CoreMS 2.0.3__tar.gz → 2.0.8__tar.gz

{CoreMS-2.0.3 → CoreMS-2.0.8}/CoreMS.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: CoreMS
-Version: 2.0.3
+Version: 2.0.8
 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/blob/v2.0.1/docs/CoreMS.COLOR_small.png?raw=true)  
+![CoreMS Logo](https://github.com/EMSL-Computing/CoreMS/tree/master/docs/CoreMS.COLOR_small.png?raw=true)  
 
 <div align="left">
 
@@ -66,7 +66,7 @@ CoreMS aims to provide
 
 ## Current Version
 
- `2.0.3`
+ `2.0.8`
 
 ***
 
@@ -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 [2.0.3 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v2.0.3), archived on Zenodo:  
+Version [2.0.8 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v2.0.8), archived on Zenodo:  
 
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.4641552.svg)](https://doi.org/10.5281/zenodo.4641552)
 

{CoreMS-2.0.3 → CoreMS-2.0.8}/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-2.0.3 → CoreMS-2.0.8}/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-2.0.3 → CoreMS-2.0.8}/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-2.0.3 → CoreMS-2.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: CoreMS
-Version: 2.0.3
+Version: 2.0.8
 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/blob/v2.0.1/docs/CoreMS.COLOR_small.png?raw=true)  
+![CoreMS Logo](https://github.com/EMSL-Computing/CoreMS/tree/master/docs/CoreMS.COLOR_small.png?raw=true)  
 
 <div align="left">
 
@@ -66,7 +66,7 @@ CoreMS aims to provide
 
 ## Current Version
 
- `2.0.3`
+ `2.0.8`
 
 ***
 
@@ -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 [2.0.3 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v2.0.3), archived on Zenodo:  
+Version [2.0.8 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v2.0.8), archived on Zenodo:  
 
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.4641552.svg)](https://doi.org/10.5281/zenodo.4641552)
 

{CoreMS-2.0.3 → CoreMS-2.0.8}/README.md

@@ -1,4 +1,4 @@
-![CoreMS Logo](https://github.com/EMSL-Computing/CoreMS/blob/v2.0.1/docs/CoreMS.COLOR_small.png?raw=true)  
+![CoreMS Logo](https://github.com/EMSL-Computing/CoreMS/tree/master/docs/CoreMS.COLOR_small.png?raw=true)  
 
 <div align="left">
 
@@ -50,7 +50,7 @@ CoreMS aims to provide
 
 ## Current Version
 
- `2.0.3`
+ `2.0.8`
 
 ***
 
@@ -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 [2.0.3 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v2.0.3), archived on Zenodo:  
+Version [2.0.8 Release on GitHub](https://github.com/EMSL-Computing/CoreMS/releases/tag/v2.0.8), archived on Zenodo:  
 
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.4641552.svg)](https://doi.org/10.5281/zenodo.4641552)
 

{CoreMS-2.0.3 → CoreMS-2.0.8}/corems/__init__.py

@@ -1,5 +1,5 @@
 __author__ = 'Yuri E. Corilo'
-__version__ = '2.0.3'
+__version__ = '2.0.8'
 __doc__ = '''
 <div align="left">
 

{CoreMS-2.0.3 → CoreMS-2.0.8}/corems/encapsulation/constant.py

@@ -36,7 +36,8 @@ class Labels: #pragma: no cover
     ion_type_translate = { 'protonated': 'DE_OR_PROTONATED',
                           'de-protonated': 'DE_OR_PROTONATED',
                           'radical': 'RADICAL',
-                          'adduct': 'ADDUCT'}
+                          'adduct': 'ADDUCT',
+                          'ADDUCT': 'ADDUCT'}
     
 class Atoms: #pragma: no cover
     """ Class for Atoms in CoreMS

{CoreMS-2.0.3 → CoreMS-2.0.8}/corems/encapsulation/factory/parameters.py

@@ -100,11 +100,17 @@ def default_parameters(file_location):  # pragma: no cover
 
     parameters["exc_low_freq"] = 0
 
+    parameters["mw_low"] = 0
+        
+    parameters["mw_high"] = 0
+
+    parameters["qpd_enabled"] = 0
+
     parameters["bandwidth"] = 0
 
     parameters['analyzer'] = 'Unknown'
 
