ipaPy2 PR

tools/ipapy2/.shed.yml

@@ -0,0 +1,15 @@
+name: ipaPy2
+owner: recetox
+remote_repository_url: "https://github.com/RECETOX/galaxytools/tree/master/tools/ipapy2"
+homepage_url: "https://github.com/francescodc87/ipaPy2"
+categories:
+  - Metabolomics
+description: "Mass spectrometry data annotation tool."
+long_description: "New Python implementation of the Integrated Probabilistic Annotation (IPA) - A Bayesian annotation method for LC/MS data integrating biochemical relations, isotope patterns and adduct formation."
+auto_tool_repositories:
+  name_template: "{{ tool_id }}"
+  description_template: "{{ tool_name }} tool from the ipaPy2 package"
+suite:
+  name: suite_ipapy2
+  description: tools from the ipaPy2 suite are used for annotation of mass spectrometry data
+  type: repository_suite_definition

tools/ipapy2/ipapy2_MS1_annotation.py

@@ -0,0 +1,128 @@
+import argparse
+
+
+from ipaPy2 import ipa
+from utils import flattern_annotations, LoadDataAction, StoreOutputAction
+
+
+def main(
+    input_dataset_database,
+    input_dataset_adduct,
+    ppm,
+    ratiosd,
+    ppmunk,
+    ratiounk,
+    ppmthr,
+    pRTNone,
+    pRTout,
+    output_dataset,
+    ncores,
+):
+    write_func, file_path = output_dataset
+
+    annotations = ipa.MS1annotation(
+        input_dataset_database,
+        input_dataset_adduct,
+        ppm=ppm,
+        ratiosd=ratiosd,
+        ppmunk=ppmunk,
+        ratiounk=ratiounk,
+        ppmthr=ppmthr,
+        pRTNone=pRTNone,
+        pRTout=pRTout,
+        ncores=ncores,
+    )
+    annotations_flat = flattern_annotations(annotations)
+    write_func(annotations_flat, file_path)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        """
+    Annotation of the dataset based on the MS1 information. Prior probabilities
+        are based on mass only, while post probabilities are based on mass, RT,
+        previous knowledge and isotope patterns.
+    """
+    )
+    parser.add_argument(
+        "--input_dataset_database",
+        nargs=2,
+        action=LoadDataAction,
+        required=True,
+        help="A dataset containing the MS1 data. Ideally obtained from map_isotope_patterns",
+    )
+    parser.add_argument(
+        "--input_dataset_adducts",
+        nargs=2,
+        action=LoadDataAction,
+        required=True,
+        help="A dataset containing information on all possible adducts.",
+    )
+    parser.add_argument(
+        "--ppm",
+        type=float,
+        required=True,
+        default=100,
+        help="accuracy of the MS instrument used.",
+    )
+    parser.add_argument(
+        "--ratiosd",
+        type=float,
+        default=0.9,
+        help="acceptable ratio between predicted intensity and observed intensity of isotopes.",
+    )
+    parser.add_argument(
+        "--ppmunk",
+        type=float,
+        help="pm associated to the 'unknown' annotation. If not provided equal to ppm.",
+    )
+    parser.add_argument(
+        "--ratiounk",
+        type=float,
+        default=0.5,
+        help="isotope ratio associated to the 'unknown' annotation.",
+    )
+    parser.add_argument(
+        "--ppmthr",
+        type=float,
+        help="maximum ppm possible for the annotations. if not provided equal to 2*ppm.",
+    )
+    parser.add_argument(
+        "--pRTNone",
+        type=float,
+        default=0.8,
+        help="multiplicative factor for the RT if no RTrange present in the database.",
+    )
+    parser.add_argument(
+        "--pRTout",
+        type=float,
+        default=0.4,
+        help="multiplicative factor for the RT if measured RT is outside the RTrange present in the database.",
+    )
+    parser.add_argument(
+        "--output_dataset",
+        nargs=2,
+        action=StoreOutputAction,
+        required=True,
+        help="MS1 annotated data",
+    )
+    parser.add_argument(
+        "--ncores",
+        type=int,
+        default=None,
+        help="number of cores to use for the computation.",
+    )
+    args = parser.parse_args()
+    main(
+        args.input_dataset_database,
+        args.input_dataset_adducts,
+        args.ppm,
+        args.ratiosd,
+        args.ppmunk,
+        args.ratiounk,
+        args.ppmthr,
+        args.pRTNone,
+        args.pRTout,
+        args.output_dataset,
+        args.ncores,
+    )

