Merge pull request RECETOX#428 from zargham-ahmad/issue422

Added tool: matchms_metadata_merge

tools/matchms/matchms_metadata_merge.xml

@@ -0,0 +1,92 @@
+<tool id="matchms_metadata_merge" name="matchms metadata merge" version="@TOOL_VERSION@+galaxy0" profile="21.09">
+    <description>Merge metadata csv into MSP by a specified column</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))
+
+metadata_table = pandas.read_csv('${metadata_table_file}', dtype=object)
+metadata_table.columns = map(str.lower, metadata_table.columns)
+
+metadata_table.drop_duplicates(subset='${user_specified_column}'.lower(), inplace=True)
+
+spectra_metadata= pandas.DataFrame.from_dict([x.metadata for x in spectra])
+spectra_metadata.dropna(axis=1, inplace=True)
+
+merged = metadata_table.merge(spectra_metadata, on='${user_specified_column}'.lower(), how='right')
+
+spectra_arr = np.asarray(spectra, dtype=object)
+
+def update_metadata(spectrum: matchms.Spectrum, row):
+    metadata = spectrum.metadata
+    metadata.update(row)
+    spectrum.metadata = metadata
+    return spectrum
+
+vec_update_metadata = np.vectorize(update_metadata)
+merged_array = vec_update_metadata(spectra_arr, merged.to_dict(orient='records'))
+
+matchms.exporting.save_as_msp(merged_array.tolist(), '${output}')
+</configfile>
+</configfiles>
+
+    <inputs>
+        <param label="Spectra file" name="spectral_library" type="data" format="msp"
+            help="Mass spectral library file." />
+        <param label="Metadata csv file" name="metadata_table_file" type="data" format="csv"
+            help="csv file containing the metadata." />
+
+        <param label="specify column/metadata key" name="user_specified_column" type="text" value="compound_name" help="Name of the user specified column to merge the data on." />
+    </inputs>
+
+    <outputs>
+        <data label="${tool.name} on ${on_string}" name="output" format="msp">
+        </data>
+    </outputs>
+
+    <tests>
+        <test>
+            <param name="spectral_library" value="metadata_merge/input.msp" ftype="msp"/>
+            <param name="metadata_table_file" value="metadata_merge/metadata.csv" ftype="csv"/>
+            <param name="user_specified_column" value="name"/>
+            <output name="output" file="metadata_merge/output.msp" ftype="msp"/>
+        </test>
+    </tests>
+
+    <help>
+        **Description**
+            The tool takes an msp file and a metadata csv file and merges the metadata in the csv 
+            file with the metadata in the MSP file on a user specified column.
+    </help>
+
+    <citations>
+        <citation type="doi">https://doi.org/10.5281/zenodo.8083373</citation>
+    </citations>
+</tool>

tools/matchms/test-data/metadata_merge/input.msp

@@ -0,0 +1,35 @@
+INCHI: InChI=1S/C10H15N5O10P2/c11-8-5-9(13-2-12-8)15(3-14-5)10-7(17)6(16)4(24-10)1-23-27(21,22)25-26(18,19)20/h2-4,6-7,10,16-17H,1H2,(H,21,22)(H2,11,12,13)(H2,18,19,20)
+INSTRUMENTTYPE: LC-ESI-QQ
+COLLISIONENERGY: 40
+FORMULA: C10H15N5O10P2
+NAME: ADP
+PRECURSORMZ: 428.31
+IONMODE: positive
+NUM PEAKS: 2
+135.0       83.0
+136.0       999.0
+
+INCHIKEY: BEJNERDRQOWKJM-UHFFFAOYSA-N
+INCHI: InChI=1S/C6H6O4/c7-2-4-1-5(8)6(9)3-10-4/h1,3,7,9H,2H2
+INSTRUMENTTYPE: LC-ESI-ITFT
+COLLISIONENERGY: 60 % (nominal)
+FORMULA: C6H6O4
+NAME: Kojic acid
+PRECURSORTYPE: [M-H]-
+PRECURSORMZ: 141.0193
+IONMODE: negative
+NUM PEAKS: 1
+141.0194    999.0
+
+INCHI: InChI=1S/C18H22N2/c1-19-12-14-20(15-13-19)18(16-8-4-2-5-9-16)17-10-6-3-7-11-17/h2-11,18H,12-15H2,1H3
+INSTRUMENTTYPE: LC-ESI-ITFT
+COLLISIONENERGY: 85% (nominal)
+FORMULA: C18H22N2
+NAME: Cyclizine
+PRECURSORTYPE: [M+H]+
+PRECURSORMZ: 267.1856
+IONMODE: positive
+NUM PEAKS: 3
+99.0917     6.0
+165.0698    2.0
+167.0856    999.0