-    parameters['aquisition_time'] = None
+    parameters['acquisition_time'] = None
 
     parameters['instrument_label'] = 'Unknown' 
 

{CoreMS-2.0.3 → CoreMS-2.0.8}/corems/encapsulation/factory/processingSetting.py

@@ -252,7 +252,7 @@ class MassSpectrumSetting:
     # How many data points (in each direction) to extrapolate the mz axis and 0 pad the abundance axis
     # This will fix peak picking at spectrum limit issues
     #  0 to keep normal behaviour, typical value 3 to fix
-    picking_point_extrapolate: int = 3 
+    picking_point_extrapolate: int = 0 
 
     calib_minimize_method: str = 'Powell'
     calib_pol_order: int = 2

{CoreMS-2.0.3 → CoreMS-2.0.8}/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-2.0.3 → CoreMS-2.0.8}/corems/mass_spectra/input/rawFileReader.py

@@ -759,7 +759,7 @@ class ThermoBaseClass:
 
         d_params["analyzer"] = self.iRawDataPlus.GetInstrumentData().Model
 
-        d_params["aquisition_time"] = self.iRawDataPlus.GetInstrumentData().Model
+        d_params["acquisition_time"] = self.get_creation_time()
 
         d_params["instrument_label"] = self.iRawDataPlus.GetInstrumentData().Name
 

{CoreMS-2.0.3 → CoreMS-2.0.8}/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-2.0.3 → CoreMS-2.0.8}/corems/mass_spectrum/calc/PeakPicking.py

@@ -147,10 +147,11 @@ class PeakPicking:
         self.abundance_profile = abundance
         self.freq_exp_profile = freq
         
-        mz, abundance, freq = self.extrapolate_axes_for_pp()
-        self.mz_exp_profile = mz
-        self.abundance_profile = abundance
-        self.freq_exp_profile = freq
+        if self.settings.picking_point_extrapolate > 0:
+            mz, abundance, freq = self.extrapolate_axes_for_pp()
+            self.mz_exp_profile = mz
+            self.abundance_profile = abundance
+            self.freq_exp_profile = freq
         
         if self.label == Labels.bruker_frequency or self.label == Labels.midas_frequency:
 
@@ -451,7 +452,7 @@ class PeakPicking:
 
         elif noise_threshold_method == 'signal_noise':
 
-            abundance_threshold = self.settings.s2n_threshold
+            abundance_threshold = self.settings.noise_threshold_min_s2n
             factor = self.baseline_noise_std
 
         elif noise_threshold_method == "relative_abundance":

{CoreMS-2.0.3 → CoreMS-2.0.8}/corems/mass_spectrum/factory/MassSpectrumClasses.py

@@ -3,7 +3,7 @@ from copy import deepcopy
 
 
 #from matplotlib import rcParamsDefault, rcParams
-from numpy import array, power, float64, where, histogram
+from numpy import array, power, float64, where, histogram, trapz
 
 from pandas import DataFrame
 from lmfit.models import GaussianModel
@@ -217,7 +217,7 @@ class MassSpecBase(MassSpecCalc, KendrickGrouping):
         - _calibration_terms
         - label
         - analyzer
-        - aquisition_time
+        - acquisition_time
         - instrument_label
         - polarity
         - scan_number
@@ -240,7 +240,7 @@ class MassSpecBase(MassSpecCalc, KendrickGrouping):
 
         self.analyzer = d_params.get('analyzer')
 
-        self.aquisition_time = d_params.get('aquisition_time')
+        self.acquisition_time = d_params.get('acquisition_time')
 
         self.instrument_label = d_params.get('instrument_label')
 
