def get_RC(self):
try:
seqs = [pept.modified_sequence for pept in self.peptideslist]
RTexp = self.RT_exp#[pept.RT_exp for pept in self.peptideslist]
RC_def = achrom.RCs_gilar_rp
RC_def['aa'].setdefault('U', RC_def['aa'].get('C', 0.0))
RC_def['aa'].setdefault('O', RC_def['aa'].get('K', 0.0))
aa_labels = set(RC_def['aa'].keys())
for pept in self.peptideslist:
for v in pept.modification_list.itervalues():
aa_labels.add(v)
xdict = {}
for key, val in RC_def['aa'].items():
xdict[key] = [val, None]
RC_dict = achrom.get_RCs_vary_lcp(seqs, RTexp, labels=aa_labels)
for key, val in RC_dict['aa'].items():
try:
xdict[key][1] = val
except:
xdict[key] = [None, val]
a, b, _, _ = aux.linear_regression([x[0] for x in xdict.values() if all(v != None for v in x)], [x[1] for x in xdict.values() if all(v != None for v in x)])
for key, x in xdict.items():
if x[1] == None:
x[1] = x[0] * a + b
RC_dict['aa'][key] = x[1]
if 'C' not in RC_dict['aa']:
RC_dict['aa']['C'] = RC_dict['aa']['C*']
except:
logger.error('Error in get_RC for achrom model. Using RCs_gilar_rp')
RC_dict = achrom.RCs_gilar_rp
self.RC = RC_dict
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
def prepare_dataframe(infile_path,
decoy_prefix=None,
decoy_infix=False,
cleavage_rule=False,
fdr=0.01,
decoy2set=None):
if not cleavage_rule:
cleavage_rule = parser.expasy_rules['trypsin']
if infile_path.lower().endswith(
'.pep.xml') or infile_path.lower().endswith('.pepxml'):
df1 = pepxml.DataFrame(infile_path)
ftype = 'pepxml'
elif infile_path.lower().endswith('.mzid'):
df1 = mzid.DataFrame(infile_path)
else:
raise WrongInputError()
if not df1.shape[0]:
raise EmptyFileError()
if 'Morpheus Score' in df1.columns:
df1 = df1[df1['Morpheus Score'] != 0]
df1['expect'] = 1 / df1['Morpheus Score']
df1['num_missed_cleavages'] = df1['peptide'].apply(
lambda x: parser.num_sites(x, rule=cleavage_rule))
if 'MS-GF:EValue' in df1.columns:
# MSGF search engine
ftype = 'msgf'
df1['peptide'] = df1['PeptideSequence']
df1['num_missed_cleavages'] = df1['peptide'].apply(
lambda x: parser.num_sites(x, rule=cleavage_rule))
df1['assumed_charge'] = df1['chargeState']
df1['spectrum'] = df1['spectrumID']
df1['massdiff'] = (
df1['experimentalMassToCharge'] -
df1['calculatedMassToCharge']) * df1['assumed_charge']
df1['calc_neutral_pep_mass'] = df1['calculatedMassToCharge'] * df1[
'chargeState'] - df1['chargeState'] * 1.00727649
df1['protein'] = df1['accession']
df1['protein_descr'] = df1['protein description']
df1['expect'] = df1['MS-GF:EValue']
if set(df1['protein_descr'].str[0]) == {None}:
# MSFragger
logger.debug('Adapting MSFragger DataFrame.')
