updated matchms filtering tool

RECETOX · Jan 8, 2024 · 06b5348 · 06b5348
1 parent 98223db
commit 06b5348
Show file tree

Hide file tree

Showing 5 changed files with 10 additions and 81 deletions.
diff --git a/tools/matchms/matchms_filtering.xml b/tools/matchms/matchms_filtering.xml
@@ -175,12 +175,12 @@
         <test>
             <param name="spectra" value="filtering/require_filter.msp" ftype="msp"/>
             <param name="require_smiles_is_true" value="TRUE"/>
-            <output name="output" file="filtering/require_smiles_out.msp" ftype="msp"/>
+            <output name="output" file="filtering/require_out.msp" ftype="msp"/>
         </test>
         <test>
             <param name="spectra" value="filtering/require_filter.msp" ftype="msp"/>
             <param name="require_inchi_is_true" value="TRUE"/>
-            <output name="output" file="filtering/require_inchi_out.msp" ftype="msp"/>
+            <output name="output" file="filtering/require_out.msp" ftype="msp"/>
         </test>
         <test>
             <param name="spectra" value="filtering/input.msp" ftype="msp"/>

diff --git a/tools/matchms/matchms_filtering_wrapper.py b/tools/matchms/matchms_filtering_wrapper.py
@@ -7,11 +7,13 @@
 from matchms.filtering import default_filters, normalize_intensities, reduce_to_number_of_peaks, select_by_mz, \
     select_by_relative_intensity
 from matchms.filtering.filter_utils.derive_precursor_mz_and_parent_mass import derive_precursor_mz_from_parent_mass
+from matchms.filtering.filter_utils.smile_inchi_inchikey_conversions import is_valid_inchi, is_valid_smiles
 from matchms.importing import load_from_mgf, load_from_msp
 
 
-def require_key(spectrum, key):
-    if spectrum.get(key):
+def require_key(spectrum, key, function):
+    value = spectrum.get(key)
+    if function(value):
         return spectrum
 
     return None
@@ -95,10 +97,10 @@ def main(argv):
             spectrum.set("precursor_mz", precursor_mz)
 
         if args.require_smiles and spectrum is not None:
-            spectrum = require_key(spectrum, "smiles")
+            spectrum = require_key(spectrum, "smiles", is_valid_smiles)
 
         if args.require_inchi and spectrum is not None:
-            spectrum = require_key(spectrum, "inchi")
+            spectrum = require_key(spectrum, "inchi", is_valid_inchi)
 
         if spectrum is not None:
             filtered_spectra.append(spectrum)

diff --git a/tools/matchms/test-data/filtering/require_filter.msp b/tools/matchms/test-data/filtering/require_filter.msp
@@ -6,7 +6,7 @@ COMPOUND_NAME: ((.eta.5-Cyclopentadienylironbiscarbonyl)(1,2-phenylenedioxysilyl
 PARENT_MASS: 347.930801
 PUBCHEMID: 10970124
 NOMINAL_MASS: 348
-SMILES: Cl[Si]1Oc2ccccc2O1.[C-]#[O+].[C-]#[O+].[CH]1C=CC=C1.[Fe]
+SMILES: nan
 NUM PEAKS: 3
 292.0       999.0
 314.0       118.89
@@ -21,7 +21,7 @@ PARENT_MASS: 186.1044655
 RETENTION_INDEX: 1588.0
 PUBCHEMID: 130762197
 NOMINAL_MASS: 186
-INCHI: InChI=1S/C13H14O/c1-13(10-14)9-12(13)8-7-11-5-3-2-4-6-11/h2-6,12,14H,9-10H2,1H3/t12-,13-/m0/s1
+INCHI: nan
 NUM PEAKS: 20
 51.0        89.92
 63.0        89.92

diff --git a/tools/matchms/test-data/filtering/require_inchi_out.msp b/tools/matchms/test-data/filtering/require_inchi_out.msp
diff --git a/...est-data/filtering/require_smiles_out.msp → ...tchms/test-data/filtering/require_out.msp b/...est-data/filtering/require_smiles_out.msp → ...tchms/test-data/filtering/require_out.msp
@@ -1,17 +1,3 @@
-FORMULA: C13H9ClFeO4Si
-CASNO: 2000570-99-8
-ID: 2011
-COMMENT: SpectrumID: 1519953; Source: C4-1998-38-3; Class: Benzenoids; CASRN not real!
-COMPOUND_NAME: ((.eta.5-Cyclopentadienylironbiscarbonyl)(1,2-phenylenedioxysilyl)chloride complex
-PARENT_MASS: 347.930801
-PUBCHEMID: 10970124
-NOMINAL_MASS: 348
-SMILES: Cl[Si]1Oc2ccccc2O1.[C-]#[O+].[C-]#[O+].[CH]1C=CC=C1.[Fe]
-NUM PEAKS: 3
-292.0       999.0
-314.0       118.89
-348.0       734.24
-
 FORMULA: C34H54O4
 CASNO: 2000774-54-3
 ID: 36905