0">
    <description>post-processes de novo transcriptome assembly</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements_assembly_post_processor" />

            #if str($options_type.options_type_selector) == 'advanced':
                #if str($options_type.target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes':
                    --gene_family_search '$options_type.target_gene_family_assembly_cond.orthogroups'
                    --scaffold '$options_type.target_gene_family_assembly_cond.scaffold.fields.path'
                    --method '$options_type.target_gene_family_assembly_cond.method'
                    --gap_trimming $options_type.gap_trimming
                #end if
                #if str($options_type.strand_specific) == 'yes':
                    --strand_specific
                #end if
                #if str($options_type.dereplicate) == 'yes':
                    --dereplicate

                        <param name="method" type="select" label="Protein clustering method">
                            <option value="gfam" selected="true">GFam</option>
                            <option value="orthofinder">OrthoFinder</option>
                            <option value="orthomcl">OrthoMCL</option>
                        </param>
                        <param name="gap_trimming" type="float" value="0.1" min="0" max="1.0" label="Trim alignments"/>
                    </when>
                </conditional>
                <param name="strand_specific" type="select" label="Strand-specific assembly?">
                    <option value="no" selected="true">No</option>
                    <option value="yes">Yes</option>
                </param>
                <param name="dereplicate" type="select" label="Remove duplicate sequences?">

**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].

   * **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).
   * **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.
   * **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.
   * **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.

 * **Strand-specific assembly?** - select 'Yes' if transcriptome library sequences were strand-specific.  If 'Yes" is selected, transcripts from the minority strand (antisense) are removed.
 * **Remove duplicate sequences?** - select 'Yes' to remove duplicated and exact subsequences[12].
 * **Minimum sequence length** - set the minimum sequence length of predicted coding regions. The default is 200 bp.

    </help>