Mercurial > repos > recetox > matchms_similarity
view matchms_similarity.xml @ 1:872d8040f713 draft default tip
planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit b1cc1aebf796f170d93e3dd46ffcdefdc7b8018a
author | recetox |
---|---|
date | Thu, 12 Oct 2023 13:25:30 +0000 |
parents | e5010b19d64d |
children |
line wrap: on
line source
<tool id="matchms_similarity" name="matchms similarity" version="@TOOL_VERSION@+galaxy2" profile="21.09"> <description>calculate the similarity score and matched peaks</description> <macros> <import>macros.xml</import> <import>help.xml</import> </macros> <expand macro="creator"/> <expand macro="bio.tools"/> <requirements> <requirement type="package" version="0.8.0">spec2vec</requirement> <requirement type="package" version="@TOOL_VERSION@">matchms</requirement> </requirements> <command detect_errors="exit_code"><![CDATA[ sh ${matchms_python_cli} ]]> </command> <environment_variables> <environment_variable name="MPLCONFIGDIR">\$_GALAXY_JOB_TMP_DIR</environment_variable> </environment_variables> <configfiles> <configfile name="matchms_python_cli"> python3 ${__tool_directory__}/matchms_similarity_wrapper.py \ #if $ri_filtering.is_true == "TRUE" -r $ri_filtering.tolerance \ #end if #if $symmetric.is_symmetric == "TRUE" -s \ #else --ref "$references" \ --ref_format "$references.ext" \ #end if --array_type "$array_type" \ #if $metric.similarity_metric == "Spec2Vec" --spec2vec_model "$metric.model_metadata" \ --spec2vec_weights "$metric.model_weights" \ --allow_missing_percentage $metric.algorithm.allow_missing_percentage \ #end if "$queries" \ "$queries.ext" \ "$metric.similarity_metric" \ #if $metric.similarity_metric == "Spec2Vec" 0 \ 0 \ #else $metric.algorithm.tolerance \ $metric.algorithm.mz_power \ #end if $metric.algorithm.intensity_power \ "$similarity_scores" </configfile> </configfiles> <inputs> <param label="Queries spectra" name="queries" type="data" format="msp,mgf" help="Query mass spectra to match against references."/> <conditional name="symmetric"> <param name="is_symmetric" label="Symmetric" type="select"> <option value="FALSE" selected="true">FALSE</option> <option value="TRUE">TRUE</option> </param> <when value="FALSE"> <param label="Reference spectra" name="references" type="data" format="msp,mgf" help="Reference mass spectra to match against as library."/> </when> <when value="TRUE"></when> </conditional> <param label="Scores array type" name="array_type" type="select" display="radio" help="Matrix type for storing scores objects. Sparse type more memory-efficient and better for large arrays. Note that whatever is selected the output might still be sprase array if scores have too much 0-entries."> <option value="numpy" selected="true">dense</option> <option value="sparse">sparse</option> </param> <conditional name="metric"> <param label="Similarity metric" name="similarity_metric" type="select" display="radio" help="Similarity metric to use for score computation."> <expand macro="similarity_metrics"/> <option value="Spec2Vec">Spec2Vec</option> </param> <when value="CosineGreedy"> <expand macro="similarity_algorithm_params"/> </when> <when value="CosineHungarian"> <expand macro="similarity_algorithm_params"/> </when> <when value="ModifiedCosine"> <expand macro="similarity_algorithm_params"/> </when> <when value="NeutralLossesCosine"> <expand macro="similarity_algorithm_params"/> </when> <when value="Spec2Vec"> <param label="Model JSON file" name="model_metadata" type="data" format="json" help="Model JSON file to use for Spec2Vec similarity computing."/> <param label="Model NPY file" name="model_weights" type="data" format="binary" help="Model NPY file to use for Spec2Vec similarity computing."