tools/ipapy2/ipapy2_MS1_annotation.xml

@@ -0,0 +1,73 @@
+<tool id="ipapy2_MS1_annotation" name="IPA MS1 annotation" version="@TOOL_VERSION@+galaxy0" profile="21.09">
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+
+    <requirements>
+        <requirement type="package" version="@TOOL_VERSION@">ipapy2</requirement>
+        <expand macro="extra_requirements"/>
+    </requirements>
+
+    <command detect_errors="exit_code"><![CDATA[
+        #set $computed_ppmthr = float($ppm) * 2
+        python3  '${__tool_directory__}/ipapy2_MS1_annotation.py'
+        --input_dataset_database '${mapped_isotope_patterns}' '${mapped_isotope_patterns.ext}'
+        --input_dataset_adducts '${all_adducts}' '${all_adducts.ext}'
+        --ppm ${ppm}
+        --ratiosd ${ratiosd}
+        #if $ppmunk
+            --ppmunk ${ppmunk}
+        #else
+            --ppmunk ${ppm}
+        #end if
+        --ratiounk ${ratiounk}
+        #if $ppmthr
+            --ppmthr ${ppmthr}
+        #else
+            --ppmthr ${computed_ppmthr}
+        #end if
+        --pRTNone ${pRTNone}
+        --pRTout ${pRTout}
+        --output_dataset '${MS1_annotations}' '${MS1_annotations.ext}'
+        --ncores \${GALAXY_SLOTS:-1}
+    ]]></command>
+
+    <inputs>
+        <param label="Mapped isotope patterns" name="mapped_isotope_patterns" type="data" format="csv,tsv,tabular,parquet" help="A dataset containing the MS1 data. Ideally obtained from map_isotope_patterns" />
+        <param label="all possible adducts" name="all_adducts" type="data" format="csv,tsv,tabular,parquet" help="A dataset containing the information on all the possible adducts given the database. Ideally obtained from compute_all_adducts" />
+        <expand macro="ppm"/>
+        <section name="unknown" title="settings for the identification of unknowns">
+            <expand macro="ms_unknown"/>
+        </section>
+        <section name="optional_settings" title="optional settings">
+            <expand macro="ms_options"/>
+        </section>
+    </inputs>
+
+    <outputs>
+        <data label="${tool.name} on ${on_string}" name="MS1_annotations" format_source="mapped_isotope_patterns"/>
+    </outputs>
+
+    <tests>
+        <test>
+            <param name="mapped_isotope_patterns" value="mapped_isotope_patterns.csv"/>
+            <param name="all_adducts" value="all_adducts.csv"/>
+            <param name="ppm" value="3"/>
+            <output name="MS1_annotations" file="MS1_annotations.csv" lines_diff="20"/>
+        </test>
+    </tests>
+
+    <help><![CDATA[
+    ::
+        Annotation of the dataset based on the MS1 information. Prior probabilities
+        are based on mass only, while post probabilities are based on mass, RT,
+        previous knowledge and isotope patterns.
+
+        https://github.com/francescodc87/ipaPy2#usage
+
+        https://academic.oup.com/bioinformatics/article/39/7/btad455/7230779
+
+    ]]></help>
+
+    <expand macro="citations"/>
+</tool>