def calc_RT(self, calibrate_coeff=(1, 0, 0, 0), RTtype='achrom'):
self.RT_predicted = []
if RTtype == 'ssrcalc':
if SSRCalc is None:
logger.critical('SSRCalc not available. Make sure that mechanize is installed.')
sys.exit(1)
ps = list(set([peptide.sequence for peptide in self.peptideslist]))
SSRCalc_RTs = SSRCalc.calculate_RH(ps[:], pore_size=100, ion_pairing_agent='FA')
for peptide in self.peptideslist:
if RTtype == 'achrom':
RT_predicted = achrom.calculate_RT(peptide.modified_sequence, self.RC, raise_no_mod=False)
if np.isinf(RT_predicted):
elems = peptide.modified_sequence.split('-')
if len(elems) > 1:
if not all(el in parser.std_amino_acids for el in elems[0]) and str(elems[0] + '-') not in self.RC['aa']:
self.RC['aa'][str(elems[0] + '-')] = self.RC['aa']['H-']
elif not all(el in parser.std_amino_acids for el in elems[-1]) and str('-' + elems[-1]) not in self.RC['aa']:
self.RC['aa'][str('-' + elems[-1])] = self.RC['aa']['-OH']
RT_predicted = achrom.calculate_RT(peptide.modified_sequence, self.RC, raise_no_mod=False)
elif RTtype == 'ssrcalc':
SSRCalc_RT = SSRCalc_RTs[peptide.sequence]
if SSRCalc_RT is not None:
RT_predicted = float(SSRCalc_RT) * calibrate_coeff[0] + calibrate_coeff[1]
else:
RT_predicted = 0
logger.error('SSRCalc error')
elif RTtype == 'biolccc':
RT_predicted = biolccc.calculateRT(peptide.sequence, biolccc.rpAcnTfaChain, biolccc.standardChromoConditions)
else:
logger.error('RT_type error')
self.RT_predicted.append(RT_predicted)
self.check_arrays()
def pyteomcis_snippets(traindf, trainy, testdf, nomod=True):
"""
"""
#pyteomics
clf = achrom.get_RCs_vary_lcp([str(i).replace("U", "C") for i in traindf],
trainy)
print("Pyteomics LCP: {}".format(clf["lcp"]))
yhat_train = [
achrom.calculate_RT(i, clf, raise_no_mod=nomod) for i in traindf
]
yhat_test = [
achrom.calculate_RT(i, clf, raise_no_mod=nomod) for i in testdf
]
return (yhat_train, yhat_test)
def rt_prediction(calib_file, finalMS1_df):
print ' from:', calib_file
calib_df = pd.read_excel(calib_file)
reten_seq = [str(x) for x in calib_df['Sequence']]
reten_peak = calib_df['PepRtimePeak'].tolist()
np.warnings.filterwarnings('ignore')
RCs = achrom.get_RCs_vary_lcp(reten_seq, reten_peak)
initRT_tuple = []
for idx, row in finalMS1_df.iterrows():
pept = str(row['pept'])
rt = achrom.calculate_RT(pept, RCs)
initRT_tuple.append((idx, pept, rt))
reten_start = calib_df['PepRtimeStart']
reten_end = calib_df['PepRtimeEnd']
initRT_width = np.mean((reten_end - reten_start).values)
reten_validate = []
for seq in reten_seq:
rt_v = achrom.calculate_RT(seq, RCs)
reten_validate.append(rt_v)
predict_coef = np.corrcoef(reten_peak, reten_validate)
return initRT_tuple, initRT_width
print 'Done!'
peptides = [peptide for peptide in peptides if peptide['length'] <= 100]
print 'Calculating the mass, charge and m/z...'
for peptide in peptides:
peptide['charge'] = int(
round(electrochem.charge(peptide['parsed_sequence'], pH=2.0)))
peptide['mass'] = mass.calculate_mass(peptide['parsed_sequence'])
peptide['m/z'] = mass.calculate_mass(peptide['parsed_sequence'],
charge=peptide['charge'])
print 'Done!'
print 'Calculating the retention time...'
for peptide in peptides:
peptide['RT_RP'] = achrom.calculate_RT(peptide['parsed_sequence'],
achrom.RCs_zubarev)
peptide['RT_normal'] = achrom.calculate_RT(peptide['parsed_sequence'],
achrom.RCs_yoshida_lc)
print 'Done!'
plt.figure()
plt.hist([peptide['m/z'] for peptide in peptides], bins=2000, range=(0, 4000))
plt.xlabel('m/z, Th')
plt.ylabel('# of peptides within 2 Th bin')
plt.figure()
plt.hist([peptide['charge'] for peptide in peptides], bins=20, range=(0, 10))
plt.xlabel('charge, e')
plt.ylabel('# of peptides')
x = [peptide['RT_RP'] for peptide in peptides]
def calc_RT(seq, RC):
try:
return achrom.calculate_RT(seq, RC)
except Exception:
return 0