view ExtractCgMLST.xml @ 3:9c4c2191b550 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/chewbbaca commit 8bb518e20d68623904232ae28bb8a51ec05c1c4a
author iuc
date Wed, 25 Sep 2024 14:13:48 +0000
parents a302f0fef852
children
line wrap: on
line source

<tool id="chewbbaca_extractcgmlst" name="chewBBACA ExtractCgMLST" version="@CHEW_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>Determine the set of loci that constitute the core genome</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[
        chewBBACA.py ExtractCgMLST
        --t $threshold
        #if $genes2remove:
            --r '$genes2remove'
        #end if 
        #if $genomes2remove:
            --g '$genomes2remove'
        #end if 
        -i '$input_file' -o 'output'
    ]]></command>
    <inputs>
        <param argument="--input-file" type="data" label="Allelic Profiles" format="tabular"/>
        <section name="advanced" title="Advanced options">
            <param argument="--genomes2remove" type="data" format="txt" label="Genomes/rows to remove from the matrix" optional="true" help="One genome identifier per line"/>
            <param argument="--threshold" type="text" value="0.95 0.99 1" label="threshold" help="Genes that constitute the core genome must be in a proportion of genomes that is at least equal to this value. Users can provide multiple values as a space-separated list.">
                <validator type="regex">[ .0-9]+</validator>
            </param>
            <param argument="--genes2remove" type="data" format="tabular" label="List of genes  to exclude from analysis" optional="true" help="the list of genes listed in the &quot;paralogous_counts.tsv&quot; file created by the AlleleCall process."/>
        </section>
    </inputs>
    <outputs>
        <collection name="output_collection" type="list" format="html,tsv,txt" label="${tool.name} on ${on_string}">
            <discover_datasets pattern="__name_and_ext__" directory="output"/>
        </collection>
    </outputs>
    <tests>
        <test>
            <param name="input_file" value="results_alleles.tsv"/>
            <output_collection name="output_collection" type="list">
                <element name="missing_loci_stats">
                    <assert_contents>
                        <has_text_matching expression="GCA_000007265"/>
                    </assert_contents>
                </element>
                <element name="presence_absence">
                    <assert_contents>
                        <has_text_matching expression="GCA_000007265"/>
                    </assert_contents>
                </element>
            </output_collection>
        </test>
    </tests>
    <help>
chewBBACA is a software suite for the creation and evaluation of core genome and whole genome MultiLocus Sequence Typing (cg/wgMLST) schemas and results.

cgMLST schemas are defined as the set of loci that are present in all strains under analysis or, due to sequencing/assembly limitations, >95% of strains analyzed. In order to have a robust definition of a cgMLST schema for a given bacterial species, a set of representative strains of the diversity of a given species should be selected. 

.. class:: infomark

**Note**

The user can define a **space-separated** list of values for --threshold
    </help>
    <expand macro="citations" />
</tool>