CoreMS 3.1.0__tar.gz → 3.2.0__tar.gz

{CoreMS-3.1.0 → CoreMS-3.2.0}/CoreMS.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: CoreMS
-Version: 3.1.0
+Version: 3.2.0
 Summary: Mass Spectrometry Framework for Small Molecules Analysis
 Home-page: https://github.com/EMSL-Computing/CoreMS
 Author: Corilo, Yuri
@@ -65,7 +65,7 @@ CoreMS aims to provide
 
 ## Current Version
 
- `3.1.0`
+ `3.2.0`
 
 ***
 
@@ -351,11 +351,11 @@ UML (unified modeling language) diagrams for Direct Infusion FT-MS and GC-MS cla
 
 If you use CoreMS in your work, please use the following citation:
 
-Version [3.1.0 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v3.1.0), archived on Zenodo:  
+Version [3.2.0 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v3.2.0), archived on Zenodo:  
 
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.14009575.svg)](https://doi.org/10.5281/zenodo.14009575)
 
-Yuri E. Corilo, William R. Kew, Lee Ann McCue, Katherine R . Heal, James C. Carr (2024, October 29). EMSL-Computing/CoreMS: CoreMS 3.1.0 (Version v3.1.0), as developed on Github. Zenodo. http://doi.org/10.5281/zenodo.14009575
+Yuri E. Corilo, William R. Kew, Lee Ann McCue, Katherine R . Heal, James C. Carr (2024, October 29). EMSL-Computing/CoreMS: CoreMS 3.2.0 (Version v3.2.0), as developed on Github. Zenodo. http://doi.org/10.5281/zenodo.14009575
 
 ```
 

{CoreMS-3.1.0 → CoreMS-3.2.0}/CoreMS.egg-info/requires.txt

@@ -10,6 +10,7 @@ netCDF4~=1.6.3
 numpy~=1.24.2
 openpyxl~=3.1.1
 pandas~=1.5.3
+psycopg2~=2.9.10
 pyswarm~=0.6
 pythonnet~=3.0.1
 pymzml~=2.5.2

{CoreMS-3.1.0 → CoreMS-3.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: CoreMS
-Version: 3.1.0
+Version: 3.2.0
 Summary: Mass Spectrometry Framework for Small Molecules Analysis
 Home-page: https://github.com/EMSL-Computing/CoreMS
 Author: Corilo, Yuri
@@ -65,7 +65,7 @@ CoreMS aims to provide
 
 ## Current Version
 
- `3.1.0`
+ `3.2.0`
 
 ***
 
@@ -351,11 +351,11 @@ UML (unified modeling language) diagrams for Direct Infusion FT-MS and GC-MS cla
 
 If you use CoreMS in your work, please use the following citation:
 
-Version [3.1.0 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v3.1.0), archived on Zenodo:  
+Version [3.2.0 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v3.2.0), archived on Zenodo:  
 
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.14009575.svg)](https://doi.org/10.5281/zenodo.14009575)
 
-Yuri E. Corilo, William R. Kew, Lee Ann McCue, Katherine R . Heal, James C. Carr (2024, October 29). EMSL-Computing/CoreMS: CoreMS 3.1.0 (Version v3.1.0), as developed on Github. Zenodo. http://doi.org/10.5281/zenodo.14009575
+Yuri E. Corilo, William R. Kew, Lee Ann McCue, Katherine R . Heal, James C. Carr (2024, October 29). EMSL-Computing/CoreMS: CoreMS 3.2.0 (Version v3.2.0), as developed on Github. Zenodo. http://doi.org/10.5281/zenodo.14009575
 
 ```
 

{CoreMS-3.1.0 → CoreMS-3.2.0}/README.md

@@ -49,7 +49,7 @@ CoreMS aims to provide
 
 ## Current Version
 
- `3.1.0`
+ `3.2.0`
 
 ***
 
@@ -335,11 +335,11 @@ UML (unified modeling language) diagrams for Direct Infusion FT-MS and GC-MS cla
 
 If you use CoreMS in your work, please use the following citation:
 
-Version [3.1.0 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v3.1.0), archived on Zenodo:  
+Version [3.2.0 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v3.2.0), archived on Zenodo:  
 
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.14009575.svg)](https://doi.org/10.5281/zenodo.14009575)
 
