CoreMS 2.0.6__tar.gz → 2.0.9__tar.gz

{CoreMS-2.0.6 → CoreMS-2.0.9}/CoreMS.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: CoreMS
-Version: 2.0.6
+Version: 2.0.9
 Summary: Mass Spectrometry Framework for Small Molecules Analysis
 Home-page: https://github.com/EMSL-Computing/CoreMS
 Author: Corilo, Yuri
@@ -14,7 +14,7 @@ Classifier: Development Status :: 4 - Beta
 Description-Content-Type: text/markdown
 License-File: LICENSE
 
-![CoreMS Logo](https://github.com/EMSL-Computing/CoreMS/tree/master/docs/CoreMS.COLOR_small.png?raw=true)  
+![CoreMS Logo](docs/CoreMS.COLOR_small.png?raw=true)  
 
 <div align="left">
 
@@ -66,7 +66,7 @@ CoreMS aims to provide
 
 ## Current Version
 
- `2.0.6`
+ `2.0.9`
 
 ***
 
@@ -339,7 +339,7 @@ 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 [2.0.6 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v2.0.6), archived on Zenodo:  
+Version [2.0.9 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v2.0.9), archived on Zenodo:  
 
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.4641552.svg)](https://doi.org/10.5281/zenodo.4641552)
 

{CoreMS-2.0.6 → CoreMS-2.0.9}/CoreMS.egg-info/SOURCES.txt

@@ -128,6 +128,24 @@ ext_lib/ThermoFisher.CommonCore.MassPrecisionEstimator.dll
 ext_lib/ThermoFisher.CommonCore.RawFileReader.dll
 ext_lib/ThermoFisher.CommonCore.RawFileReader.xml
 ext_lib/__init__.py
+ext_lib/dotnet/OpenMcdf.Extensions.dll
+ext_lib/dotnet/OpenMcdf.dll
+ext_lib/dotnet/OpenMcdf.xml
+ext_lib/dotnet/System.IO.FileSystem.AccessControl.dll
+ext_lib/dotnet/System.IO.FileSystem.AccessControl.xml
+ext_lib/dotnet/System.Security.AccessControl.dll
+ext_lib/dotnet/System.Security.AccessControl.xml
+ext_lib/dotnet/System.Security.Principal.Windows.dll
+ext_lib/dotnet/System.Security.Principal.Windows.xml
+ext_lib/dotnet/ThermoFisher.CommonCore.BackgroundSubtraction.dll
+ext_lib/dotnet/ThermoFisher.CommonCore.BackgroundSubtraction.xml
+ext_lib/dotnet/ThermoFisher.CommonCore.Data.dll
+ext_lib/dotnet/ThermoFisher.CommonCore.Data.xml
+ext_lib/dotnet/ThermoFisher.CommonCore.MassPrecisionEstimator.dll
+ext_lib/dotnet/ThermoFisher.CommonCore.MassPrecisionEstimator.xml
+ext_lib/dotnet/ThermoFisher.CommonCore.RawFileReader.dll
+ext_lib/dotnet/ThermoFisher.CommonCore.RawFileReader.xml
+ext_lib/dotnet/__init__.py
 tests/test.py
 tests/test_LossFinder.py
 tests/test_assembly_identification.py

{CoreMS-2.0.6 → CoreMS-2.0.9}/CoreMS.egg-info/requires.txt

@@ -2,7 +2,7 @@ beautifulsoup4~=4.12.0
 chardet~=5.1.0
 comtypes~=1.1.14
 h5py~=3.8.0
-IsoSpecPy~=2.0.2
+IsoSpecPy~=2.2.2
 lmfit~=1.1.0
 lxml~=4.9.3
 matplotlib~=3.7.0

{CoreMS-2.0.6 → CoreMS-2.0.9}/MANIFEST.in

@@ -1,4 +1,5 @@
 include requirements.txt
 include disclaimer.txt
 include Dockerfile
-include ext_lib/*
+include ext_lib/*
+include ext_lib/dotnet/*

