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'])
df1.loc[pd.isna(df1['protein_descr']),
'protein_descr'] = df1.loc[pd.isna(df1['protein_descr']),
'protein']
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 = 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)
try:
logger.info('Calibrating retention model...')
with warnings.catch_warnings():
warnings.simplefilter("ignore")
df1['RT pred'] = df1['peptide'].apply(
lambda x: calc_RT(x, retention_coefficients))
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
'^(\s+[^\s]+){2}(\s+(?P<peptide>[A-Z]+))(\s+[^\s]+){10}(\s+(?P<affinity>[0-9]{1,2}\.[0-9]+))'
)
results = {}
with open(output_location, 'r') as f:
for line in f:
match = regex.match(line)
if match:
peptide = match.group('peptide')
affinity = float(match.group('affinity'))
results[peptide] = affinity
else:
print('Could not match line: %s' % line)
return results
mzid_parser = mzid.DataFrame(args.mzid_file)
netmhc_alleles = ['H-2-Kb']
"""
First, extract the targets and decoys from the PIN file.
"""
target_peptides = set()
decoy_peptides = set()
with open(args.pin_file, 'r') as f:
reader = csv.DictReader(f, delimiter='\t', restkey='Proteins')
next(reader)
for row in reader:
label = row['Label'].strip()
peptide = clean_peptide(row['Peptide'])
if len(peptide) >= min_peptide_length and len(
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
def read_mzid(path):
return mzid.DataFrame(path)