-Yuri E. Corilo, William R. Kew, Lee Ann McCue, Katherine R . Heal, James C. Carr (2024, October 29). EMSL-Computing/CoreMS: CoreMS 3.1.0 (Version v3.1.0), as developed on Github. Zenodo. http://doi.org/10.5281/zenodo.14009575
+Yuri E. Corilo, William R. Kew, Lee Ann McCue, Katherine R . Heal, James C. Carr (2024, October 29). EMSL-Computing/CoreMS: CoreMS 3.2.0 (Version v3.2.0), as developed on Github. Zenodo. http://doi.org/10.5281/zenodo.14009575
 
 ```
 

{CoreMS-3.1.0 → CoreMS-3.2.0}/corems/__init__.py

@@ -1,5 +1,5 @@
 __author__ = "Yuri E. Corilo"
-__version__ = "3.1.0"
+__version__ = "3.2.0"
 import time
 import os
 import sys
@@ -21,19 +21,22 @@ else:
 
 
 
-def timeit(method):
-    def timed(*args, **kw):
-        ts = time.time()
-        result = method(*args, **kw)
-        te = time.time()
-        if "log_time" in kw:
-            name = kw.get("log_name", method.__name__.upper())
-            kw["log_time"][name] = int((te - ts) * 1000)
-        else:
-            print("%r  %2.2f ms" % (method.__name__, (te - ts) * 1000))
-        return result
-
-    return timed
+def timeit(print_time=True):
+    def decorator(method):
+        def timed(*args, **kw):
+            # Extract print_time from kwargs if provided
+            local_print_time = kw.pop('print_time', print_time)
+            ts = time.time()
+            result = method(*args, **kw)
+            te = time.time()
+            if "log_time" in kw:
+                name = kw.get("log_name", method.__name__.upper())
+                kw["log_time"][name] = int((te - ts) * 1000)
+            elif local_print_time:
+                print("%r  %2.2f ms" % (method.__name__, (te - ts) * 1000))
+            return result
+        return timed
+    return decorator
 
 
 class SuppressPrints:

{CoreMS-3.1.0 → CoreMS-3.2.0}/corems/encapsulation/factory/parameters.py

@@ -13,6 +13,12 @@ from corems.encapsulation.factory.processingSetting import (
 )
 from corems.encapsulation.factory.processingSetting import DataInputSetting
 
+def hush_output():
+    """Toggle all the verbose_processing flags to False on the MSParameters, GCMSParameters and LCMSParameters classes"""
+    MSParameters.molecular_search.verbose_processing = False
+    MSParameters.mass_spectrum.verbose_processing = False
+    GCMSParameters.gc_ms.verbose_processing = False
+    LCMSParameters.lc_ms.verbose_processing = False
 
 def reset_ms_parameters():
     """Reset the MSParameter class to the default values"""

{CoreMS-3.1.0 → CoreMS-3.2.0}/corems/encapsulation/factory/processingSetting.py

@@ -816,7 +816,10 @@ class MolecularFormulaSearchSettings:
         m/z error average. Default is 0.0.
     used_atom_valences : dict, optional
         Dictionary of atoms and valences. Default is {'C': 4, '13C': 4, 'H': 1, 'O': 2, '18O': 2, 'N': 3, 'S': 2, '34S': 2, 'P': 3, 'Cl': 1, '37Cl': 1, 'Br': 1, 'Na': 1, 'F': 1, 'K': 0}.
+    verbose_processing: bool, optional
+        If True, print verbose processing information. Default is True.
     """
+    verbose_processing: bool = True    
 
     use_isotopologue_filter: bool = False
 

{CoreMS-3.1.0 → CoreMS-3.2.0}/corems/mass_spectra/factory/GC_Class.py

@@ -201,6 +201,18 @@ class GCMSBase(GC_Calculations, MassDeconvolution):
 
         self.scans_number = sorted(self._ms.keys())
 
+    @property
+    def parameters(self):
+        """GCMS Parameters"""
+        return self._parameters
+
+    @parameters.setter
+    def parameters(self, gcms_parameters_instance):
+        self._parameters = gcms_parameters_instance
+
+    # Note: maintaining `parameter` for backwards compatibility,
+    # but proper usage would reference `parameters` to conform
+    # to other classes.
     @property
     def parameter(self):
         """GCMS Parameters"""
@@ -213,20 +225,20 @@ class GCMSBase(GC_Calculations, MassDeconvolution):
     @property
     def molecular_search_settings(self):
         """Molecular Search Settings"""
-        return self.parameter.molecular_search
+        return self.parameters.molecular_search
 
     @molecular_search_settings.setter