/> <section name="algorithm" title="Algorithm Parameters" expanded="true"> <param label="intensity_power" name="intensity_power" type="float" value="0.0" help="Spectrum vectors are a weighted sum of the word vectors. The given word intensities will be raised to the given power. The default is 0, which means that no weighing will be done."/> <param label="Maximum share of new peaks" name="allow_missing_percentage" type="float" value="0.1" max="1.0" min="0.0" help="Maximum allowed share of the peaks that are new to the model in relation to the whole peak corpus."/> </section> </when> </conditional> <conditional name="ri_filtering"> <param name="is_true" label="Apply RI filtering" type="select"> <option value="FALSE" selected="true">FALSE</option> <option value="TRUE">TRUE</option> </param> <when value="TRUE"> <param label="tolerance" name="tolerance" type="float" value="60" help="Peaks will be considered a match when less than tolerance apart."/> </when> <when value="FALSE"></when> </conditional> </inputs> <outputs> <data label="$metric.similarity_metric scores of ${on_string}" name="similarity_scores" format="json"/> </outputs> <tests> <test> <!-- TEST #1: Test scoring of different file formats. --> <param name="references" value="similarity/fill.mgf" ftype="mgf"/> <param name="queries" value="similarity/fill2.msp" ftype="msp"/> <conditional name="metric"> <param name="similarity_metric" value="CosineGreedy"/> </conditional> <output name="similarity_scores" file="similarity/scores_test1_out.json" ftype="json"/> </test> <test> <!-- TEST #2: 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"/> <conditional name="metric"> <param name="similarity_metric" value="CosineGreedy"/> </conditional> <output name="similarity_scores" file="similarity/scores_test2_out.json" ftype="json"/> </test> <test> <!-- TEST #3: Test scoring with applying RI filtering --> <param name="references" value="similarity/fill.mgf" ftype="mgf"/> <param name="queries" value="similarity/fill2.msp" ftype="msp"/> <conditional name="ri_filtering"> <param name="is_true" value="TRUE"></param> <param name="tolerance" value="60.0" /> </conditional> <conditional name="metric"> <param name="similarity_metric" value="CosineHungarian"/> </conditional> <output name="similarity_scores" file="similarity/scores_test3_out.json" ftype="json"/> </test> <test> <!-- TEST #4: Test symmetric scoring. --> <param name="queries" value="similarity/recetox_gc-ei_ms_20201028.msp" ftype="msp"/> <param name="is_symmetric" value="TRUE"/> <conditional name="metric"> <param name="similarity_metric" value="NeutralLossesCosine"/> </conditional> <output name="similarity_scores" file="similarity/scores_test4_out.json" ftype="json"/> </test> <test> <!-- TEST #5: Test symmetric scoring with applying RI filtering. --> <param name="queries" value="similarity/recetox_gc-ei_ms_20201028.msp" ftype="msp"/> <conditional name="metric"> <param name="similarity_metric" value="ModifiedCosine"/> </conditional> <param name="is_symmetric" value="TRUE" /> <conditional name="ri_filtering"> <param name="is_true" value="TRUE"></param> <param name="tolerance" value="60.0" /> </conditional> <output name="similarity_scores" file="similarity/scores_test5_out.json" ftype="json"/> </test> <test> <!-- TEST #6: Test Spec2Vec. --> <param name="references" value="similarity/spec2vec/inp_filtered_library.msp" ftype="msp"/> <param name="queries" value="similarity/spec2vec/inp_filtered_spectra.msp" ftype="msp"/> <conditional name="metric"> <param name="similarity_metric" value="Spec2Vec"/> <param name="model_metadata" value="similarity/spec2vec/model.json" ftype="json"/> <param name="model_weights" value="similarity/spec2vec/weights_100.binary" ftype="auto"/> <param name="allow_missing_percentage" value="1.0"/> </conditional> <output name="similarity_scores" file="similarity/scores_test6_out.json" ftype="json" compare="sim_size" delta="1000"/> </test> </tests> <help> @HELP_matchms@ </help> <expand macro="citations"/> </tool>