def test_priorityAssignment():
MSParameters.molecular_search.error_method = 'None'
MSParameters.molecular_search.min_ppm_error = -3
MSParameters.molecular_search.max_ppm_error = 5
MSParameters.molecular_search.mz_error_range = 1
MSParameters.molecular_search.isProtonated = True
MSParameters.molecular_search.isRadical= True
MSParameters.molecular_search.isAdduct= False
usedatoms = {'C': (1,100) , 'H': (4,200), 'O': (1,10)}
MSParameters.molecular_search.usedAtoms = usedatoms
mass_spec_obj = create_mass_spectrum()
mass_spec_obj.process_mass_spec()
assignOx = OxygenPriorityAssignment(mass_spec_obj)
assignOx.run()
#test classification
mass_spec_obj.percentile_assigned()
mass_spectrum_by_classes = HeteroatomsClassification(mass_spec_obj)
mass_spectrum_by_classes.plot_ms_assigned_unassigned()
mass_spectrum_by_classes.atoms_ratio_all("H", "C")
mass_spectrum_by_classes.atoms_ratio_all("H", "C")
def run_assignment(file_location):
#mass_spectrum = run_bruker(file_location)
mass_spectrum = get_masslist(file_location)
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.url_database = "postgres://*****:*****@localhost:5432/molformula"
mass_spectrum.molecular_search_settings.min_dbe = 0
mass_spectrum.molecular_search_settings.max_dbe = 50
mass_spectrum.molecular_search_settings.usedAtoms['C'] = (1, 100)
mass_spectrum.molecular_search_settings.usedAtoms['H'] = (4, 200)
mass_spectrum.molecular_search_settings.usedAtoms['O'] = (1, 22)
mass_spectrum.molecular_search_settings.usedAtoms['N'] = (0, 0)
mass_spectrum.molecular_search_settings.usedAtoms['S'] = (0, 0)
mass_spectrum.molecular_search_settings.usedAtoms['Cl'] = (0, 0)
mass_spectrum.molecular_search_settings.usedAtoms['Br'] = (0, 0)
mass_spectrum.molecular_search_settings.usedAtoms['P'] = (0, 0)
mass_spectrum.molecular_search_settings.usedAtoms['Na'] = (0, 0)
mass_spectrum.molecular_search_settings.isProtonated = True
mass_spectrum.molecular_search_settings.isRadical = False
mass_spectrum.molecular_search_settings.isAdduct = False
#mass_spectrum.filter_by_max_resolving_power(15, 2)
SearchMolecularFormulas(mass_spectrum,
first_hit=False).run_worker_mass_spectrum()
mass_spectrum.percentile_assigned(report_error=True)
mass_spectrum.to_csv("15T_Neg_ESI_SRFA")
export_calc_isotopologues(mass_spectrum,
"15T_Neg_ESI_SRFA_Calc_Isotopologues")
mass_spectrum_by_classes = HeteroatomsClassification(
mass_spectrum, choose_molecular_formula=True)
mass_spectrum_by_classes.plot_ms_assigned_unassigned()
#plt.show()
# dataframe = mass_spectrum_by_classes.to_dataframe()
return (mass_spectrum, mass_spectrum_by_classes)
def run_assignment(file_location):
# mass_spectrum = run_bruker(file_location)
# mass_spectrum = get_masslist(file_location)
mass_spectrum = run_thermo(file_location)
mass_spectrum.molecular_search_settings.error_method = 'None'
mass_spectrum.molecular_search_settings.min_ppm_error = -5
mass_spectrum.molecular_search_settings.max_ppm_error = 5
mass_spectrum.molecular_search_settings.url_database = None
mass_spectrum.molecular_search_settings.min_dbe = 0
mass_spectrum.molecular_search_settings.max_dbe = 50
mass_spectrum.molecular_search_settings.usedAtoms['C'] = (1, 100)
mass_spectrum.molecular_search_settings.usedAtoms['H'] = (4, 200)
mass_spectrum.molecular_search_settings.usedAtoms['O'] = (1, 30)
mass_spectrum.molecular_search_settings.usedAtoms['N'] = (0, 0)