@@ -612,7 +612,7 @@ class MassSpecBase(MassSpecCalc, KendrickGrouping):
     @property
     def tic(self):
         """Return the total ion current of the mass spectrum."""
-        return sum(self.abundance_profile)
+        return trapz(self.abundance_profile, self.mz_exp_profile)
 
     def check_mspeaks_warning(self):
         """Check if the mass spectrum has MSpeaks objects.
@@ -1263,6 +1263,7 @@ class MassSpecfromFreq(MassSpecBase):
         if self._mz_exp[0] > self._mz_exp[-1]:
             self._mz_exp = self._mz_exp[::-1]
             self._abundance = self._abundance[::-1]
+            self._frequency_domain = self._frequency_domain[::-1]
 
     def _set_mz_domain(self):
         """Set the m/z domain of the mass spectrum based on the settings of d_params."""
@@ -1375,6 +1376,8 @@ class MassSpecCentroid(MassSpecBase):
 
         self.is_centroid = True
         self.data_dict = data_dict
+        self._mz_exp = data_dict[Labels.mz]
+        self._abundance = data_dict[Labels.abundance]
 
         if auto_process:
             self.process_mass_spec()

{CoreMS-2.0.3 → CoreMS-2.0.8}/corems/mass_spectrum/input/massList.py

@@ -83,6 +83,10 @@ class ReadCoremsMasslist(MassListBaseClass):
             ion_type_df = dataframe["Ion Type"]
             ion_charge_df = dataframe["Ion Charge"]
             is_isotopologue_df = dataframe['Is Isotopologue']
+            if 'Adduct' in dataframe:
+                adduct_df = dataframe['Adduct']
+            else:
+                adduct_df = None
 
         mass_spec_mz_exp_list = mass_spec_obj.mz_exp
 
@@ -102,7 +106,11 @@ class ReadCoremsMasslist(MassListBaseClass):
             if sum(counts) > 0:
 
                 ion_type = str(Labels.ion_type_translate.get(ion_type_df[df_index]))
-                mfobj = MolecularFormula(formula_list, int(ion_charge_df[df_index]), mspeak_parent=mass_spec_obj[ms_peak_index] , ion_type=ion_type)
+                if adduct_df is not None:
+                    adduct_atom = str(adduct_df[df_index])
+                else:
+                    adduct_atom = None
+                mfobj = MolecularFormula(formula_list, int(ion_charge_df[df_index]), mspeak_parent=mass_spec_obj[ms_peak_index] , ion_type=ion_type, adduct_atom=adduct_atom)
                 mfobj.is_isotopologue = bool(is_isotopologue_df[df_index])
                 mass_spec_obj[ms_peak_index].add_molecular_formula(mfobj)
 

