view ncbi_fcs_adaptor.xml @ 0:d55ad8533d58 draft default tip

planemo upload for repository https://github.com/richard-burhans/galaxytools/tree/main/tools/ncbi_fcs_adaptor commit 74ccb005520db16be005e6471e8624357aca7d94

<tool id="ncbi_fcs_adaptor" name="NCBI FCS Adaptor" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>detects contamination from foreign organisms in genome sequences</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="edam_ontology"/>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[
        /app/fcs/bin/av_screen_x -o "\$(pwd)" '$tax' '$input'
    ]]></command>
    <inputs>
        <param name="input" type="data" format="fasta" label="Input file (Fasta file)" help="To detect contamination from adaptors and vectors, a genome sequence in a fasta file."/>
        <param name="tax" type="select" label="Choose the taxonomy">
            <option value="--euk" selected="true">Eukaryotes</option>
            <option value="--prok">Prokaryotes</option>
        </param>
        <section name="advanced" title="Advanced options" expanded="false">
            <param name="optional_log" type="select" label="Choose additional logs" multiple="true" display="checkboxes">
                <option value="adaptor_log" selected="false">Adaptor log</option>
                <option value="validate_fasta_log" selected="false">FASTA validation log</option>
            </param>
        </section>
    </inputs>
    <outputs>
        <data name="adaptor_report" format="tabular" from_work_dir="fcs_adaptor_report.txt" label="${tool.name} on ${on_string}: Adaptor report"/>
        <data name="clean_fasta" format="fasta" from_work_dir="cleaned_sequences/*.dat" label="${tool.name} on ${on_string}: Cleaned Fasta"/>
        <data name="adaptor_log" format="txt" from_work_dir="fcs_adaptor.log" label="${tool.name} on ${on_string}: Adaptor log">
            <filter>advanced['optional_log'] is not None and 'adaptor_log' in advanced['optional_log'].split(',')</filter>
        </data>
        <data name="validate_fasta_log" format="txt" from_work_dir="validate_fasta.txt" label="${tool.name} on ${on_string}: FASTA validation log">
            <filter>advanced['optional_log'] is not None and 'validate_fasta_log' in advanced['optional_log'].split(',')</filter>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="2">
            <param name="input" value="fcsadaptor_prok_test.fa.gz" ftype="fasta"/>
            <param name="tax" value="--prok"/>
            <output name="adaptor_report" file="adaptor_report.tab" ftype="tabular" />
            <output name="clean_fasta" decompress="true" file="clean_fasta.fa.gz" ftype="fasta" />
        </test>
        <test expect_num_outputs="4">
            <param name="input" value="fcsadaptor_prok_test.fa.gz" ftype="fasta"/>
            <param name="tax" value="--prok"/>
            <param name="optional_log" value="adaptor_log,validate_fasta_log"/>
            <output name="adaptor_report" file="adaptor_report.tab" ftype="tabular" />
            <output name="clean_fasta" decompress="true" file="clean_fasta.fa.gz" ftype="fasta" />
            <output name="adaptor_log">
                <assert_contents>
                    <has_text_matching expression="\bINFO \[workflow \] completed success\b" />
                </assert_contents>
            </output>
            <output name="validate_fasta_log">
                <assert_contents>
                    <has_size value="0" />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
    FCS-adaptor is a high-throughput implementation of NCBI VecScreen.  FCS-adaptor runs a pipeline to screen input sequences against a non-redudant database of adaptors and vectors using stringent BLAST searches and remove contaminants from your genome.

    FCS-adaptor removes terminal and internal matches to foreign sequences. Sequences identified as mostly adaptor/vector are removed entirely. FCS-adaptor produces a tabular output with details on the contaminant sequences identified as well as a cleaned FASTA.

    Please see the wiki for more information.

    https://github.com/ncbi/fcs/wiki/FCS-adaptor
    ]]></help>
</tool>