CoreMS 4.0.0__py3-none-any.whl

corems-4.0.0.dist-info/licenses/LICENSE

@@ -0,0 +1,22 @@
+Copyright Battelle Memorial Institute
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+this list of conditions and the following disclaimer in the documentation
+and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

corems-4.0.0.dist-info/top_level.txt

@@ -0,0 +1,4 @@
+corems
+examples
+ext_lib
+support_code

examples/archive/scripts/CoreMS_tutorial.py

@@ -0,0 +1,94 @@
+from pathlib import Path
+
+from matplotlib import pyplot
+
+from corems.encapsulation.factory.parameters import MSParameters
+from corems.transient.input.brukerSolarix import ReadBrukerSolarix
+from corems.mass_spectrum.calc.Calibration import MzDomainCalibration
+
+file_location =  "tests/tests_data/ftms/ESI_NEG_SRFA.d"
+
+MSParameters.transient.apodization_method = "Hanning"
+MSParameters.transient.number_of_truncations = 0
+MSParameters.transient.number_of_zero_fills = 1
+
+MSParameters.mass_spectrum.noise_threshold_method = 'relative_abundance'
+MSParameters.mass_spectrum.noise_threshold_min_relative_abundance = 1
+
+#MSParameters.mass_spectrum.noise_threshold_method = 'signal_noise'
+#MSParameters.mass_spectrum.noise_threshold_min_s2n = 50
+
+#MSParameters.mass_spectrum.noise_threshold_method = 'log'
+#MSParameters.mass_spectrum.noise_threshold_min_std = 32
+
+MSParameters.ms_peak.peak_min_prominence_percent = 1
+        
+def import_transient():
+    
+    with ReadBrukerSolarix(file_location) as bruker_transient:
+
+        mass_spectrum = bruker_transient.get_mass_spectrum(plot_result=True, auto_process=True)
+
+        mass_spectrum.plot_profile_and_noise_threshold()
+
+        print("m/z count", len(mass_spectrum))
+
+        print('first m/z', mass_spectrum.mspeaks[0].mz_exp, 'final m/z', mass_spectrum.mspeaks[-1].mz_exp)
+    
+    return mass_spectrum
+
+mass_spectrum = import_transient()
+
+
+MSParameters.mass_spectrum.min_calib_ppm_error = -5
+MSParameters.mass_spectrum.max_calib_ppm_error = 5
+
+mass_spectrum = import_transient()
+
+ref_file_location = 'tests/tests_data/ftms/SRFA.ref'
+
+MzDomainCalibration(mass_spectrum, ref_file_location).run()
+
+from corems.molecular_id.search.molecularFormulaSearch import SearchMolecularFormulas
+from corems.molecular_id.factory.classification import HeteroatomsClassification
+
+mass_spectrum.molecular_search_settings.url_database = "postgresql+psycopg2://coremsappdb:coremsapppnnl@localhost:5432/coremsapp"
+
+mass_spectrum.molecular_search_settings.error_method = 'None'
+mass_spectrum.molecular_search_settings.min_ppm_error  = -1
+mass_spectrum.molecular_search_settings.max_ppm_error = 1
+
+mass_spectrum.molecular_search_settings.min_dbe = 0
+mass_spectrum.molecular_search_settings.max_dbe = 50
+
+mass_spectrum.molecular_search_settings.isProtonated = True 
+mass_spectrum.molecular_search_settings.isRadical= False 
+mass_spectrum.molecular_search_settings.isadduct = True 
+
+mass_spectrum.molecular_search_settings.usedAtoms['C'] = (1,90)
+mass_spectrum.molecular_search_settings.usedAtoms['H'] = (4,200)
+mass_spectrum.molecular_search_settings.usedAtoms['O'] = (1,20)
+mass_spectrum.molecular_search_settings.usedAtoms['N'] = (0,0)
+mass_spectrum.molecular_search_settings.usedAtoms['S'] = (0,0)
+
+SearchMolecularFormulas(mass_spectrum, first_hit=True).run_worker_mass_spectrum()
+mass_spectrum.percentile_assigned(report_error=True)
+
+mass_spectrum_by_classes = HeteroatomsClassification(mass_spectrum, choose_molecular_formula=True)
+mass_spectrum_by_classes.plot_ms_assigned_unassigned()
+
+for mspeaks in mass_spectrum.sort_by_abundance():
+   if mspeaks: #or just if mspeak:
+        for mf in mspeaks:
+            print(mf.mz_calc, mf.dbe, mf.class_label, mf.string_formated)
+
+#exporting data
+mass_spectrum.to_csv("test")
+
+# save pandas Datarame to pickle
+mass_spectrum.to_pandas("test")
+
+# get pandas Dataframe
+df = mass_spectrum.to_dataframe()
+
+df.head()

