view recetox_aplcms_merge_known_table.xml @ 9:17a48d0a80f4 draft

planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/recetox_aplcms commit b88eaca14b030fc0023989f3c83479e4975d172a

<tool id="recetox_aplcms_merge_known_table" name="recetox-aplcms - merge known table" version="@TOOL_VERSION@+galaxy0" profile="21.09">
    <description>join knowledge from aligned features and known table.</description>
    <macros>
        <import>macros.xml</import>
        <import>help.xml</import>
    </macros>
    <expand macro="annotation"/>
    <edam_operations>
        <edam_operation>operation_3436</edam_operation>
    </edam_operations>
    <expand macro="refs"/>
    <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[
              metadata <- load_data_from_parquet_file('$metadata_file')
              rt_table <- load_data_from_parquet_file('$rt_file')
              intensity_table <- load_data_from_parquet_file('$intensity_file')
              known_table <- read_known_table('$known_table')

              feature_tables <- join_tables_to_list(metadata, rt_table, intensity_table)

              merged <- merge_features_and_known_table(
                  features = feature_tables,
                  known_table = known_table,
                  #if $match_tol_ppm:
                  match_tol_ppm = $match_tol_ppm,
                  #else:
                  match_tol_ppm = NA,
                  #end if
                  mz_tol_relative = $mz_tol_relative_ppm * 1e-06,
                  rt_tol_relative = $rt_tol,
                  #if $direction.selection == "TRUE":
                  new_feature_min_count = $direction.new_feature_min_count,
                  #end if
                  from_features_to_known_table = $direction.selection
              )

              #if $direction.selection == "TRUE":
              save_known_table(merged, '$output_known_table')
              save_pairing(merged, '$output_pairing')
              #else:
              save_aligned_features(merged, '$output_metadata_file', '$output_rt_file', '$output_intensity_file')
              #end if
         ]]></configfile>
    </configfiles>

    <inputs>
        <param name="metadata_file" type="data" format="parquet" label="Metadata table"
               help="Peak metadata table from the align features step" />
        <param name="rt_file" type="data" format="parquet" label="RT table"
               help="Table with retention times for features (rows) across samples (columns)." />
        <param name="intensity_file" type="data" format="parquet" label="Intensity table"
               help="Table with intensities for features (rows) across samples (columns)." />
        <param label="Table of known features" name="known_table" type="data" format="parquet"
               help="A data table containing the known metabolite ions and previously found features. The table must
               contain these 18 columns: chemical_formula (optional), HMDB_ID (optional), KEGG_compound_ID (optional),
               neutral.mass (optional), ion.type (the ion form - optional), m.z (either theoretical or mean observed
               m/z value of previously found features), Number_profiles_processed (the total number of processed
               samples to build this database), Percent_found (the percentage of historically processed samples in
               which the feature appeared), mz_min (minimum  observed m/z value), mz_max (maximum observed m/z value),
               RT_mean (mean observed retention time), RT_sd (standard deviation of observed retention time),
               RT_min (minimum observed retention time), RT_max (maximum observed retention time),
               int_mean.log. (mean observed log intensity), int_sd.log. (standard deviation of observed log intensity),
               int_min.log. (minimum observed log intensity), int_max.log. (maximum observed log intensity)." />
        <expand macro="tolerances"/>

        <conditional name="direction">
            <param label="Tables merge direction" name="selection" type="select"
                   help="Choose between merging feature to known_table and known_table to features.">
                <option value="TRUE">Merge features to known table</option>
                <option value="FALSE">Merge known table to features</option>
            </param>
            <when value="TRUE">
                <param name="new_feature_min_count" type="integer" value="2" min="1" label="Minimal occurence of feature"
                       help="The minimum number of occurrences of a historically unseen (unknown) feature to add
                       this feature into the database of known features." />
            </when>
            <when value="FALSE"></when>
        </conditional>

        <param name="match_tol_ppm" type="integer" optional="true" min="0" label="Match tolerance [ppm]"
               help="The ppm tolerance to match identified features to known metabolites/features." />
    </inputs>

    <outputs>
        <data name="output_metadata_file" format="parquet" label="${tool.name} on ${on_string} (metadata table)">
            <filter>direction['selection'] == 'FALSE'</filter>
        </data>
        <data name="output_rt_file" format="parquet" label="${tool.name} on ${on_string} (rt table)">
            <filter>direction['selection'] == 'FALSE'</filter>
        </data>
        <data name="output_intensity_file" format="parquet" label="${tool.name} on ${on_string} (intensity table)">
            <filter>direction['selection'] == 'FALSE'</filter>
        </data>

        <data label="${tool.name} on ${on_string} (known table)" name="output_known_table" format="parquet" >
            <filter>direction['selection'] == 'TRUE'</filter>
        </data>
        <data label="${tool.name} on ${on_string} (pairing)" name="output_pairing" format="parquet" >
            <filter>direction['selection'] == 'TRUE'</filter>
        </data>
    </outputs>

    <tests>
        <test expect_failure="true" />
    </tests>

    <help>
        <![CDATA[
            @MERGE_KNOWN_TABLES_HELP@

            @GENERAL_HELP@
        ]]>
    </help>

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