mass_spectrum.molecular_search_settings.usedAtoms['S'] = (0, 0)
mass_spectrum.molecular_search_settings.usedAtoms['Cl'] = (0, 0)
mass_spectrum.molecular_search_settings.usedAtoms['Br'] = (0, 0)
mass_spectrum.molecular_search_settings.usedAtoms['P'] = (0, 0)
mass_spectrum.molecular_search_settings.usedAtoms['Na'] = (0, 0)
mass_spectrum.molecular_search_settings.isProtonated = True
mass_spectrum.molecular_search_settings.isRadical = False
mass_spectrum.molecular_search_settings.isAdduct = False
# mass_spectrum.filter_by_max_resolving_power(15, 2)
SearchMolecularFormulas(mass_spectrum,
first_hit=False).run_worker_mass_spectrum()
mass_spectrum.percentile_assigned(report_error=True)
mass_spectrum.molecular_search_settings.score_method = "prob_score"
mass_spectrum.molecular_search_settings.output_score_method = "prob_score"
# export_calc_isotopologues(mass_spectrum, "15T_Neg_ESI_SRFA_Calc_Isotopologues")
mass_spectrum_by_classes = HeteroatomsClassification(
mass_spectrum, choose_molecular_formula=True)
mass_spectrum_by_classes.plot_ms_assigned_unassigned()
plt.show()
mass_spectrum_by_classes.plot_mz_error()
plt.show()
mass_spectrum_by_classes.plot_ms_class("O2")
plt.show()
# dataframe = mass_spectrum_by_classes.to_dataframe()
return mass_spectrum
mass_spectrum.molecular_search_settings.isProtonated = True
mass_spectrum.molecular_search_settings.isRadical = False
mass_spectrum.molecular_search_settings.isAdduct = False
# mass_spectrum.filter_by_max_resolving_power(15, 2)
SearchMolecularFormulas(mass_spectrum,
first_hit=False).run_worker_mass_spectrum()
mass_spectrum.percentile_assigned(report_error=True)
mass_spectrum.molecular_search_settings.score_method = "prob_score"
mass_spectrum.molecular_search_settings.output_score_method = "prob_score"
# export_calc_isotopologues(mass_spectrum, "15T_Neg_ESI_SRFA_Calc_Isotopologues")
mass_spectrum_by_classes = HeteroatomsClassification(
mass_spectrum, choose_molecular_formula=True)
mass_spectrum_by_classes.plot_ms_assigned_unassigned()
plt.show()
mass_spectrum_by_classes.plot_mz_error()
plt.show()
mass_spectrum_by_classes.plot_ms_class("O2")
plt.show()
mass_spectrum.molecular_search_settings.error_method = 'None'
mass_spectrum.molecular_search_settings.min_ppm_error = -2
mass_spectrum.molecular_search_settings.max_ppm_error = 4
mass_spectrum.molecular_search_settings.url_database = None
mass_spectrum.molecular_search_settings.min_dbe = 0
mass_spectrum.molecular_search_settings.max_dbe = 50
mass_spectrum.molecular_search_settings.usedAtoms['Cl'] = (0, 0)
mass_spectrum.molecular_search_settings.usedAtoms['P'] = (0, 0)
mass_spectrum.molecular_search_settings.usedAtoms['Na'] = (0, 0)
mass_spectrum.molecular_search_settings.usedAtoms['K'] = (0, 0)
mass_spectrum.molecular_search_settings.usedAtoms['Fe'] = (0, 0)
mass_spectrum.molecular_search_settings.usedAtoms['Se'] = (0, 0)
mass_spectrum.molecular_search_settings.isProtonated = True
mass_spectrum.molecular_search_settings.isRadical = False
mass_spectrum.molecular_search_settings.isAdduct = True
SearchMolecularFormulas(mass_spectrum,
first_hit=False).run_worker_mass_spectrum()
mass_spectrum.percentile_assigned()
mass_spectrum_by_classes = HeteroatomsClassification(
mass_spectrum, choose_molecular_formula=False)
mass_spectrum_by_classes.plot_ms_assigned_unassigned()
plt.show()
all_classes = 0
for classe in mass_spectrum_by_classes.get_classes(threshold_perc=0,