{CoreMS-2.0.6 → CoreMS-2.0.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: CoreMS
-Version: 2.0.6
+Version: 2.0.9
 Summary: Mass Spectrometry Framework for Small Molecules Analysis
 Home-page: https://github.com/EMSL-Computing/CoreMS
 Author: Corilo, Yuri
@@ -14,7 +14,7 @@ Classifier: Development Status :: 4 - Beta
 Description-Content-Type: text/markdown
 License-File: LICENSE
 
-![CoreMS Logo](https://github.com/EMSL-Computing/CoreMS/tree/master/docs/CoreMS.COLOR_small.png?raw=true)  
+![CoreMS Logo](docs/CoreMS.COLOR_small.png?raw=true)  
 
 <div align="left">
 
@@ -66,7 +66,7 @@ CoreMS aims to provide
 
 ## Current Version
 
- `2.0.6`
+ `2.0.9`
 
 ***
 
@@ -339,7 +339,7 @@ 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 [2.0.6 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v2.0.6), archived on Zenodo:  
+Version [2.0.9 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v2.0.9), archived on Zenodo:  
 
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.4641552.svg)](https://doi.org/10.5281/zenodo.4641552)
 

{CoreMS-2.0.6 → CoreMS-2.0.9}/README.md

@@ -1,4 +1,4 @@
-![CoreMS Logo](https://github.com/EMSL-Computing/CoreMS/tree/master/docs/CoreMS.COLOR_small.png?raw=true)  
+![CoreMS Logo](docs/CoreMS.COLOR_small.png?raw=true)  
 
 <div align="left">
 
@@ -50,7 +50,7 @@ CoreMS aims to provide
 
 ## Current Version
 
- `2.0.6`
+ `2.0.9`
 
 ***
 
@@ -323,7 +323,7 @@ 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 [2.0.6 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v2.0.6), archived on Zenodo:  
+Version [2.0.9 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v2.0.9), archived on Zenodo:  
 
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.4641552.svg)](https://doi.org/10.5281/zenodo.4641552)
 

{CoreMS-2.0.6 → CoreMS-2.0.9}/corems/__init__.py

@@ -1,5 +1,5 @@
 __author__ = 'Yuri E. Corilo'
-__version__ = '2.0.6'
+__version__ = '2.0.9'
 __doc__ = '''
 <div align="left">
 

{CoreMS-2.0.6 → CoreMS-2.0.9}/corems/encapsulation/factory/processingSetting.py

@@ -63,16 +63,16 @@ class DataInputSetting:
         self.header_translate = {'m/z': Labels.mz, 
                                  'mOz': Labels.mz,
                                  'Mass': Labels.mz,
-                                 'Resolving Power': 'Resolving Power',
+                                 'Resolving Power': Labels.rp,
                                  'Res.': Labels.rp,
+                                 'resolution': Labels.rp,
                                  'Intensity': Labels.abundance,
                                  'I': Labels.abundance,
                                  'Abundance': Labels.abundance,
+                                 'abs_abu': Labels.abundance,
                                  'Signal/Noise': Labels.s2n,
                                  'S/N': Labels.s2n,
-                                 'abs_abu': Labels.abundance,
-                                 'sn': Labels.s2n,
-                                 'resolution': Labels.rp}
+                                 'sn': Labels.s2n}
 
     def add_mz_label(self, label):
         """Add a label to the header_translate dictionary to be translated to the corems label for mz."""