     def molecular_search_settings(self, settings_class_instance):
-        self.parameter.molecular_search = settings_class_instance
+        self.parameters.molecular_search = settings_class_instance
 
     @property
     def chromatogram_settings(self):
         """Chromatogram Settings"""
-        return self.parameter.gc_ms
+        return self.parameters.gc_ms
 
     @chromatogram_settings.setter
     def chromatogram_settings(self, settings_class_instance):
-        self.parameter.gc_ms = settings_class_instance
+        self.parameters.gc_ms = settings_class_instance
 
     @property
     def scans_number(self):

{CoreMS-3.1.0 → CoreMS-3.2.0}/corems/mass_spectrum/calc/Calibration.py

@@ -65,7 +65,7 @@ class MzDomainCalibration:
 
         # define reference mass list - bruker .ref format
         self.ref_mass_list_path = ref_masslist
-        if self.mass_spectrum.percentile_assigned()[0] != 0:
+        if self.mass_spectrum.percentile_assigned(mute_output=True)[0] != 0:
             warnings.warn(
                 "Warning: calibrating spectra which have already been assigned may yield erroneous results"
             )
@@ -77,10 +77,6 @@ class MzDomainCalibration:
                 "MS Obj loaded - " + str(len(mass_spectrum.mspeaks)) + " peaks found."
             )
 
-            print(
-                "MS Obj loaded - " + str(len(mass_spectrum.mspeaks)) + " peaks found."
-            )
-
     def load_ref_mass_list(self):
         """Load reference mass list (Bruker format)
 
@@ -228,7 +224,7 @@ class MzDomainCalibration:
             cal_peaks_mz = list(tmpdf.values)
             cal_refs_mz = list(tmpdf.index)
         elif calibration_ref_match_method == "merged":
-            warnings.warn("Using experimental new reference mass list merging")
+            #warnings.warn("Using experimental new reference mass list merging")
             # This is a new approach (August 2024) which uses Pandas 'merged_asof' to find the peaks closest in m/z between
             # reference and measured masses. This is a quicker way to match, and seems to get more matches.
             # It may not work as well when the data are far from correc initial mass

{CoreMS-3.1.0 → CoreMS-3.2.0}/corems/mass_spectrum/calc/MassErrorPrediction.py

@@ -90,12 +90,12 @@ class MassErrorPrediction(Thread):
 
     def calc_error_dist(self):
         """Calculate the error distribution."""
+        verbose = self.mass_spectrum_obj.parameters.mass_spectrum.verbose_processing
         results_list = []
 
         indexes_without_results = list(range(len(self.mass_spectrum_obj)))
         # loop trough mass spectrum
-
-        for peak_obj_idx, peak_obj in enumerate(tqdm(self.mass_spectrum_obj)):
+        for peak_obj_idx, peak_obj in enumerate(tqdm(self.mass_spectrum_obj), disable=not verbose):
             # access ms peaks triplets ( peak_obj_idx -1, peak_obj_idx, and peak_obj_idx + 1)
             # check lower and upper boundaries to not excesses mass spectrum range
 

{CoreMS-3.1.0 → CoreMS-3.2.0}/corems/mass_spectrum/calc/MassSpectrumCalc.py

@@ -38,13 +38,16 @@ class MassSpecCalc(PeakPicking, NoiseThresholdCalc):
         Calculate the weight average molecular weight
     """
 
-    def percentile_assigned(self, report_error: bool = False):
+    def percentile_assigned(self, report_error: bool = False, mute_output: bool = False):
         """Percentage of peaks which are assigned
 
         Parameters
         -----------
         report_error: bool, optional
             Report the error of the assigned peaks. Default is False.
+        mute_output: bool, optional
+            Override the verbose setting. Default is False.
+            If True, the function will silence results
         """
         verbose = self.parameters.mass_spectrum.verbose_processing
         assign_abun = 0
@@ -68,7 +71,7 @@ class MassSpecCalc(PeakPicking, NoiseThresholdCalc):
         total_relative_abundance = (assign_abun / (not_assign_abun + assign_abun)) * 100
         if report_error:
             rms_error = sqrt(mean(array(error) ** 2))
-            if verbose:
+            if verbose and not mute_output:
                 print(
                     "%i assigned peaks and %i unassigned peaks, total  = %.2f %%, relative abundance = %.2f %%, RMS error (best candidate) (ppm) = %.3f"
                     % (i, j, total_percent, total_relative_abundance, rms_error)
@@ -76,7 +79,7 @@ class MassSpecCalc(PeakPicking, NoiseThresholdCalc):
             return i, j, total_percent, total_relative_abundance, rms_error
 
         else:
-            if verbose:
+            if verbose and not mute_output:
                 print(
                     "%i assigned peaks and %i unassigned peaks , total  = %.2f %%, relative abundance = %.2f %%"
                     % (

{CoreMS-3.1.0 → CoreMS-3.2.0}/corems/mass_spectrum/input/massList.py

@@ -106,6 +106,7 @@ class ReadCoremsMasslist(MassListBaseClass):
         mass_spec_mz_exp_list = mass_spec_obj.mz_exp
 
         for df_index, mz_exp in enumerate(mz_exp_df):
+            bad_mf = False
             counts = 0
 
             ms_peak_index = list(mass_spec_mz_exp_list).index(float(mz_exp))
@@ -175,7 +176,7 @@ class ReadCoremsMasslist(MassListBaseClass):
                     # Next, generate isotopologues from the parent
                     isos = list(
                         mono_mfobj.isotopologues(
-                            min_abundance=mass_spec_obj[df_index].abundance * 0.001,
+                            min_abundance=mass_spec_obj.abundance.min()*0.01,
                             current_mono_abundance=mass_spec_obj[mono_index].abundance,
                             dynamic_range=mass_spec_obj.dynamic_range,
                         )
@@ -200,28 +201,32 @@ class ReadCoremsMasslist(MassListBaseClass):
                                     matched_isos.append(iso)
 
                     if len(matched_isos) == 0:
-                        raise ValueError("No isotopologue matched the formula_dict")
-                    mfobj = matched_isos[0]
-
-                    # Add the mono isotopic index, confidence score and isotopologue similarity
-                    mfobj.mspeak_index_mono_isotopic = int(
-                        dataframe.iloc[df_index]["Mono Isotopic Index"]
-                    )
-
-                # Add the confidence score and isotopologue similarity and average MZ error score
-                if "m/z Error Score" in dataframe:
-                    mfobj._mass_error_average_score = float(
-                        dataframe.iloc[df_index]["m/z Error Score"]
-                    )
-                if "Confidence Score" in dataframe:
-                    mfobj._confidence_score = float(
-                        dataframe.iloc[df_index]["Confidence Score"]
-                    )
-                if "Isotopologue Similarity" in dataframe:
-                    mfobj._isotopologue_similarity = float(
-                        dataframe.iloc[df_index]["Isotopologue Similarity"]
-                    )
-                mass_spec_obj[ms_peak_index].add_molecular_formula(mfobj)
+                        #FIXME: This should not occur see https://code.emsl.pnl.gov/mass-spectrometry/corems/-/issues/190
+                        warnings.warn(f"No isotopologue matched the formula_dict: {formula_dict}")
+                        bad_mf = True
+                    else:
+                        bad_mf = False                   
+                        mfobj = matched_isos[0]
+
+                        # Add the mono isotopic index, confidence score and isotopologue similarity
+                        mfobj.mspeak_index_mono_isotopic = int(
+                            dataframe.iloc[df_index]["Mono Isotopic Index"]
+                        )
+                if not bad_mf:
+                    # Add the confidence score and isotopologue similarity and average MZ error score
+                    if "m/z Error Score" in dataframe:
+                        mfobj._mass_error_average_score = float(
+                            dataframe.iloc[df_index]["m/z Error Score"]
+                        )
+                    if "Confidence Score" in dataframe:
+                        mfobj._confidence_score = float(
