Precursor m/z value fix

src/nplinker/metabolomics/gnps/gnps_spectrum_loader.py

@@ -85,36 +85,17 @@ def _load(self) -> None:
 
             # Load the spectrum
             spectrum_id: str = spec["params"]["scans"]
-            # calculate precursor m/z from precursor mass and charge
-            precursor_mass = spec["params"]["pepmass"][0]
-            precursor_charge = self._get_precursor_charge(spec["params"]["charge"])
-            precursor_mz: float = precursor_mass / abs(precursor_charge)
+            precursor_mz: float = spec["params"]["pepmass"][0]
+            precursor_charge: int = spec["params"]["charge"][0]
             rt = spec["params"].get("rtinseconds", 0)
 
             spectrum = Spectrum(
                 id=spectrum_id,
                 mz=list(spec["m/z array"]),
                 intensity=list(spec["intensity array"]),
                 precursor_mz=precursor_mz,
+                precursor_charge=precursor_charge,
                 rt=rt,
                 metadata=spec["params"],
             )
             self._spectra.append(spectrum)
-
-    def _get_precursor_charge(self, charges: list[int]) -> int:
-        """Get the precursor charge from the charge list.
-
-        Args:
-            charges: list of charge values.
-
-        Returns:
-            the precursor charge.
-        """
-        charge = charges[0]
-        if charge == 0:
-            logger.warning(
-                f"Invalid precursor charge value 0. "
-                f"Assuming charge is 1 for spectrum '{self._file}'."
-            )
-            charge = 1
-        return charge

src/nplinker/metabolomics/spectrum.py

@@ -17,10 +17,10 @@ class Spectrum:
         id: the spectrum ID.
         mz: the list of m/z values.
         intensity: the list of intensity values.
-        precursor_mz: the m/z value of the precursor.
+        precursor_mz: the m/z value of the precursor ion.
+        precursor_charge: the charge of the precursor ion.
         rt: the retention time in seconds.
-        metadata: the metadata of the spectrum, i.e. the header information in the MGF
-            file.
+        metadata: the metadata of the spectrum, i.e. the header information in the MGF file.
         gnps_annotations: the GNPS annotations of the spectrum.
         gnps_id: the GNPS ID of the spectrum.
         strains: the strains that this spectrum belongs to.
@@ -34,6 +34,7 @@ def __init__(
         mz: list[float],
         intensity: list[float],
         precursor_mz: float,
+        precursor_charge: int,
         rt: float = 0,
         metadata: dict | None = None,
     ) -> None:
@@ -44,6 +45,7 @@ def __init__(
             mz: the list of m/z values.
             intensity: the list of intensity values.
             precursor_mz: the precursor m/z.
+            precursor_charge: the charge of the precursor ion.
             rt: the retention time in seconds. Defaults to 0.
             metadata: the metadata of the spectrum, i.e. the header information
                 in the MGF file.
@@ -52,6 +54,7 @@ def __init__(
         self.mz = mz
         self.intensity = intensity
         self.precursor_mz = precursor_mz
+        self.precursor_charge = precursor_charge
         self.rt = rt
         self.metadata = metadata or {}
 
@@ -78,7 +81,15 @@ def __reduce__(self) -> tuple:
         """Reduce function for pickling."""
         return (
             self.__class__,
-            (self.id, self.mz, self.intensity, self.precursor_mz, self.rt, self.metadata),
+            (
+                self.id,
+                self.mz,
+                self.intensity,
+                self.precursor_mz,
+                self.precursor_charge,
+                self.rt,
+                self.metadata,
+            ),
             self.__dict__,
         )
 

tests/unit/metabolomics/test_molecular_family.py

@@ -8,7 +8,7 @@
 @pytest.fixture()
 def spectrum1():
     """Return a Spectrum object."""
-    spec = Spectrum(id="spec001", mz=[1.0], intensity=[1.0], precursor_mz=100.0)
+    spec = Spectrum(id="spec001", mz=[1.0], intensity=[1.0], precursor_mz=100.0, precursor_charge=1)
     spec.strains = StrainCollection()
     spec.strains.add(Strain("strain001"))
     yield spec
@@ -17,7 +17,7 @@ def spectrum1():
 @pytest.fixture()
 def spectrum2():
     """Return a Spectrum object."""
-    spec = Spectrum(id="spec002", mz=[1.0], intensity=[1.0], precursor_mz=100.0)
+    spec = Spectrum(id="spec002", mz=[1.0], intensity=[1.0], precursor_mz=100.0, precursor_charge=1)
     spec.strains = StrainCollection()
     spec.strains.add(Strain("strain002"))
     yield spec

tests/unit/metabolomics/test_spectrum.py

@@ -14,12 +14,13 @@
 )
 def test_init(rt, metadata, expected_metadata):
     """Test the initialization of the Spectrum class."""
-    spec = Spectrum("spec1", [100, 200], [0.1, 0.2], 150, rt, metadata)
+    spec = Spectrum("spec1", [100, 200], [0.1, 0.2], 150, 1, rt, metadata)
 
     assert spec.id == "spec1"
     assert spec.mz == [100, 200]
     assert spec.intensity == [0.1, 0.2]
     assert spec.precursor_mz == 150
+    assert spec.precursor_charge == 1
     assert spec.rt == rt
     assert spec.metadata == expected_metadata
 