{CoreMS-2.0.6 → CoreMS-2.0.9}/corems/mass_spectra/factory/LC_Temp.py

@@ -10,7 +10,9 @@ class TIC_Data:
     Time: [floats]
         list of retention times
     TIC: [floats]
-        total ion chromatogram
+        total ion current [chromatogram]
+    BPC: [floats]
+        base peak [chromatogram]
     Apexes: [int]    
         original thermo apex scan number after peak picking 
      '''
@@ -18,6 +20,7 @@ class TIC_Data:
      scans : List[int] = field(default_factory=list)
      time : List[float] = field(default_factory=list)
      tic : List[float] = field(default_factory=list)
+     bpc : List[float] = field(default_factory=list)
      apexes : List[int] = field(default_factory=list)
 
 @dataclass

{CoreMS-2.0.6 → CoreMS-2.0.9}/corems/mass_spectra/input/brukerSolarix.py

@@ -1,7 +1,6 @@
 __author__ = "Yuri E. Corilo"
 __date__ = "Oct 29, 2019"
 
-from future import __annotations__
 from threading import Thread
 from pathlib import Path
 from s3path import S3Path

{CoreMS-2.0.6 → CoreMS-2.0.9}/corems/mass_spectra/input/rawFileReader.py

@@ -503,9 +503,15 @@ class ThermoBaseClass:
             # plt.show()
 
     def get_tic(
-        self, ms_type="MS !d", peak_detection=True, smooth=True, plot=False, ax=None
+        self, ms_type="MS !d", peak_detection=True, smooth=True, plot=False, ax=None,trace_type='TIC',
     ) -> Tuple[TIC_Data, axes.Axes]:
-        """ms_type: str ('MS', MS2')
+        """ms_type: str ('MS !d', 'MS2', None)
+            if you use None you get all scans.
+        peak_detection: bool
+        smooth: bool
+        plot: bool
+        ax: matplotlib axis object
+        trace_type: str ('TIC','BPC')
 
         returns:
             chroma: dict
@@ -520,9 +526,16 @@ class ThermoBaseClass:
                 original thermo apex scan number after peak picking
             }
         """
-
-        settings = ChromatogramTraceSettings(TraceType.TIC)
-        settings.Filter = ms_type
+        if trace_type == 'TIC':
+            settings = ChromatogramTraceSettings(TraceType.TIC)
+        elif trace_type == 'BPC':
+            settings = ChromatogramTraceSettings(TraceType.BasePeak)
+        else:
+            print(f'{trace_type} undefined')
+        if ms_type == "all":
+            settings.Filter = None
+        else:
+            settings.Filter = ms_type
 
         chroma_settings = IChromatogramSettings(settings)
 
@@ -532,7 +545,7 @@ class ThermoBaseClass:
 
         trace = ChromatogramSignal.FromChromatogramData(data)
 
-        data = TIC_Data(time=[], scans=[], tic=[], apexes=[])
+        data = TIC_Data(time=[], scans=[], tic=[], bpc=[], apexes=[])
 
         if trace[0].Length > 0:
             for i in range(trace[0].Length):
@@ -564,7 +577,7 @@ class ThermoBaseClass:
                     ax = plt.gca()
                     # fig, ax = plt.subplots(figsize=(6, 3))
 
-                ax.plot(data.time, data.tic, label=" TIC")
+                ax.plot(data.time, data.tic, label=trace_type)
                 ax.set_xlabel("Time (min)")
                 ax.set_ylabel("a.u.")
                 if peak_detection:
@@ -578,8 +591,13 @@ class ThermoBaseClass:
                         )
 
                 # plt.show()
+                if trace_type == 'BPC':
+                    data.bpc = data.tic
+                    data.tic = []
                 return data, ax
-
+            if trace_type == 'BPC':
+                data.bpc = data.tic
+                data.tic = []
             return data, None
 
         else:

{CoreMS-2.0.6 → CoreMS-2.0.9}/corems/mass_spectrum/calc/Calibration.py

@@ -381,13 +381,15 @@ class MzDomainCalibration:
             if self.mzsegment:
                 # Recombine the mass domains
                 mz_domain = np.concatenate([mz_domain,mz_exp_peaks_unchanged])
-                mz_profile_calc = np.concatenate([mz_profile_calc,mz_exp_profile_unchanged])
-                # Sort them 
                 mz_domain.sort()
-                mz_profile_calc.sort()
+                if not self.mass_spectrum.is_centroid:
+                    mz_profile_calc = np.concatenate([mz_profile_calc,mz_exp_profile_unchanged])
+                    mz_profile_calc.sort()
+                # Sort them 
                 if mz_exp_peaks[0] > mz_exp_peaks[1]: #If originally descending mass order
                     mz_domain = mz_domain[::-1]
-                    mz_profile_calc = mz_profile_calc[::-1]
+                    if not self.mass_spectrum.is_centroid:
+                        mz_profile_calc = mz_profile_calc[::-1]
 
             self.mass_spectrum.mz_cal = mz_domain
             if not self.mass_spectrum.is_centroid:

{CoreMS-2.0.6 → CoreMS-2.0.9}/corems/mass_spectrum/calc/NoiseCalc.py

@@ -79,7 +79,7 @@ class NoiseThresholdCalc:
 
             elif self.settings.noise_threshold_method == 'signal_noise':
 
-                normalized_threshold = (self.max_abundance * self.settings.s2n_threshold )/self.max_signal_to_noise
+                normalized_threshold = (self.max_abundance * self.settings.noise_threshold_min_s2n )/self.max_signal_to_noise
                 y = (normalized_threshold, normalized_threshold)
             
             elif self.settings.noise_threshold_method == "relative_abundance":
@@ -115,7 +115,7 @@ class NoiseThresholdCalc:
 
                     max_sn = self.abundance_profile.max()/self.baseline_noise_std
 
-                    normalized_threshold = (self.abundance_profile.max() * self.settings.s2n_threshold )/max_sn
+                    normalized_threshold = (self.abundance_profile.max() * self.settings.noise_threshold_min_s2n )/max_sn
                     y = (normalized_threshold, normalized_threshold)
 
                 elif self.settings.noise_threshold_method == "relative_abundance":

{CoreMS-2.0.6 → CoreMS-2.0.9}/corems/mass_spectrum/calc/PeakPicking.py

@@ -452,8 +452,11 @@ class PeakPicking:
 
         elif noise_threshold_method == 'signal_noise':
 
-            abundance_threshold = self.settings.s2n_threshold
-            factor = self.baseline_noise_std
+            abundance_threshold = self.settings.noise_threshold_min_s2n
+            if self.is_centroid:
+                factor = 1
+            else:
+                factor = self.baseline_noise_std
 
         elif noise_threshold_method == "relative_abundance":
 

{CoreMS-2.0.6 → CoreMS-2.0.9}/corems/molecular_formula/calc/MolecularFormulaCalc.py

@@ -1,8 +1,8 @@
 __author__ = "Yuri E. Corilo"
 __date__ = "Jun 24, 2019"
 
-from IsoSpecPy import IsoSpecPy
-from numpy import isnan, power, exp, nextafter
+
+from numpy import isnan, power, exp, nextafter, array
 from pandas import DataFrame
 from scipy.stats import pearsonr, spearmanr, kendalltau
 
@@ -11,6 +11,19 @@ from corems.encapsulation.constant import Labels
 from corems.encapsulation.factory.parameters import MSParameters
 from corems.molecular_id.calc.SpectralSimilarity import SpectralSimilarity
 
+# this is to handle both versions of IsoSpecPy, 2.0.2 and 2.2.2
+# TODO in a future release remove support for legacy isospecpy
+from packaging import version
+import IsoSpecPy
+isospec_version = IsoSpecPy.__version__
+if version.parse(isospec_version) > version.parse('2.0.2'): 
+    legacy_isospec = False
+else: legacy_isospec = True
+if legacy_isospec:
+    from IsoSpecPy import IsoSpecPy
+    print(f"IsoSpecPy version {isospec_version} is installed, and support is deprecated. Please update to 2.2.2")
+
+
 class MolecularFormulaCalc:
     """Class of calculations related to molecular formula
 
