comparison matchms_spectral_similarity.xml @ 0:9ff95a1a2705 draft

planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f79a5b51599254817727bc9028b9797ea994cb4e

0:9ff95a1a2705

<tool id="matchms_spectral_similarity" name="matchms spectral similarity" version="@TOOL_VERSION@+galaxy0" profile="21.09">
    <description>matchms spectral similarity calculation</description>

    <macros>
        <import>macros.xml</import>
        <import>help.xml</import>
    </macros>
    <expand macro="creator"/>
    <expand macro="bio.tools"/>

    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">matchms</requirement>
    </requirements>

    <environment_variables>
        <environment_variable name="MPLCONFIGDIR">\$_GALAXY_JOB_TMP_DIR</environment_variable>
    </environment_variables>

    <command detect_errors="exit_code"><![CDATA[
        python3 ${python_wrapper}
    ]]> </command>

<configfiles>
<configfile name="python_wrapper">
@init_logger@

from matchms.similarity import (CosineGreedy, CosineHungarian, MetadataMatch,
                                ModifiedCosine, NeutralLossesCosine)

similarity = ${similarity_metric}(
    ${algorithm.tolerance},
    ${algorithm.mz_power},
    ${algorithm.intensity_power}
)
name="${similarity_metric}_${algorithm.tolerance}_${algorithm.mz_power}_${algorithm.intensity_power}"

@init_scores@

layer = similarity.sparse_array(
    references=scores.references,
    queries=scores.queries,
    idx_row = scores._scores.row,
    idx_col = scores._scores.col,
    is_symmetric=False)

scores._scores.add_sparse_data(scores._scores.row, scores._scores.col, layer, name)

scores.filter_by_range(inplace=True, name=name+"_matches", low=0)
scores.to_json("$similarity_scores")
</configfile>
</configfiles>
    <inputs>
        <expand macro="input_param"/>
        <param label="Similarity metric" name="similarity_metric" type="select" display="radio"
            help="Similarity metric to use for score computation.">
            <expand macro="similarity_metrics"/>
        </param>
        <expand macro="similarity_algorithm_params"/>
    </inputs>

    <outputs>
        <data label="$similarity_metric scores of ${on_string}" name="similarity_scores" format="json"/>
    </outputs>
    <tests>
        <test> <!-- TEST #1: Test scoring of the same file formats. -->
            <param name="references" value="similarity/RECETOX_Exposome_pesticides_HR_MS_20220323.msp" ftype="msp"/>
            <param name="queries" value="similarity/fill2.msp" ftype="msp"/>
            <param name="similarity_metric" value="CosineGreedy"/>
            <output name="similarity_scores" file="spectral_similarity/test1.json" ftype="json"/>
        </test>
        <test> <!-- TEST #2: Test scoring with scores as json. -->
            <param name="use_scores" value="True"/>
            <param name="scores_in" value="metadata_match/ri_match_60.json" ftype="json"/>
            <param name="similarity_metric" value="CosineHungarian"/>
            <output name="similarity_scores" file="spectral_similarity/test2.json" ftype="json"/>
        </test>
    </tests>

    <help>
        Description
            To compute the spectral similarity, only peaks matching another within the specified tolerance are used.
            Non-overlapping peaks do not contribute to the score computation.
            This spectrum vectorization can be interpreted as taking the intersection of spectra A and B.

            This is different from the NIST scoring algorithm which computes a weighted score computed for both spaces, A and B.
            For more details see this `galaxy training`_.

        .. rubric:: **Footnotes**
        .. [1] SQL join types explained on LearnSQL_.
        
        .. _LearnSQL: https://learnsql.com/blog/sql-joins-types-explained/
        .. _galaxy training: https://training.galaxyproject.org/training-material/topics/metabolomics/tutorials/gc_ms_with_xcms/tutorial.html

        @HELP_matchms@
    </help>

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