isotopologue=True):
mass_spectrum_by_classes.plot_dbe_vs_carbon_number(classe)
#plt.show()
mass_spectrum_by_classes.plot_ms_class(classe)
plt.show()
mass_spectrum_by_classes.plot_mz_error_class(classe)
def create_plots(mass_spectrum, workflow_params, dirloc):
ms_by_classes = HeteroatomsClassification(mass_spectrum,
choose_molecular_formula=False)
if workflow_params.plot_ms_assigned_unassigned:
print("Plotting assigned vs. unassigned mass spectrum")
ax_ms = ms_by_classes.plot_ms_assigned_unassigned()
plt.savefig(dirloc / "assigned_unassigned.png", bbox_inches='tight')
plt.clf()
if workflow_params.plot_mz_error:
print("Plotting mz_error")
ax_ms = ms_by_classes.plot_mz_error()
plt.savefig(dirloc / "mz_error.png", bbox_inches='tight')
plt.clf()
if workflow_params.plot_van_krevelen:
van_krevelen_dirloc = dirloc / "van_krevelen"
van_krevelen_dirloc.mkdir(exist_ok=True, parents=True)
if workflow_params.plot_c_dbe:
c_dbe_dirloc = dirloc / "dbe_vs_c"
c_dbe_dirloc.mkdir(exist_ok=True, parents=True)
if workflow_params.plot_ms_classes:
ms_class_dirloc = dirloc / "ms_class"
ms_class_dirloc.mkdir(exist_ok=True, parents=True)
if workflow_params.plot_mz_error_classes:
mz_error_class_dirloc = dirloc / "mz_error_class"
mz_error_class_dirloc.mkdir(exist_ok=True, parents=True)
pbar = tqdm(ms_by_classes.get_classes())
for classe in pbar:
pbar.set_description_str(
desc="Plotting results for class {}".format(classe), refresh=True)
if workflow_params.plot_van_krevelen:
ax_c = ms_by_classes.plot_van_krevelen(classe)
plt.savefig(van_krevelen_dirloc / "{}.png".format(classe),
bbox_inches='tight')
plt.clf()
if workflow_params.plot_mz_error_classes:
ax_c = ms_by_classes.plot_mz_error_class(classe)
plt.savefig(mz_error_class_dirloc / "{}.png".format(classe),
bbox_inches='tight')
plt.clf()
if workflow_params.plot_ms_classes:
ax_c = ms_by_classes.plot_ms_class(classe)
plt.savefig(ms_class_dirloc / "{}.png".format(classe),
bbox_inches='tight')
plt.clf()
if workflow_params.plot_c_dbe:
ax_c = ms_by_classes.plot_dbe_vs_carbon_number(classe)
plt.savefig(c_dbe_dirloc / "{}.png".format(classe),
bbox_inches='tight')
plt.clf()
def test_heteroatoms_classification():
MSParameters.molecular_search.error_method = 'None'
MSParameters.molecular_search.min_ppm_error = -10
MSParameters.molecular_search.max_ppm_error = 10
MSParameters.molecular_search.mz_error_range = 1
MSParameters.molecular_search.isProtonated = True
MSParameters.molecular_search.isRadical= False
MSParameters.molecular_search.isAdduct= False
MSParameters.molecular_search.usedAtoms['C'] = (1, 100)
MSParameters.molecular_search.usedAtoms['H'] = (4, 200)
MSParameters.molecular_search.usedAtoms['O'] = (1, 18)
#MSParameters.molecular_search.usedAtoms = usedatoms
mass_spec_obj = create_mass_spectrum()
assignOx = SearchMolecularFormulas(mass_spec_obj).run_worker_mass_spectrum()
#test classification
mass_spec_obj.percentile_assigned()
mass_spectrum_by_classes = HeteroatomsClassification(mass_spec_obj)
mass_spectrum_by_classes.plot_ms_assigned_unassigned()
mass_spectrum_by_classes.atoms_ratio_all("H", "C")
mass_spectrum_by_classes.dbe_all()
mass_spectrum_by_classes.carbon_number_all()
mass_spectrum_by_classes.abundance_assigned()
mass_spectrum_by_classes.mz_exp_assigned()
mass_spectrum_by_classes.abundance_count_percentile(Labels.unassigned)
mass_spectrum_by_classes.peaks_count_percentile(Labels.unassigned)