@@ -645,15 +658,31 @@ class MolecularFormulaCalc:
                 atoms_count.append(formula_dict.get(atom_label))
                 masses_list_tuples.append(masses)
                 props_list_tuples.append(props)
-        
-        iso = IsoSpecPy.IsoSpec(atoms_count,masses_list_tuples,props_list_tuples, cut_off_to_IsoSpeccPy)
-        
-        conf = iso.getConfs()
-        masses = conf[0]
-        probs = exp(conf[1])
-        molecular_formulas = conf[2]
-        #print('conf', conf)
-        #print('probs', conf[1])
+        if legacy_isospec:
+            iso = IsoSpecPy.IsoSpec(atoms_count,masses_list_tuples,props_list_tuples, cut_off_to_IsoSpeccPy)
+            conf = iso.getConfs()
+            masses = conf[0]
+            probs = exp(conf[1])
+            molecular_formulas = conf[2]
+            #print('conf', conf)
+            #print('probs', conf[1])
+        else:
+            # This syntax in IsoSpecPy 2.2.2 yields the same information as the legacy approach
+            iso = IsoSpecPy.IsoTotalProb(atomCounts = atoms_count, isotopeMasses = masses_list_tuples, 
+                           isotopeProbabilities = props_list_tuples, prob_to_cover =cut_off_to_IsoSpeccPy, get_confs=True)
+            masses = list(iso.masses)
+            probs = array(list(iso.probs))
+            confs = list(iso.confs)
+
+            molecular_formulas = []
+            for x in confs:
+                tmplist = []
+                for y in x:
+                    tmplist.extend(list(y))
+                molecular_formulas.append(tmplist)
+
+
+
         
         new_formulas = []
         

{CoreMS-2.0.6 → CoreMS-2.0.9}/corems/molecular_formula/factory/MolecularFormulaFactory.py

@@ -406,9 +406,14 @@ class MolecularFormulaBase(MolecularFormulaCalc):
         -----
         This calculation ignores the hydrogen isotopes.
         """
-        
+        isotopologues = []
         for mf in self._cal_isotopologues(self._d_molecular_formula, min_abundance, current_mono_abundance, dynamic_range ):
-             
+            isotopologues.append(mf)
+        
+        # To account for differences in how the isotopologue outputs are sorted between IsoSpec versions. 
+        sorted_isotopologues = sorted(isotopologues, key=lambda mf: mf[1], reverse=True)
+
+        for mf in sorted_isotopologues:
             yield MolecularFormulaIsotopologue(
                 *mf, 
                 current_mono_abundance, 

{CoreMS-2.0.6 → CoreMS-2.0.9}/corems/ms_peak/calc/MSPeakCalc.py

@@ -27,9 +27,9 @@ class MSPeakCalculation:
         The parent MSParent object associated with the MSPeakCalculation object.
     mz_exp : float
         The experimental m/z value of the peak.
-    start_scan : int
+    peak_left_index : int
         The start scan index of the peak.
-    final_scan : int
+    peak_right_index : int
         The final scan index of the peak.
     resolving_power : float
         The resolving power of the peak.
@@ -136,11 +136,10 @@ class MSPeakCalculation:
         float
             peak area
         """
-        #TODO throughout change final_scan and start_scan when the MSPeakClasses 
-        if self.final_scan > self.start_scan:
+        if self.peak_right_index > self.peak_left_index:
 