examples/archive/scripts/DI HR-MS Halogens Bruker.py

@@ -0,0 +1,196 @@
+import sys
+sys.path.append("./")
+
+import warnings
+warnings.filterwarnings("ignore")
+
+from pathlib import Path
+
+import matplotlib.pyplot as plt
+from numpy import unique
+
+from corems import SuppressPrints, get_dirnames
+from corems.molecular_id.factory.classification import HeteroatomsClassification, Labels
+from corems.molecular_id.search.priorityAssignment import OxygenPriorityAssignment
+from corems.transient.input.brukerSolarix import ReadBrukerSolarix
+from corems.molecular_id.search.molecularFormulaSearch import SearchMolecularFormulas
+from corems.mass_spectrum.calc.MassErrorPrediction import MassErrorPrediction
+
+
+def get_mass_spectrum(file_location):
+
+    bruker_reader = ReadBrukerSolarix(file_location)
+
+    bruker_transient = bruker_reader.get_transient()
+
+    return bruker_transient.get_mass_spectrum(plot_result=False, auto_process=True)
+
+def export(list_dict, export_name):
+
+    import pandas as pd
+
+    columns = [ "Sample Name", 
+                "Calculated m/z",
+                "Experimental m/z",
+                "Error m/z", 
+                "Peak Height",
+                "Signal Noise Ratio",
+                "Peak Datapoint Count",
+                "Resolving Power",
+                "Molecular Formula",
+                "Peak Area",
+                "Area Ratio Error",
+                "Probability Ratio",
+                "Abundance Error"
+               ]
+
+    df = pd.DataFrame(list_dict, columns=columns)
+    df.to_pickle(export_name + ".pkl")
+    df.to_csv(export_name + ".csv", index=False)
+
+
+def set_settings_for_bromothymol_blue(mass_spectrum):
+
+    mass_spectrum.molecular_search_settings.min_ppm_error = -2
+    mass_spectrum.molecular_search_settings.max_ppm_error = 5
+
+    mass_spectrum.molecular_search_settings.usedAtoms['C'] = (1, 90)
+    mass_spectrum.molecular_search_settings.usedAtoms['H'] = (4, 200)
+    mass_spectrum.molecular_search_settings.usedAtoms['O'] = (5, 5)
+    mass_spectrum.molecular_search_settings.usedAtoms['N'] = (0, 0)
+    mass_spectrum.molecular_search_settings.usedAtoms['S'] = (1, 1)
+    mass_spectrum.molecular_search_settings.usedAtoms['Br'] = (2, 2)
+
+    #enables the search for Br compounds 
+    mass_spectrum.molecular_search_settings.adduct_atoms_neg = ['Cl', 'F']
+
+    mass_spectrum.molecular_search_settings.isProtonated = True
+    mass_spectrum.molecular_search_settings.isRadical = False
+    mass_spectrum.molecular_search_settings.isAdduct = False
+
+    mass_spectrum.molecular_search_settings.use_min_peaks_filter = False
+
+def set_settings_for_chlorophenol_red(mass_spectrum):
+    #Chlorophenol Red –  C19H12Cl2O5S -  421.978241
+
+    mass_spectrum.molecular_search_settings.min_ppm_error  = -2
+    mass_spectrum.molecular_search_settings.max_ppm_error = 5
+
+    mass_spectrum.molecular_search_settings.usedAtoms['C'] = (1,90)
+    mass_spectrum.molecular_search_settings.usedAtoms['H'] = (4,200)
+    mass_spectrum.molecular_search_settings.usedAtoms['O'] = (5,5)
+    mass_spectrum.molecular_search_settings.usedAtoms['N'] = (0,0)
+    mass_spectrum.molecular_search_settings.usedAtoms['S'] = (1,1)
+    mass_spectrum.molecular_search_settings.usedAtoms['Cl'] = (2,2)
+
+    #enables the search for Cl compounds 
+    mass_spectrum.molecular_search_settings.adduct_atoms_neg = ['Br', 'F']
+
+    mass_spectrum.molecular_search_settings.isProtonated = True
+    mass_spectrum.molecular_search_settings.isRadical= False
+    mass_spectrum.molecular_search_settings.isAdduct = False
+
+    mass_spectrum.molecular_search_settings.use_min_peaks_filter = False
+
+if __name__ == "__main__":
+    
+    list_dict = []
+    
+    dirnames = get_dirnames()
+    
+    if dirnames:
+        
+        for file_location in dirnames:
+            
+            print(file_location)
+            
+            mass_spectrum = get_mass_spectrum(file_location)
+            
+            set_settings_for_bromothymol_blue(mass_spectrum)
+            #set_settings_for_chlorophenol_red(mass_spectrum)
+
+            SearchMolecularFormulas(mass_spectrum, first_hit=True).run_worker_mass_spectrum()