CoreMS-2.0.8/corems/mass_spectrum/input/numpyArray.py

@@ -0,0 +1,108 @@
+
+__author__ = "Yuri E. Corilo"
+__date__ = "Oct 23, 2019"
+
+from corems.mass_spectrum.factory.MassSpectrumClasses import MassSpecProfile, MassSpecCentroid
+from corems.encapsulation.factory.parameters import default_parameters
+from corems.encapsulation.constant import Labels
+
+def ms_from_array_profile(mz, abundance, dataname:str, polarity:int = -1, auto_process:bool = True, data_type:str = Labels.simulated_profile):
+    """Create a MassSpecProfile object from an array of m/z values and abundance values.
+
+    Parameters
+    ----------
+    mz : numpy.ndarray
+        Array of m/z values.
+    abundance : numpy.ndarray
+        Array of abundance values.
+    dataname : str
+        Name of the data.
+    polarity : int, optional
+        Polarity of the data. The default is -1.
+    auto_process : bool, optional
+        Flag to automatically process the data. The default is True.
+    data_type : str, optional
+        Type of the data. The default is Labels.simulated_profile.
+
+    Returns
+    -------
+    MassSpecProfile
+        The created MassSpecProfile object.
+    """
+    data_dict = {Labels.mz: mz, Labels.abundance: abundance}
+    
+    output_parameters = get_output_parameters(polarity, dataname)
+    
+    output_parameters[Labels.label] = data_type
+
+    ms = MassSpecProfile(data_dict, output_parameters, auto_process=auto_process)
+    
+    return ms
+
+def ms_from_array_centroid(mz, abundance, rp:list[float], s2n:list[float], dataname:str, polarity:int=-1, auto_process:bool=True):
+    """Create a MassSpecCentroid object from an array of m/z values, abundance values, resolution power, and signal-to-noise ratio.
+
+    Parameters
+    ----------
+    mz : numpy.ndarray
+        Array of m/z values.
+    abundance : numpy.ndarray
+        Array of abundance values.
+    rp : list(float)
+        List of resolving power values.
+    s2n : list(float)
+        List of signal-to-noise ratio values.
+    dataname : str
+        Name of the data.
+    polarity : int, optional
+        Polarity of the data. The default is -1.
+    auto_process : bool, optional
+
+    Returns
+    -------
+    MassSpecCentroid
+        The created MassSpecCentroid object.
+    """
+    data_dict = {Labels.mz: mz, Labels.abundance: abundance, Labels.s2n : s2n, Labels.rp: rp}
+    
+    output_parameters = get_output_parameters(polarity, dataname)
+    output_parameters[Labels.label] = Labels.corems_centroid
+    
+    return MassSpecCentroid(data_dict, output_parameters, auto_process)
+    
+def get_output_parameters(polarity:int, file_location:str):
+    """Generate the output parameters for creating a MassSpecProfile or MassSpecCentroid object.
+
+    Parameters
+    ----------
+    polarity : int
+        Polarity of the data.
+    file_location : str
+        File location.
+
+    Returns
+    -------
+    dict
+        Output parameters.
+    """
+    d_params = default_parameters(file_location)
+    
+    d_params['analyzer'] = 'Generic Simulated'
+
+    d_params['instrument_label'] = 'Generic Simulated'
+
+    d_params["polarity"] = polarity
+    
+    d_params["filename_path"] = file_location
+    
+    d_params["mobility_scan"] = 0
+    
+    d_params["mobility_rt"] = 0
+    
+    d_params["scan_number"] = 0
+    
+    d_params["rt"] = 0
+
+    d_params[Labels.label] = Labels.simulated_profile
+    
+    return d_params

{CoreMS-2.0.3 → CoreMS-2.0.8}/corems/mass_spectrum/output/export.py

@@ -111,6 +111,7 @@ class HighResMassSpecExport(Thread):
                               'O/C',
                               'Heteroatom Class',
                               'Ion Type',
+                              'Adduct',
                               'Is Isotopologue',
                               'Mono Isotopic Index',
                               'Molecular Formula'
@@ -160,7 +161,6 @@ class HighResMassSpecExport(Thread):
 
     def get_pandas_df(self):
         """Returns the mass spectrum data as a pandas DataFrame."""
-
         columns = self.columns_label + self.get_all_used_atoms_in_order(self.mass_spectrum)
         dict_data_list = self.get_list_dict_data(self.mass_spectrum)
         df = DataFrame(dict_data_list, columns=columns)
@@ -563,6 +563,9 @@ class HighResMassSpecExport(Thread):
                            'Is Isotopologue': int(mformula.is_isotopologue),
                            'Molecular Formula': eval("mformula.string{}".format(encode))
                            }
+            
+            if mformula.adduct_atom:
+                dict_result['Adduct'] = eval("mformula.adduct_atom{}".format(encode))
 
             if mformula.is_isotopologue:
                 dict_result['Mono Isotopic Index'] = mformula.mspeak_index_mono_isotopic

{CoreMS-2.0.3 → CoreMS-2.0.8}/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 = []