view cfsan_snp_pipeline_snp_matrix.xml @ 2:610251aac6ef draft

Uploaded

<tool id="cfsan_snp_pipeline_snp_matrix" name="CFSAN SNP Pipeline: create SNP matrix"  version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>and associated matrices</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[
#if str($reference_cond.reference_source) == 'cached'
    set reference = '$reference_cond.reference.fields.path'
#else:
    set reference = '$reference_cond.reference'
#end if

python '$__tool_directory__/snp_wind.py' ./ -p 'consensus.fasta'
#for $fa in sorted($input_fasta_collection, key=lambda f: f.element_identifier):
    -n '$fa.element_identifier' -f '$fa'
#end for
> ./file &&
cfsan_snp_pipeline snp_matrix -o '$output_snp_matrix_fasta' ./file &&
cfsan_snp_pipeline distance -p '$output_snp_pairwise_matrix_tsv' -m '$output_snp_distance_matrix_tsv' '$output_snp_matrix_fasta' &&
cfsan_snp_pipeline snp_reference -l '$input_merged_snp_sites' -o '$output_snp_reference_fasta' '$reference'
    ]]></command>
    <inputs>
        <param name="input_fasta_collection" type="data_collection" format="fasta" collection_type="list" label="Collection of fasta files"/>
        <expand macro="reference_cond"/>
        <param name="input_merged_snp_sites" type="data" format="tabular" label="Merged SNP sites tabular file"/>
    </inputs>
    <outputs>
        <data name="output_snp_matrix_fasta" format="fasta" label="SNP matrix (fasta)"/>
        <data name="output_snp_pairwise_matrix_tsv" format="tsv" label="SNP pairwise matrix (tsv)"/>
        <data name="output_snp_distance_matrix_tsv" format="tsv" label="SNP distance matrix (tsv)"/>
        <data name="output_snp_reference_fasta" format="fasta" label="SNP Reference (fasta)"/>
    </outputs>
    <tests>
        <test>
            <param name="input_fasta_collection">
                <collection type="list">
                    <element name="sample1" value="input1.fasta"/>
                    <element name="sample2" value="input2.fasta"/>
                    <element name="sample3" value="input3.fasta"/>
                    <element name="sample4" value="input4.fasta"/>
                </collection>
            </param>
            <param name="reference_source" value="history"/>
            <param name="reference" value="lambda_virus.fasta"/>
            <param name="input_merged_snp_sites" value="input_merged_snp_sites.tabular"/>
            <output name="output_snp_matrix_fasta" value="output_snp_matrix.fasta"/>
            <output name="output_snp_pairwise_matrix_tsv" value="output_snp_pairwise_matrix.tsv"/>
            <output name="output_snp_distance_matrix_tsv" value="output_snp_distance_matrix.tsv"/>
            <output name="output_snp_reference_fasta" value="output_snp_reference.fasta"/>
        </test>
    </tests>
    <help><![CDATA[
**What it does**

Create the SNP matrix containing the consensus base for each of the samples at
the positions where high-confidence SNPs were found in any of the samples. The
matrix contains one row per sample and one column per SNP position. Non-SNP
positions are not included in the matrix. The matrix is formatted as a fasta
file, with each sequence (all of identical length) corresponding to the SNPs
in the correspondingly named sequence.

**More information**

CFSAN SNP Pipeline `create SNP matrix documentation <https://snp-pipeline.readthedocs.io/en/latest/cmd_ref.html#snp-matrix>`_
    ]]></help>
    <expand macro="citations"/>
</tool>