def __call__(self, spectrum: SpectrumType,
reference_spectrum: SpectrumType) -> bool:
"""Compare parent masses"""
parentmass = spectrum.get("parent_mass")
parentmass_ref = reference_spectrum.get("parent_mass")
assert parentmass is not None and parentmass_ref is not None, "Missing parent mass."
return abs(parentmass - parentmass_ref) <= self.tolerance
def pair(self, reference: SpectrumType, query: SpectrumType) -> float:
"""Compare precursor m/z between reference and query spectrum.
Parameters
----------
reference
Single reference spectrum.
query
Single query spectrum.
"""
entry_ref = reference.get(self.field)
entry_query = query.get(self.field)
if entry_ref is None or entry_query is None:
return np.asarray(False, dtype=self.score_datatype)
if self.matching_type == "equal_match":
score = (entry_ref == entry_query)
return np.asarray(score, dtype=self.score_datatype)
if isinstance(entry_ref,
(int, float)) and isinstance(entry_query, (int, float)):
score = abs(entry_ref - entry_query) <= self.tolerance
return np.asarray(score, dtype=self.score_datatype)
logger.warning(
"Non-numerical entry not compatible with 'difference' method")
return np.asarray(False, dtype=self.score_datatype)
def pair(self, reference: SpectrumType, query: SpectrumType) -> float:
"""Compare parent masses between reference and query spectrum.
Parameters
----------
reference
Single reference spectrum.
query
Single query spectrum.
"""
parentmass_ref = reference.get("parent_mass")
parentmass_query = query.get("parent_mass")
assert parentmass_ref is not None and parentmass_query is not None, "Missing parent mass."
return abs(parentmass_ref - parentmass_query) <= self.tolerance
def pair(self, reference: SpectrumType, query: SpectrumType) -> float:
"""Compare precursor m/z between reference and query spectrum.
Parameters
----------
reference
Single reference spectrum.
query
Single query spectrum.
"""
precursormz_ref = reference.get("precursor_mz")
precursormz_query = query.get("precursor_mz")
assert precursormz_ref is not None and precursormz_query is not None, "Missing precursor m/z."
if self.type == "Dalton":
return abs(precursormz_ref - precursormz_query) <= self.tolerance
mean_mz = (precursormz_ref + precursormz_query) / 2
score = abs(precursormz_ref -
precursormz_query) / mean_mz <= self.tolerance
return numpy.asarray(score, dtype=self.score_datatype)
def pair(self, reference: SpectrumType, query: SpectrumType) -> float:
"""Calculate fingerprint based similarity score between two spectra.
Parameters
----------
reference
Single reference spectrum.
query
Single query spectrum.
"""
fingerprint_ref = reference.get("fingerprint")
fingerprint_query = query.get("fingerprint")
if self.similarity_measure == "jaccard":
return jaccard_index(fingerprint_ref, fingerprint_query)
if self.similarity_measure == "dice":
return dice_similarity(fingerprint_ref, fingerprint_query)
if self.similarity_measure == "cosine":
return cosine_similarity(fingerprint_ref, fingerprint_query)
raise NotImplementedError
def get_tanimoto_for_spectrum_ids(
self, query_spectrum: SpectrumType,
spectra_ids_list: List[str]) -> pd.DataFrame:
"""Returns a dataframe with tanimoto scores
Spectra in spectra_ids_list without inchikey are removed.
Args:
------
query_spectrum:
Single Spectrum, the tanimoto scores are calculated between this
spectrum and the spectra in match_spectrum_ids.
match_spectrum_ids:
list of spectrum_ids, which are preselected matches of the
query_spectrum
"""
query_inchikey14 = query_spectrum.get("inchikey")[:14]
assert len(query_inchikey14) == 14, \
f"Expected inchikey of length 14, " \
f"got inchikey = {query_inchikey14}"
# Get inchikeys belonging to spectra ids
metadata_dict = get_metadata_from_sqlite(
self.sqlite_file_name, spectra_ids_list,
self.settings["spectrum_id_column_name"])
unfiltered_inchikeys = [
metadata_dict[spectrum_id]["inchikey"]
for spectrum_id in spectra_ids_list
]
inchikey14s_dict = {}
for i, inchikey in enumerate(unfiltered_inchikeys):
# Only get the first 14 characters of the inchikeys
inchikey14 = inchikey[:14]
spectrum_id = spectra_ids_list[i]
# Don't save spectra that do not have an inchikey. If a spectra has
# no inchikey it is stored as "", so it will not be stored.
if len(inchikey14) == 14:
inchikey14s_dict[spectrum_id] = inchikey14
tanimoto_scores_spectra_ids = pd.DataFrame(
columns=["Tanimoto_score"], index=list(inchikey14s_dict.keys()))
for spectrum_id, inchikey14 in inchikey14s_dict.items():
tanimoto_score = self.tanimoto_scores.loc[inchikey14,
query_inchikey14]
tanimoto_scores_spectra_ids.at[spectrum_id, "Tanimoto_score"] = \
tanimoto_score
return tanimoto_scores_spectra_ids