tools/matchms/test-data/metadata_merge/metadata.csv

@@ -0,0 +1,4 @@
+Name,inchikey,SMILES
+ADP,XTWYTFMLZFPYCI-UHFFFAOYSA-N,C1=NC2=C(C(=N1)N)N=CN2C3C(C(C(O3)COP(=O)(O)OP(=O)(O)O)O)O
+Kojic acid,BEJNERDRQOWKJM-UHFFFAOYSA-N,C1=C(OC=C(C1=O)O)CO
+Cyclizine,,CN1CCN(CC1)C(C2=CC=CC=C2)C3=CC=CC=C3

tools/matchms/test-data/metadata_merge/output.msp

@@ -0,0 +1,41 @@
+INCHI: InChI=1S/C10H15N5O10P2/c11-8-5-9(13-2-12-8)15(3-14-5)10-7(17)6(16)4(24-10)1-23-27(21,22)25-26(18,19)20/h2-4,6-7,10,16-17H,1H2,(H,21,22)(H2,11,12,13)(H2,18,19,20)
+INSTRUMENTTYPE: LC-ESI-QQ
+COLLISIONENERGY: 40
+FORMULA: C10H15N5O10P2
+NAME: ADP
+PRECURSORMZ: 428.31
+IONMODE: positive
+INCHIKEY: XTWYTFMLZFPYCI-UHFFFAOYSA-N
+SMILES: C1=NC2=C(C(=N1)N)N=CN2C3C(C(C(O3)COP(=O)(O)OP(=O)(O)O)O)O
+NUM PEAKS: 2
+135.0       83.0
+136.0       999.0
+
+INCHIKEY: BEJNERDRQOWKJM-UHFFFAOYSA-N
+INCHI: InChI=1S/C6H6O4/c7-2-4-1-5(8)6(9)3-10-4/h1,3,7,9H,2H2
+INSTRUMENTTYPE: LC-ESI-ITFT
+COLLISIONENERGY: 60 % (nominal)
+FORMULA: C6H6O4
+NAME: Kojic acid
+PRECURSORTYPE: [M-H]-
+PRECURSORMZ: 141.0193
+IONMODE: negative
+SMILES: C1=C(OC=C(C1=O)O)CO
+NUM PEAKS: 1
+141.0194    999.0
+
+INCHI: InChI=1S/C18H22N2/c1-19-12-14-20(15-13-19)18(16-8-4-2-5-9-16)17-10-6-3-7-11-17/h2-11,18H,12-15H2,1H3
+INSTRUMENTTYPE: LC-ESI-ITFT
+COLLISIONENERGY: 85% (nominal)
+FORMULA: C18H22N2
+NAME: Cyclizine
+PRECURSORTYPE: [M+H]+
+PRECURSORMZ: 267.1856
+IONMODE: positive
+INCHIKEY: nan
+SMILES: CN1CCN(CC1)C(C2=CC=CC=C2)C3=CC=CC=C3
+NUM PEAKS: 3
+99.0917     6.0
+165.0698    2.0
+167.0856    999.0
+