def get_psms(self):
self.header = self.oldheader[:]
if self.denomcols is not None:
denomcols = [
self.number_to_headerfield(col, self.oldheader)
for col in self.denomcols
]
elif self.denompatterns is not None:
denomcolnrs = [
tsv.get_columns_by_pattern(self.oldheader, pattern)
for pattern in self.denompatterns
]
denomcols = set([col for cols in denomcolnrs for col in cols])
else:
raise RuntimeError('Must define either denominator column numbers '
'or regex pattterns to find them')
quantcols = tsv.get_columns_by_pattern(self.oldheader,
self.quantcolpattern)
if self.medianpsms is not None:
medianheader = tsv.get_tsv_header(self.medianpsms)
else:
medianheader = False
self.psms = prep.get_normalized_ratios(self.fn, self.oldheader,
quantcols, denomcols,
self.minint, self.medianpsms,
medianheader)
def set_features(self):
denomcols = False
if self.denomcols is not None:
denomcols = [self.number_to_headerfield(col, self.oldheader)
for col in self.denomcols]
elif self.denompatterns is not None:
denomcolnrs = [tsvreader.get_columns_by_pattern(self.oldheader, pattern)
for pattern in self.denompatterns]
denomcols = set([col for cols in denomcolnrs for col in cols])
elif not self.mediansweep and not self.medianintensity:
raise RuntimeError('Must define either denominator column numbers '
'or regex pattterns to find them')
quantcols = tsvreader.get_columns_by_pattern(self.oldheader,
self.quantcolpattern)
mn_factors = False
if self.mednorm_factors:
mnhead = tsvreader.get_tsv_header(self.mednorm_factors)
mn_factors = tsvreader.generate_split_tsv_lines(self.mednorm_factors, mnhead)
nopsms = [isosummarize.get_no_psms_field(qf) for qf in quantcols]
if self.featcol:
self.get_column_header_for_number(['featcol'], self.oldheader)
self.header = [self.featcol] + quantcols + nopsms + [HEADER_NO_FULLQ_PSMS]
else:
self.header = (self.oldheader +
['ratio_{}'.format(x) for x in quantcols])
self.psms = isosummarize.get_isobaric_ratios(self.fn, self.oldheader,
quantcols, denomcols, self.mediansweep, self.medianintensity,
self.median_or_avg, self.minint, False, False, self.featcol,
False, False, False, self.logisoquant, self.mediannormalize,
mn_factors, self.keepnapsms)
def get_psms(self):
if self.denomcols is not None:
denomcols = [self.number_to_headerfield(col, self.oldheader)
for col in self.denomcols]
elif self.denompatterns is not None:
denomcolnrs = [tsv.get_columns_by_pattern(self.oldheader, pattern)
for pattern in self.denompatterns]
denomcols = set([col for cols in denomcolnrs for col in cols])
else:
raise RuntimeError('Must define either denominator column numbers '
'or regex pattterns to find them')
quantcols = tsv.get_columns_by_pattern(self.oldheader,
self.quantcolpattern)
self.get_column_header_for_number(['proteincol'], self.oldheader)
nopsms = [prep.get_no_psms_field(qf) for qf in quantcols]
if self.proteincol and self.targettable:
targetheader = tsv.get_tsv_header(self.targettable)
self.header = targetheader + quantcols + nopsms
elif not self.proteincol and not self.targettable:
self.header = (self.oldheader +
['ratio_{}'.format(x) for x in quantcols])
elif self.proteincol and not self.targettable:
self.header = [prottabledata.HEADER_ACCESSION] + quantcols + nopsms
self.psms = prep.get_isobaric_ratios(self.fn, self.oldheader,
quantcols, denomcols, self.minint,
self.targettable, self.proteincol,
self.normalize,
self.normalizeratios)
def get_psms(self):
if self.denomcols is not None:
denomcols = [
self.number_to_headerfield(col, self.oldheader)
for col in self.denomcols
]
elif self.denompatterns is not None:
denomcolnrs = [
tsv.get_columns_by_pattern(self.oldheader, pattern)
for pattern in self.denompatterns
]
denomcols = set([col for cols in denomcolnrs for col in cols])
else:
raise RuntimeError('Must define either denominator column numbers '
'or regex pattterns to find them')
quantcols = tsv.get_columns_by_pattern(self.oldheader,
self.quantcolpattern)
self.get_column_header_for_number(['proteincol'], self.oldheader)
nopsms = [prep.get_no_psms_field(qf) for qf in quantcols]
if self.proteincol and self.targettable:
targetheader = tsv.get_tsv_header(self.targettable)
self.header = targetheader + quantcols + nopsms
elif not self.proteincol and not self.targettable:
self.header = (self.oldheader +
['ratio_{}'.format(x) for x in quantcols])
elif self.proteincol and not self.targettable:
self.header = [prottabledata.HEADER_ACCESSION] + quantcols + nopsms
self.psms = prep.get_isobaric_ratios(self.fn, self.oldheader,
quantcols, denomcols, self.minint,
self.targettable, self.proteincol,
self.normalize,
self.normalizeratios)
def get_quant(self, theader, features):
if self.precursor:
tpeps = tsvreader.generate_split_tsv_lines(self.fn, theader)
self.header.append(prottabledata.HEADER_AREA)
features = proteins.add_ms1_quant_from_top3_mzidtsv(
features, tpeps, self.headeraccfield, self.fixedfeatcol)
if self.quantcolpattern:
psmheader = tsvreader.get_tsv_header(self.psmfile)
denomcols = False
if self.denomcols is not None:
denomcols = [
self.number_to_headerfield(col, psmheader)
for col in self.denomcols
]
elif self.denompatterns is not None:
denomcolnrs = [
tsvreader.get_columns_by_pattern(psmheader, pattern)
for pattern in self.denompatterns
]
denomcols = set([col for cols in denomcolnrs for col in cols])
elif not self.mediansweep and not self.medianintensity:
print(
'Must define either denominator column numbers '
'or regex pattterns to find them, or use median sweep, or '
'report median intensities.')