@@ -32,36 +33,36 @@ def test_init(rt, metadata, expected_metadata):
 
 def test_str_repr():
     """Test the __str__ and __repr__ methods."""
-    spec = Spectrum("spec1", [100, 200], [0.1, 0.2], 150)
+    spec = Spectrum("spec1", [100, 200], [0.1, 0.2], 150, 1)
     assert str(spec) == "Spectrum(id=spec1, #strains=0)"
     assert repr(spec) == "Spectrum(id=spec1, #strains=0)"
 
 
 def test_eq():
     """Test the __eq__ method."""
-    spec1 = Spectrum("spec1", [100, 200], [0.1, 0.2], 150, 0, {"info": "test"})
-    spec2 = Spectrum("spec1", [100, 200], [0.1, 0.2], 150, 0, {"info": "test"})
-    spec3 = Spectrum("spec2", [100, 200], [0.1, 0.2], 150, 0, {"info": "test"})
+    spec1 = Spectrum("spec1", [100, 200], [0.1, 0.2], 150, 1, 0, {"info": "test"})
+    spec2 = Spectrum("spec1", [100, 200], [0.1, 0.2], 150, 1, 0, {"info": "test"})
+    spec3 = Spectrum("spec2", [100, 200], [0.1, 0.2], 150, 1, 0, {"info": "test"})
 
     assert spec1 == spec2
     assert spec1 != spec3
 
 
 def test_hash():
     """Test the __hash__ method."""
-    spec = Spectrum("spec1", [100, 200], [0.1, 0.2], 150)
+    spec = Spectrum("spec1", [100, 200], [0.1, 0.2], 150, 1)
     assert hash(spec) == hash(("spec1", 150))
 
 
 def test_peaks():
     """Test the peaks attribute."""
-    spec = Spectrum("spec1", [100, 200], [0.1, 0.2], 150)
+    spec = Spectrum("spec1", [100, 200], [0.1, 0.2], 150, 1)
     assert np.array_equal(spec.peaks, np.array([[100, 0.1], [200, 0.2]]))
 
 
 def test_has_strain():
     """Test the has_strain method."""
-    spec = Spectrum("spec1", [100, 200], [0.1, 0.2], 150)
+    spec = Spectrum("spec1", [100, 200], [0.1, 0.2], 150, 1)
     strain1 = Strain("strain1")
     strain2 = Strain("strain2")
 

tests/unit/metabolomics/test_utils.py

@@ -17,9 +17,9 @@ def spectra():
     """Fixture for a list of Spectrum objects."""
     # The order of the spectra is important for the tests.
     return [
-        Spectrum("spec0", [100, 200], [0.1, 0.2], 150),
-        Spectrum("spec1", [100, 200], [0.1, 0.2], 150),
-        Spectrum("spec2", [100, 200], [0.1, 0.2], 150),
+        Spectrum("spec0", [100, 200], [0.1, 0.2], 150, 1),
+        Spectrum("spec1", [100, 200], [0.1, 0.2], 150, 1),
+        Spectrum("spec2", [100, 200], [0.1, 0.2], 150, 1),
     ]
 
 

tests/unit/scoring/conftest.py

@@ -37,11 +37,11 @@ def gcfs(strains_list) -> tuple[GCF, GCF, GCF]:
 
 @fixture(scope="session")
 def spectra(strains_list) -> tuple[Spectrum, Spectrum, Spectrum]:
-    spectrum1 = Spectrum("spectrum1", [1], [1], 10.0)
+    spectrum1 = Spectrum("spectrum1", [1], [1], 10.0, 1)
     spectrum1.strains.add(strains_list[0])
-    spectrum2 = Spectrum("spectrum2", [1], [1], 10.0)
+    spectrum2 = Spectrum("spectrum2", [1], [1], 10.0, 1)
     spectrum2.strains.add(strains_list[1])
-    spectrum3 = Spectrum("spectrum3", [1], [1], 10.0)
+    spectrum3 = Spectrum("spectrum3", [1], [1], 10.0, 1)
     spectrum3.strains.add(strains_list[0])
     spectrum3.strains.add(strains_list[1])
     return spectrum1, spectrum2, spectrum3