logger.debug('Proteins before: %s', df1.loc[1, 'protein'])
protein = df1['protein'].apply(
lambda row: [x.split(None, 1) for x in row])
df1['protein'] = protein.apply(lambda row: [x[0] for x in row])
try:
df1['protein_descr'] = protein.apply(
lambda row: [x[1] for x in row])
except IndexError:
df1['protein_descr'] = protein.apply(lambda row: ['' for x in row])
logger.debug('Proteins after: %s', df1.loc[1, 'protein'])
# if any(None in set(df1['protein_descr'].str[0])):
# print('HERE')
# df1['protein_descr'] = df1.apply(lambda x: x['protein_descr'] if x['protein_descr'] else x['protein'], axis=1)
df1.loc[pd.isna(df1['protein_descr']),
'protein_descr'] = df1.loc[pd.isna(df1['protein_descr']),
'protein']
# try:
# df1['expect'] = 1.0 / df1['bions_score_neg'].values
# except:
# pass
df1 = df1[~pd.isna(df1['peptide'])]
if 'MS1Intensity' not in df1:
df1['MS1Intensity'] = 0.0
df1['length'] = df1['peptide'].apply(len)
df1 = df1[df1['length'] >= 6]
df1['spectrum'] = df1['spectrum'].apply(lambda x: x.split(' RTINS')[0])
if 'retention_time_sec' not in df1.columns:
if 'scan start time' in df1.columns:
df1['RT exp'] = df1['scan start time']
df1 = df1.drop([
'scan start time',
], axis=1)
else:
df1['RT exp'] = 0
else:
df1['RT exp'] = df1['retention_time_sec'] / 60
df1 = df1.drop([
'retention_time_sec',
], axis=1)
df1['massdiff_int'] = df1['massdiff'].apply(lambda x: int(round(x, 0)))
df1['massdiff_ppm'] = 1e6 * (df1['massdiff'] - df1['massdiff_int'] *
1.003354) / df1['calc_neutral_pep_mass']
df1['decoy'] = df1['protein'].apply(is_decoy,
decoy_prefix=decoy_prefix,
decoy_infix=decoy_infix)
if not df1.decoy.sum():
raise NoDecoyError()
if decoy2set is None:
decoy2set = split_decoys(df1)
else:
df1['decoy2'] = df1['protein'].apply(
lambda p: all(x in decoy2set for x in p))
df1['decoy1'] = df1['decoy'] & (~df1['decoy2'])
df1 = remove_column_hit_rank(df1)
if ftype == 'pepxml':
df1['mods_counter'] = df1.apply(parse_mods, axis=1)
elif ftype == 'msgf':
df1['mods_counter'] = df1.apply(parse_mods_msgf, axis=1)
prepare_mods(df1)
pep_ratio = df1['decoy2'].sum() / df1['decoy'].sum()
df1_f = filter_custom(df1[~df1['decoy1']],
fdr=fdr,
key='expect',
is_decoy='decoy2',
reverse=False,
remove_decoy=False,
ratio=pep_ratio,
formula=1,
correction=None,
loglabel='PSMs default')
num_psms_def = df1_f[~df1_f['decoy2']].shape[0]
logger.info(
'Default target-decoy filtering, 1%% PSM FDR: Number of target PSMs = %d',
num_psms_def)
try:
logger.info('Calibrating retention model...')
with warnings.catch_warnings():
warnings.simplefilter("ignore")
retention_coefficients = achrom.get_RCs_vary_lcp(
df1_f['peptide'].values, df1_f['RT exp'].values)
df1_f['RT pred'] = df1_f['peptide'].apply(
lambda x: calc_RT(x, retention_coefficients))
df1['RT pred'] = df1['peptide'].apply(
lambda x: calc_RT(x, retention_coefficients))
_, _, r_value, std_value = aux.linear_regression(
df1_f['RT pred'], df1_f['RT exp'])
logger.info('RT model training results: R^2 = %f , std = %f',
r_value**2, std_value)
df1['RT diff'] = df1['RT pred'] - df1['RT exp']
logger.info('Retention model calibrated successfully.')
except Exception:
logger.warning('Retention times are probably missing in input file.')
df1['RT pred'] = df1['peptide'].apply(
lambda x: calc_RT(x, achrom.RCs_krokhin_100A_tfa))
df1['RT diff'] = df1['RT exp']
return df1, decoy2set