annotate recetox_xmsannotator_advanced.xml @ 1:2c6fa447f6a0 draft

planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/recetox-xmsannotator commit 8547c5323747595eabbeed29039a1b2363491243

<tool id="recetox_xmsannotator_advanced" name="recetox-xMSannotator" version="@TOOL_VERSION@+galaxy0">

    <description>annotate peak intensity table including scores and confidence levels</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="creator"/>
    <xrefs>
        <xref type="bio.tools">recetox-xmsannotator</xref>
    </xrefs>
    <expand macro="requirements" />
    <command detect_errors="aggressive"><![CDATA[
        Rscript -e 'source("${__tool_directory__}/utils.R")' -e "n_workers <- \${GALAXY_SLOTS:-1}" -e "source('${wrapper}')"
    ]]></command>

    <configfiles>
        <configfile name="wrapper"><![CDATA[
            metadata_table <- load_table("$metadata_table", "$metadata_table.ext")
            intensity_table <- load_table("$intensity_table", "$intensity_table.ext")
            peak_table <- create_peak_table(metadata_table, intensity_table)

            filter_by <- create_filter_by_adducts("$filter_by")

            annotation <- advanced_annotation(
                peak_table = peak_table,
                adduct_table = load_table("$adduct_table", "$adduct_table.ext"),
                adduct_weights = load_table("$adduct_weights", "$adduct_weights.ext"),
                compound_table = load_table("$compound_table", "$compound_table.ext"),
                mass_tolerance = 1e-6 * ${mass_tolerance_ppm},
                time_tolerance = $time_tolerance,
                correlation_threshold = as.double($clustering.correlation_threshold),
                min_cluster_size = as.integer($clustering.min_cluster_size),
                deep_split = as.integer($clustering.deep_split),
                network_type = "$clustering.network_type",
                redundancy_filtering = $scoring.redundancy_filtering,
                n_workers = n_workers,
                intensity_deviation_tolerance = as.double($intensity_deviation_tolerance),
                mass_defect_tolerance = as.double($mass_defect_tolerance),
                mass_defect_precision = as.double($mass_defect_precision),
                peak_rt_width = as.integer($peak_rt_width),
                maximum_isotopes = as.integer($maximum_isotopes),
                min_ions_per_chemical = as.integer($min_ions_per_chemical),
                filter_by = filter_by
            )

            save_table(annotation, "$output_file", "$output_file.ext")
        ]]></configfile>
    </configfiles>

    <inputs>
        <expand macro="inputs"/>
        <expand macro="tolerance">
            <param name="time_tolerance" type="float" value="10" min="0">
                <label>Retention time tolerance [s]</label>
                <help>
                    Retention time tolerance in seconds for finding peaks derived from the same parent compound.
                </help>
            </param>
        </expand>
        <section name="clustering" title="Clustering">
            <param name="correlation_threshold" type="float" value="0.7">
                <label>Correlation threshold</label>
                <help>Correlation threshold between peaks to qualify as adducts/isotopes of the same metabolite.</help>
            </param>
            <param name="min_cluster_size" type="integer" value="10" min="1">
                <label>Minimum cluster size</label>
                <help>The minimum number of nodes to be considered as a cluster.</help>
            </param>
            <param name="deep_split" type="integer" value="2" min="0" max="4">
                <label>Deep split</label>
                <help>
                    Deep split provides a rough control over sensitivity to cluster splitting. The higher the value,
                    the more and smaller clusters will be produced (see WGCNA package documentation).
                </help>
            </param>
            <param name="network_type" type="select" display="radio">
                <label>Network type</label>
                <help>
                    Network type parameter affects how the network's adjacency matrix is created from the correlation
                    matrix (see WGCNA package documentation).
                </help>
                <option value="signed">Signed</option>
                <option value="unsigned" selected="true">Unsigned</option>
            </param>
        </section>
        <section name="scoring" title="Scoring" expanded="true">
            <param name="strict_boosting" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE">
                <label>Strict boosting</label>
                <help>
                    Boost the scores of metabolites that not only belongs to the same pathway but also to the same
                    cluster. Otherwise, do not account for cluster membership.
                </help>
            </param>
            <param name="min_isp" type="integer" min="0" value="1">
                <label>Minimum number of expected isotopes</label>
                <help>
                    Minimum number of adducts/isotopes to be present for a match to be considered as a high confidence match.
                </help>
            </param>
            <param name="max_isp" type="integer" min="0" value="5">
                <label>Maximum number of expected isotopes</label>
                <help>
                    Maximum number of adducts/isotopes to be present for a match to be considered as a high confidence match.
                </help>
            </param>
            <param name="redundancy_filtering" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE">
                <label>Redundancy filtering</label>
                <help>Whether to filter out low-scored multiple matcher or not.</help>
            </param>
        </section>
        <param name="intensity_deviation_tolerance" type="float" value="0.1">
            <label>Tolerance of intensity deviation</label>
            <help>A numeric threshold by which an intensity ratio of two isotopic peaks may differ from their actual abundance ratio.</help>
        </param>
        <param name="mass_defect_tolerance" type="float" value="0.1">
            <label>Tolerance of mass defect</label>
            <help>Maximum difference in mass defect between two peaks of the same compound.</help>
        </param>
        <param name="mass_defect_precision" type="float" value="0.01">
            <label>Precision for computing mass defect</label>
        </param>
        <param name="peak_rt_width" type="integer" value="1">
            <label>Estimated chromatographic peak width</label>
        </param>
        <param name="maximum_isotopes" type="integer" value="10">
            <label>Maximum isotopes</label>
        </param>
        <param name="min_ions_per_chemical" type="integer" value="2">
            <label>Minimum ions per chemical</label>
        </param>
        <param name="filter_by" type="select" label="Adducts to filter by" multiple="true" optional="true">
            <option value="M-H" selected="true">M-H</option>
            <option value="M+H" selected="true">M+H</option>
            <option value="2M-H">2M-H</option>
            <option value="M-2H">M-2H</option>
        </param>
    </inputs>

    <outputs>
        <expand macro="outputs"/>
    </outputs>

    <tests>
        <test>
            <param name="metadata_table" value="metadata_table.parquet" ftype="parquet" />
            <param name="intensity_table" value="intensity_table.parquet" ftype="parquet" />
            <param name="compound_table" value="database.parquet" ftype="parquet" />
            <param name="adduct_table" value="adduct_table.parquet" ftype="parquet" />
            <output name="output_file" file="expected_output.parquet" ftype="parquet"/>
        </test>
        <test>
            <param name="metadata_table" value="metadata_table.csv" ftype="csv" />
            <param name="intensity_table" value="intensity_table.csv" ftype="csv" />
            <param name="compound_table" value="database.csv" ftype="csv" />
            <param name="adduct_table" value="adduct_table.csv" ftype="csv" />
            <output name="output_file" file="expected_output.csv" ftype="csv"/>
        </test>
    </tests>

    <help>
        <![CDATA[
            @HELP@
        ]]>
    </help>

    <citations>
        <expand macro="citations"/>
    </citations>
</tool>