+                            dataframe.iloc[df_index]["Confidence Score"]
+                        )
+                    if "Isotopologue Similarity" in dataframe:
+                        mfobj._isotopologue_similarity = float(
+                            dataframe.iloc[df_index]["Isotopologue Similarity"]
+                        )
+                    mass_spec_obj[ms_peak_index].add_molecular_formula(mfobj)
 
 
 class ReadMassList(MassListBaseClass):

{CoreMS-3.1.0 → CoreMS-3.2.0}/corems/molecular_id/factory/MolecularLookupTable.py

@@ -364,14 +364,17 @@ class MolecularCombinations:
                     self.sql_db.session.execute(insert_query)
                 self.sql_db.session.commit()
 
-    @timeit
-    def runworker(self, molecular_search_settings):
+    @timeit(print_time=True)
+    def runworker(self, molecular_search_settings, **kwargs):
         """Run the molecular formula lookup table worker.
 
         Parameters
         ----------
         molecular_search_settings : object
             An object containing user-defined settings.
+        kwargs : dict
+            A dictionary of keyword arguments.
+            Most notably, the print_time argument which is passed to the timeit decorator.
 
         Returns
         -------
@@ -380,6 +383,7 @@ class MolecularCombinations:
 
 
         """
+        verbose = molecular_search_settings.verbose_processing
 
         classes_list, class_to_create, existing_classes_objs = (
             self.check_database_get_class_list(molecular_search_settings)
@@ -412,7 +416,7 @@ class MolecularCombinations:
             self.even_ch_dbe = [obj.dbe for obj in even_ch_obj]
 
             all_results = list()
-            for class_tuple in tqdm(class_to_create):
+            for class_tuple in tqdm(class_to_create, disable = not verbose):
                 results = self.populate_combinations(class_tuple, settings)
                 all_results.extend(results)
                 if settings.db_jobs == 1:
@@ -438,8 +442,8 @@ class MolecularCombinations:
                 ]
                 p = multiprocessing.Pool(settings.db_jobs)
                 for class_list in tqdm(
-                    p.imap_unordered(insert_database_worker, worker_args)
-                ):
+                        p.imap_unordered(insert_database_worker, worker_args), disable= not verbose
+                        ):
                     pass
                 p.close()
                 p.join()

{CoreMS-3.1.0 → CoreMS-3.2.0}/corems/molecular_id/factory/molecularSQL.py

@@ -473,6 +473,7 @@ class MolForm_SQL:
         if the number of classes and nominal_m/zs are higher than 999 the query will fail
         Solution: use postgres or split query
         """
+        verbose = molecular_search_settings.verbose_processing
 
         def query_normal(class_list, len_adduct):
             """query for normal database
@@ -565,10 +566,7 @@ class MolForm_SQL:
 
                 elif ion_type == Labels.adduct_ion and adduct_atom:
                     return int(formula_obj._adduct_mz(ion_charge, adduct_atom))
-
-            for formula_obj, ch_obj, classe_obj in tqdm.tqdm(
-                formulas, desc="Loading molecular formula database"
-            ):
+            for formula_obj, ch_obj, classe_obj in tqdm.tqdm(formulas, desc="Loading molecular formula database", disable = not verbose):
                 nominal_mz = nominal_mass_by_ion_type(formula_obj)
 
                 if self.type != "normal":

{CoreMS-3.1.0 → CoreMS-3.2.0}/corems/molecular_id/search/compoundSearch.py

@@ -127,7 +127,6 @@ class LowResMassSpectralMatch(Thread):
 
         return spectral_similarity_scores, ri_score, similarity_score
 
-    # @timeit
     def run(self):
         """Runs the low-resolution mass spectral match."""
         # TODO select the best gcms peak
@@ -148,8 +147,8 @@ class LowResMassSpectralMatch(Thread):
         self.gcms_obj.chromatogram_settings.use_deconvolution = (
             original_use_deconvolution
         )
-
-        for gc_peak in tqdm.tqdm(self.gcms_obj):
+        verbose = self.gcms_obj.chromatogram_settings.verbose_processing