-            yy = self._ms_parent.abundance_profile[self.start_scan:self.final_scan]
-            xx = self._ms_parent.mz_exp_profile[self.start_scan:self.final_scan]
+            yy = self._ms_parent.abundance_profile[self.peak_left_index:self.peak_right_index]
+            xx = self._ms_parent.mz_exp_profile[self.peak_left_index:self.peak_right_index]
             # check if the axis is high to low m/z or not. if its MSFromFreq its high mz first, if its from Profile, its low mz first
             if xx[0] > xx[-1]:
                 xx = flip(xx)    
@@ -182,8 +181,8 @@ class MSPeakCalculation:
         mz_extend here extends the x-axis domain so that we have sufficient points either side of the apex to fit.
         Takes about 10ms per peak
         """
-        start_index = self.start_scan - mz_extend  if not self.start_scan == 0 else 0
-        final_index = self.final_scan + mz_extend  if not self.final_scan == len(self._ms_parent.mz_exp_profile) else self.final_scan
+        start_index = self.peak_left_index - mz_extend  if not self.peak_left_index == 0 else 0
+        final_index = self.peak_right_index + mz_extend  if not self.peak_right_index == len(self._ms_parent.mz_exp_profile) else self.peak_right_index
 
         # check if MSPeak contains the resolving power info
         if self.resolving_power:
@@ -385,8 +384,8 @@ class MSPeakCalculation:
             # Thermo data is noise reduced by also noise subtracted, so starts at 0
             # Absorption mode/phased data will have positive and negative components and may not be baseline corrected
 
-        start_index = self.start_scan - mz_extend  if not self.start_scan == 0 else 0
-        final_index = self.final_scan + mz_extend  if not self.final_scan == len(self._ms_parent.mz_exp_profile) else self.final_scan
+        start_index = self.peak_left_index - mz_extend  if not self.peak_left_index == 0 else 0
+        final_index = self.peak_right_index + mz_extend  if not self.peak_right_index == len(self._ms_parent.mz_exp_profile) else self.peak_right_index
 
         # check if MSPeak contains the resolving power info
         if self.resolving_power:
@@ -649,8 +648,8 @@ class MSPeakCalculation:
             x-axis domain for fit
         
         """
-        start_index = self.start_scan - mz_overlay  if not self.start_scan == 0 else 0
-        final_index = self.final_scan + mz_overlay  if not self.final_scan == len(self._ms_parent.mz_exp_profile) else self.final_scan
+        start_index = self.peak_left_index - mz_overlay  if not self.peak_left_index == 0 else 0
+        final_index = self.peak_right_index + mz_overlay  if not self.peak_right_index == len(self._ms_parent.mz_exp_profile) else self.peak_right_index
 
         if oversample_multiplier == 1:
 

{CoreMS-2.0.6 → CoreMS-2.0.9}/corems/ms_peak/factory/MSPeakClasses.py

@@ -79,10 +79,9 @@ class _MSPeak(MSPeakCalculation):
         self.resolving_power = float(resolving_power)
         self.signal_to_noise = float(signal_to_noise)
         # profile indexes
-        #TODO fix these names from 'scan' to be more logical about peak indexes.
-        self.start_scan = int(indexes[0])
-        self.apex_scan = int(indexes[1])
-        self.final_scan = int(indexes[2])
+        self.peak_left_index = int(indexes[0])
+        self.peak_apex_index = int(indexes[1])
+        self.peak_right_index = int(indexes[2])
 
         # mass spec obj index
         self.index = int(index)
@@ -318,15 +317,15 @@ class _MSPeak(MSPeakCalculation):
 
             if ax is None:
                 ax = plt.gca()
-            x = self._ms_parent.mz_exp_profile[self.start_scan : self.final_scan]
-            y = self._ms_parent.abundance_profile[self.start_scan : self.final_scan]
+            x = self._ms_parent.mz_exp_profile[self.peak_left_index : self.peak_right_index]
+            y = self._ms_parent.abundance_profile[self.peak_left_index : self.peak_right_index]
 
             ax.plot(x, y, color=color, label="Data")
             ax.set(xlabel="m/z", ylabel="abundance")
             if derivative and not self._ms_parent.is_centroid:
                 dy = sp.derivate(
                     self._ms_parent.abundance_profile[
-                        self.start_index : self.final_index + 1
+                        self.peak_left_index : self.peak_right_index + 1
                     ]
                 )
                 ax.plot(x, dy, c=deriv_color)