comparison matchms_subsetting.xml @ 0:2b61ec493df6 draft

planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit a0565620150b69e0ca87aa686709c25356436f71

0:2b61ec493df6

<tool id="matchms_subsetting" name="matchms subsetting" version="@TOOL_VERSION@+galaxy0" profile="21.09">
    <description>Extract spectra from a library given unique metadata identifier</description>
    
    <macros>
        <import>macros.xml</import>
        <import>help.xml</import>
    </macros>

    <expand macro="creator"/>

    <edam_operations>
        <edam_operation>operation_2409</edam_operation>
    </edam_operations>
    <expand macro="bio.tools"/>

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

    <command detect_errors='aggressive'><![CDATA[
        python '${matchms_python_cli}'
    ]]></command>

<configfiles>
<configfile name="matchms_python_cli">
import pandas
import matchms
import numpy as np

matchms.set_matchms_logger_level('ERROR')
matchms.Metadata.set_key_replacements({})

spectra = list(matchms.importing.load_from_msp('${spectral_library}', False))

if "$list_of_identifiers.ext" == "csv":
    identifiers_table = pandas.read_csv('${list_of_identifiers}', dtype=object)
else:
    identifiers_table = pandas.read_csv('${list_of_identifiers}', dtype=object, sep='\t')

identifiers_table.columns = map(str.lower, identifiers_table.columns)

spectra_arr = np.asarray(spectra, dtype=object)

def filter_spectra(spectra, identifiers, mode):
    identifier_column = identifiers.columns[0]

    indices = []
    for i, spectrum in enumerate(spectra):
        if spectrum.get(identifier_column) in identifiers.values:
            indices.append(i)

    if mode == "include":
        spectra_filtered = spectra[indices]
    else:
        spectra_filtered = np.delete(spectra, indices)

    return spectra_filtered

filtered_spectra = filter_spectra(spectra_arr, identifiers_table, "${mode}")

matchms.exporting.save_as_msp(filtered_spectra.tolist(), '${output}')
</configfile>
</configfiles>

    <inputs>
        <param label="Spectra file" name="spectral_library" type="data" format="msp"
            help="Mass spectral library file." />
        <param label="Select mode" name="mode" type="select"
                help="Include/Exclude the spectra matching the identifiers in the file. The default is include.">
            <option value="include" selected="true">include</option>
            <option value="exclude">exclude</option>
        </param>
        <param label="list of identifiers" name="list_of_identifiers" type="data" format="csv,tsv,tabular"
            help="file containing list of identifiers in tsv or csv." />

    </inputs>

    <outputs>
        <data label="${tool.name} on ${on_string}" name="output" format="msp">
        </data>
    </outputs>

    <tests>
        <test>
            <param name="spectral_library" value="out_matchms_add_key.msp" ftype="msp"/>
            <param name="mode" value="include"/>
            <param name="list_of_identifiers" value="subsetting/identifier.csv" ftype="csv"/>
            <output name="output" file="subsetting/subsetting_output.msp" ftype="msp"/>
        </test>
        <test>
            <param name="spectral_library" value="out_matchms_add_key.msp" ftype="msp"/>
            <param name="mode" value="exclude"/>
            <param name="list_of_identifiers" value="subsetting/identifier.csv" ftype="csv"/>
            <output name="output" file="subsetting/subsetting_output2.msp" ftype="msp"/>
        </test>
    </tests>

    <help>
        **Description**
            The tool takes an msp file and a csv/tsv file containing list of identifier and 
            extract spectra from a library based on the provided list of identifiers.
    </help>

    <citations>
        <citation type="doi">https://doi.org/10.5281/zenodo.8083373</citation>
    </citations>
</tool>