+        for gc_peak in tqdm.tqdm(self.gcms_obj, disable = not verbose):
             if not self.calibration:
                 window = self.gcms_obj.molecular_search_settings.ri_search_range
 

{CoreMS-3.1.0 → CoreMS-3.2.0}/corems/molecular_id/search/database_interfaces.py

@@ -646,12 +646,14 @@ class MetabRefLCInterface(MetabRefInterface):
         super().__init__()
 
         # API endpoint for precursor m/z search
+        # inputs = mz, tolerance (in Da), polarity, page_no, per_page
         self.PRECURSOR_MZ_URL = (
-            "https://metabref.emsl.pnnl.gov/api/precursors/m/{}/t/{}/{}"
+            "https://metabref.emsl.pnnl.gov/api/precursors/m/{}/t/{}/{}?page={}&per_page={}"
         )
 
         # API endpoint for returning full list of precursor m/z values in database
-        self.PRECURSOR_MZ_ALL_URL = "https://metabref.emsl.pnnl.gov/api/precursors/{}"
+        # inputs = polarity, page_no, per_page
+        self.PRECURSOR_MZ_ALL_URL = "https://metabref.emsl.pnnl.gov/api/precursors/{}?page={}&per_page={}"
 
         self.__init_format_map__()
 
@@ -674,7 +676,7 @@ class MetabRefLCInterface(MetabRefInterface):
         self.format_map["fe"] = self.format_map["flashentropy"]
         self.format_map["flash-entropy"] = self.format_map["flashentropy"]
 
-    def query_by_precursor(self, mz_list, polarity, mz_tol_ppm, mz_tol_da_api=0.2):
+    def query_by_precursor(self, mz_list, polarity, mz_tol_ppm, mz_tol_da_api=0.2, max_per_page=50):
         """
         Query MetabRef by precursor m/z values.
 
@@ -690,6 +692,8 @@ class MetabRefLCInterface(MetabRefInterface):
         mz_tol_da_api : float, optional
             Maximum tolerance between precursor m/z values for API search, in daltons.
             Used to group similar mzs into a single API query for speed. Default is 0.2.
+        max_per_page : int, optional
+            Maximum records to return from MetabRef API query at a time.  Default is 50.
 
         Returns
         -------
@@ -705,7 +709,7 @@ class MetabRefLCInterface(MetabRefInterface):
         mz_list.sort()
         mz_groups = [[mz_list[0]]]
         for x in mz_list[1:]:
-            if abs(x - mz_groups[-1][-1]) <= mz_tol_da_api:
+            if abs(x - mz_groups[-1][0]) <= mz_tol_da_api:
                 mz_groups[-1].append(x)
             else:
                 mz_groups.append([x])
@@ -722,32 +726,59 @@ class MetabRefLCInterface(MetabRefInterface):
                 tol = (max(mz_group) - min(mz_group)) / 2 + mz_tol_ppm**-6 * max(
                     mz_group
                 )
-            lib = lib + self.get_query(
-                self.PRECURSOR_MZ_URL.format(str(mz), str(tol), polarity)
+            
+            # Get first page of results
+            response = self.get_query(
+                self.PRECURSOR_MZ_URL.format(str(mz), str(tol), polarity, 1, max_per_page)
             )
+            lib = lib + response['results']
+
+            # If there are more pages of results, get them
+            if response['total_pages'] > 1: 
+                for i in np.arange(2, response['total_pages']+1):
+                    lib = lib + self.get_query(
+                        self.PRECURSOR_MZ_URL.format(str(mz), str(tol), polarity, i, max_per_page)
+                        )['results']
 
         return lib
 
-    def request_all_precursors(self, polarity):
+    def request_all_precursors(self, polarity, per_page = 50000):
         """
-        Request all precursor m/z values from MetabRef.
+        Request all precursor m/z values for MS2 spectra from MetabRef.
 
         Parameters
         ----------
         polarity : str
             Ionization polarity, either "positive" or "negative".
+        per_page : int, optional
+            Number of records to fetch per call. Default is 50000
 
         Returns
         -------
         list
-            List of all precursor m/z values.
+            List of all precursor m/z values, sorted.
         """
         # If polarity is anything other than positive or negative, raise error
         if polarity not in ["positive", "negative"]:
             raise ValueError("Polarity must be 'positive' or 'negative'")
 
-        # Query MetabRef for all precursor m/z values
-        return self.get_query(self.PRECURSOR_MZ_ALL_URL.format(polarity))
+        precursors = []    
+
+        # Get first page of results and total number of pages of results
+        response = self.get_query(self.PRECURSOR_MZ_ALL_URL.format(polarity, str(1), str(per_page)))
+        total_pages = response['total_pages']
+        precursors.extend([x['precursor_ion'] for x in response['results']])
+
+        # Go through remaining pages of results
+        for i in np.arange(2, total_pages + 1):
+            response = self.get_query(self.PRECURSOR_MZ_ALL_URL.format(polarity, str(i), str(per_page)))
+            precursors.extend([x['precursor_ion'] for x in response['results']])
+        
+        # Sort precursors from smallest to largest and remove duplicates
+        precursors = list(set(precursors))
+        precursors.sort()
+
+        return precursors
 
     def get_lipid_library(
         self,
@@ -789,14 +820,25 @@ class MetabRefLCInterface(MetabRefInterface):
 
         """
         mz_list.sort()
+        mz_list = np.array(mz_list)
 
         # Get all precursors in the library matching the polarity
         precusors_in_lib = self.request_all_precursors(polarity=polarity)
-        precusors_in_lib.sort()
         precusors_in_lib = np.array(precusors_in_lib)
 
         # Compare the mz_list with the precursors in the library, keep any mzs that are within mz_tol of any precursor in the library
-        mz_list = np.array(mz_list)
+        lib_mz_df = pd.DataFrame(precusors_in_lib, columns=["lib_mz"])
+        lib_mz_df["closest_obs_mz"] = mz_list[
+            find_closest(mz_list, lib_mz_df.lib_mz.values)
+        ]
+        lib_mz_df["mz_diff_ppm"] = np.abs(
+            (lib_mz_df["lib_mz"] - lib_mz_df["closest_obs_mz"])
+            / lib_mz_df["lib_mz"]
+            * 1e6
+        )
+        lib_mz_sub = lib_mz_df[lib_mz_df["mz_diff_ppm"] <= mz_tol_ppm]
+
+        # Do the same in the opposite direction
         mz_df = pd.DataFrame(mz_list, columns=["mass_feature_mz"])
         mz_df["closest_lib_pre_mz"] = precusors_in_lib[
             find_closest(precusors_in_lib, mz_df.mass_feature_mz.values)
@@ -808,9 +850,15 @@ class MetabRefLCInterface(MetabRefInterface):
         )
         mz_df_sub = mz_df[mz_df["mz_diff_ppm"] <= mz_tol_ppm]
 
+        # Evaluate which is fewer mzs - lib_mz_sub or mz_df_sub and use that as the input for next step
+        if len(lib_mz_sub) < len(mz_df_sub):
+            mzs_to_query = lib_mz_sub.lib_mz.values
+        else:
+            mzs_to_query = mz_df_sub.mass_feature_mz.values
+
         # Query the library for the precursors in the mz_list that are in the library to retrieve the spectra and metadata
         lib = self.query_by_precursor(
-            mz_list=mz_df_sub.mass_feature_mz.values,
+            mz_list=mzs_to_query,
             polarity=polarity,
             mz_tol_ppm=mz_tol_ppm,
             mz_tol_da_api=mz_tol_da_api,
@@ -830,6 +878,12 @@ class MetabRefLCInterface(MetabRefInterface):
             {k: v for k, v in x.items() if k not in ["Molecular Data", "Lipid Tree"]}
             for x in lib
         ]
+        # Unpack the 'Lipid Fragments' key and the 'MSO Data" key from each entry
+        for x in lib:
+            if "Lipid Fragments" in x.keys():
+                x.update(x.pop("Lipid Fragments"))
+            if "MSO Data" in x.keys():
+                x.update(x.pop("MSO Data"))
 
         # Format the spectral library
         format_func = self._get_format_func(format)

{CoreMS-3.1.0 → CoreMS-3.2.0}/corems/molecular_id/search/lcms_spectral_search.py

@@ -88,7 +88,7 @@ class LCMSSpectralSearch:
                 )
 
             # Get types of fragments in the lib entry
-            lib_frags = lib_entry["fragment_types"].split(", ")
+            lib_frags = lib_entry["fragment_types"]
             # make list of the fragment types that are present in the query spectrum
             lib_in_query_ids = list(
                 set(