+            
+            #mass_error_prediction = MassErrorPrediction(mass_spectrum)
+    
+            #mass_error_prediction.get_results()
+
+            ax = mass_spectrum.plot_mz_domain_profile()
+            #plt.show()
+            
+            for mspeak in mass_spectrum:
+                
+                if mspeak:
+                    
+                    for mf in mspeak: 
+                    
+                        ax.plot(mspeak.mz_exp,mspeak.abundance, color='black', linewidth=0, marker='s', markersize = 8, label='Assigned')
+                        
+                        if mf.is_isotopologue:
+                            
+                            ax.annotate(round(mf.abundance_error,1), (mspeak.mz_exp+0.2, mspeak.abundance), label="Error (%)")
+                            list_dict.append( {
+                                
+                                "Sample Name" : mass_spectrum.sample_name, 
+                                "Resolving Power" : mspeak.resolving_power, 
+                                "Peak Height" : mspeak.abundance, 
+                                "Signal Noise Ratio" : mspeak.signal_to_noise,
+                                "Calculated m/z" : mf.mz_calc,
+                                "Experimental m/z" : mspeak.mz_exp, 
+                                "Error m/z" : mf.mz_error, 
+                                "Peak Area": mspeak.area, 
+                                "Molecular Formula" : mf.string,
+                                "Probability Ratio": mf.prob_ratio,
+                                "Area Ratio Error": mf.area_error,
+                                "Abundance Error": mf.abundance_error,
+                                "Peak Datapoint Count" : mspeak.final_index-mspeak.start_index
+                            })
+                        
+                        else:
+                            print(mf.confidence_score)
+                            print( mf.string, mf.mz_calc, mf.mz_error) 
+                            
+                            list_dict.append( {
+                                
+                                "Sample Name" : mass_spectrum.sample_name, 
+                                "Resolving Power" : mspeak.resolving_power,
+                                "Peak Height" : mspeak.abundance, 
+                                "Signal Noise Ratio" : mspeak.signal_to_noise,
+                                "Calculated m/z" : mf.mz_calc,
+                                "Experimental m/z" : mspeak.mz_exp, 
+                                "Error m/z" : mf.mz_error, 
+                                "Peak Area": mspeak.area,
+                                "Molecular Formula" : mf.string,
+                                "Peak Datapoint Count" : mspeak.final_index-mspeak.start_index
+                            })
+                        #ax.annotate(mspeak.mz_exp, (mspeak.mz_exp, mspeak.abundance))
+
+                        for imf in mf.expected_isotopologues: 
+                            
+                            ax.plot(imf.mz_calc, imf.abundance_calc, color='red', linewidth=0, marker='v', markersize = 8, label='Calculated')
+
+                            #ax.annotate(imf.string, (imf.mz_calc, imf.abundance_calc))
+            
+            hand, labl = ax.get_legend_handles_labels()
+            handout=[]
+            lablout=[]
+            for h,l in zip(hand,labl):
+                if l not in lablout:
+                        lablout.append(l)
+                        handout.append(h)
+            
+            plt.legend(handout, lablout)
+            plt.xlim(620,630)
+            # plt.show()
+            #plt.savefig(mass_spectrum.sample_name+"_area"+".png")
+            plt.cla()
+            
+        export(list_dict, "Chlorophenol Red C19 H12 Cl2 O5 S1")
+        #export(list_dict, "Chlorophenol Red C19 H12 Cl2 O5 S1")    
+        
+        # Bromothymol Blue –  C27H28Br2O5S -  622.002380
+        # Bromocresol Green – C21H14Br4O5S - 693.729492
+        # Chlorophenol Red –  C19H12Cl2O5S -  421.978241
+        # Bromphenol Blue –   C19H10Br4O5S(Na) -  665.698242
+        
+