comparison recetox_aplcms_align_features.xml @ 2:4d1583e15960 draft

planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/recetox_aplcms commit 506df2aef355b3791567283e1a175914f06b405a

1:148327f1e1be

<tool id="recetox_aplcms_align_features" name="RECETOX apLCMS - align features" version="@TOOL_VERSION@+galaxy1">
    <description>align features from LC/MS spectra across samples</description>
    <macros>
        <import>macros.xml</import>
        <import>macros_split.xml</import>
    </macros>
    <expand macro="creator"/>

    <expand macro="requirements"/>
    <command detect_errors="aggressive"><![CDATA[
        sh ${symlink_inputs} &&
        Rscript -e 'source("${__tool_directory__}/utils.R")' -e 'source("${run_script}")'
    ]]></command>
    <configfiles>
        <configfile name="symlink_inputs">
            #for $infile in $ms_files
                ln -s '${infile}' '${infile.element_identifier}'
            #end for
             #for $infile in $corrected_files
                ln -s '${infile}' '${infile.element_identifier}'
            #end for
        </configfile>
        <configfile name="run_script"><![CDATA[
            #set filenames_str = str("', '").join([str($f.element_identifier) for $f in $ms_files])
            files_list <- sort_samples_by_acquisition_number(c('$filenames_str'))
            sample_names <- get_sample_name(files_list)

            #set corrected_files = str("', '").join([str($f.element_identifier) for $f in $corrected_files])
            corrected_features <- load_features(c('$corrected_files'))

            aligned <- align_features(
                sample_names = sample_names,
                features = corrected_features,
                min.exp = $min_exp,
                mz.tol = $peak_alignment.align_mz_tol,
                chr.tol = $peak_alignment.align_chr_tol,
                find.tol.max.d = 10 * $mz_tol,
                max.align.mz.diff = $peak_alignment.max_align_mz_diff,
                do.plot = FALSE
            )

            save_aligned_features(aligned, "$rt_cross_table", "$int_cross_table", "$tolerances")
        ]]></configfile>
    </configfiles>

    <inputs>
        <param name="ms_files" type="data_collection" collection_type="list" format="mzdata,mzml,mzxml,netcdf"
               label="Input data collection" help="Mass spectrometry file for peak extraction." />
        <param name="corrected_files" type="data_collection" collection_type="list" format="parquet"
               label="Input corrected feature samples collection"
               help="Mass spectrometry files containing corrected feature samples." />
        <expand macro="mz_tol_macro"/>
        <param name="min_exp" type="integer" min="1" value="2" label="min_exp"
               help="If a feature is to be included in the final feature table, it must be present in at least this number of spectra." />
        <expand macro="peak_alignment"/>
    </inputs>

    <outputs>
        <data name="tolerances" format="parquet" label="${tool.name} on ${on_string} (tolerances)" />
        <data name="rt_cross_table" format="parquet" label="${tool.name} on ${on_string} (rt cross table)" />
        <data name="int_cross_table" format="parquet" label="${tool.name} on ${on_string} (int cross table)" />
    </outputs>

    <tests>
        <test>
            <param name="ms_files">
                <collection type="list">
                    <element name="mbr_test0.mzml" value="mbr_test0.mzml"/>
                    <element name="mbr_test1.mzml" value="mbr_test1.mzml"/>
                    <element name="mbr_test2.mzml" value="mbr_test2.mzml"/>
                </collection>
            </param>
            <param name="corrected_files">
                <collection type="list">
                    <element name="corrected_features_0.parquet" value="corrected_expected/corrected_0.parquet"/>
                    <element name="corrected_features_1.parquet" value="corrected_expected/corrected_1.parquet"/>
                    <element name="corrected_features_2.parquet" value="corrected_expected/corrected_2.parquet"/>
                </collection>
            </param>
            <output name="tolerances" file="tolerances.parquet" ftype="parquet"/>
            <output name="rt_cross_table" file="rt_cross_table.parquet" ftype="parquet"/>
            <output name="int_cross_table" file="int_cross_table.parquet" ftype="parquet"/>
        </test>
    </tests>

    <help>
        <![CDATA[
            This is a tool which runs apLCMS alignment of features.

            @GENERAL_HELP@
        ]]>
    </help>

2:4d1583e15960

<tool id="recetox_aplcms_align_features" name="recetox-aplcms - align features" version="@TOOL_VERSION@+galaxy0">
    <description>align peaks across samples</description>
    <macros>
        <import>macros.xml</import>
        <import>help.xml</import>
    </macros>
    <expand macro="creator"/>
    <expand macro="requirements"/>

    <command detect_errors="aggressive"><![CDATA[
        Rscript -e 'source("${__tool_directory__}/utils.R")' -e 'source("${run_script}")'
    ]]></command>
    <configfiles>
        <configfile name="run_script"><![CDATA[
             #set filenames = str("', '").join([str($f) for $f in $files])
             feature_tables <- load_parquet_collection(c('$filenames'))
             sample_names <- unlist(lapply(feature_tables, load_sample_name))

             validate_sample_names(sample_names)

             ordering <- order(sample_names)
             feature_tables <- feature_tables[ordering]
             sample_names <- sample_names[ordering]

             tolerances <- load_data_from_parquet_file('$input_tolerances')

             aligned_features <- create_aligned_feature_table(
                  features_table = dplyr::bind_rows(feature_tables),
                  min_occurrence = $min_occurrence,
                  sample_names = sample_names,
                  mz_tol_relative = get_mz_tol(tolerances),
                  rt_tol_relative = get_rt_tol(tolerances)
             )

             save_aligned_features(aligned_features, '$metadata_file', '$rt_file', '$intensity_file')
        ]]></configfile>
    </configfiles>

    <inputs>
        <param name="files" type="data_collection" collection_type="list" format="parquet"
               label="Clustered features" help="List of tables containing clustered features." />
        <param label="Input tolerances values" name="input_tolerances" type="data" format="parquet"
               help="Table containing tolerance values." />
        <param name="min_occurrence" type="integer" min="2" value="2" label="min_occurrence"
               help="A feature has to show up in at least this number of profiles to be included in the final result." />
    </inputs>

    <outputs>
        <data name="metadata_file" format="parquet" label="${tool.name} on ${on_string} (metadata table)"/>
        <data name="rt_file" format="parquet" label="${tool.name} on ${on_string} (rt table)"/>
        <data name="intensity_file" format="parquet" label="${tool.name} on ${on_string} (intensity table)"/>
    </outputs>

    <tests>

    </tests>

    <help>
        <![CDATA[
            @ALIGN_FEATURES_HELP@

            @GENERAL_HELP@
        ]]>
    </help>