sys.exit(1)
elif self.medianintensity and self.mediannormalize:
print(
'Cannot do median-centering on intensity values, exiting')
sys.exit(1)
quantcols = tsvreader.get_columns_by_pattern(
psmheader, self.quantcolpattern)
mn_factors = False
if self.mednorm_factors:
mnhead = tsvreader.get_tsv_header(self.mednorm_factors)
mn_factors = tsvreader.generate_split_tsv_lines(
self.mednorm_factors, mnhead)
nopsms = [isosummarize.get_no_psms_field(qf) for qf in quantcols]
self.header = self.header + quantcols + nopsms + [
prottabledata.HEADER_NO_FULLQ_PSMS
]
features = isosummarize.get_isobaric_ratios(
self.psmfile, psmheader, quantcols, denomcols,
self.mediansweep, self.medianintensity, self.median_or_avg,
self.minint, features, self.headeraccfield, self.fixedfeatcol,
False, False, False, self.logisoquant, self.mediannormalize,
mn_factors, self.keepnapsms)
return features
def get_psms(self):
self.header = self.oldheader[:]
if self.denomcols is not None:
denomcols = [self.number_to_headerfield(col, self.oldheader)
for col in self.denomcols]
elif self.denompatterns is not None:
denomcolnrs = [tsv.get_columns_by_pattern(self.oldheader, pattern)
for pattern in self.denompatterns]
denomcols = set([col for cols in denomcolnrs for col in cols])
else:
raise RuntimeError('Must define either denominator column numbers '
'or regex pattterns to find them')
quantcols = tsv.get_columns_by_pattern(self.oldheader,
self.quantcolpattern)
if self.medianpsms is not None:
medianheader = tsv.get_tsv_header(self.medianpsms)
else:
medianheader = False
self.psms = prep.get_normalized_ratios(self.fn, self.oldheader,
quantcols, denomcols,
self.minint, self.medianpsms,
medianheader)
def get_psm2pep_header(oldheader, isobq_pattern=False, precurqfield=False):
header = oldheader[:]
if isobq_pattern:
isocols = tsv.get_columns_by_pattern(header, isobq_pattern)
for col in isocols:
header.pop(header.index(col))
if precurqfield:
header = [peptabledata.HEADER_AREA if x == precurqfield
else x for x in header]
peptable_header = [peptabledata.HEADER_LINKED_PSMS]
ix = header.index(mzidtsvdata.HEADER_PEPTIDE)
header = header[:ix] + peptable_header + header[ix:]
switch_map = switch_psm_to_peptable_fields(header)
return [switch_map[field] if field in switch_map else field
for field in header]
def get_psm2pep_header(oldheader, isobq_pattern=False, precurqfield=False):
header = oldheader[:]
if isobq_pattern:
isocols = tsv.get_columns_by_pattern(header, isobq_pattern)
for col in isocols:
header.pop(header.index(col))
if precurqfield:
header = [
peptabledata.HEADER_AREA if x == precurqfield else x
for x in header
]
peptable_header = [peptabledata.HEADER_LINKED_PSMS]
ix = header.index(mzidtsvdata.HEADER_PEPTIDE)
header = header[:ix] + peptable_header + header[ix:]
switch_map = switch_psm_to_peptable_fields(header)
return [
switch_map[field] if field in switch_map else field for field in header
]
def set_features(self):
qpat = self.quantcolpattern if self.quantcolpattern else '[a-z]+[0-9]+plex_'
header = [x for x in self.oldheader if x != psmh.HEADER_SPECFILE]
try:
isocols = tsvreader.get_columns_by_pattern(header, qpat)
except RuntimeError:
pass
else:
for col in isocols:
header.pop(header.index(col))
if self.precurquantcol:
header = [peph.HEADER_AREA if x == self.precurquantcol
else x for x in header]
header = [peph.HEADER_PEPTIDE, peph.HEADER_LINKED_PSMS] + [
x for x in header if x != psmh.HEADER_PEPTIDE]
switch_map = {old: new for old, new in zip(
[psmh.HEADER_PEPTIDE, psmh.HEADER_PROTEIN, psmh.HEADER_PEPTIDE_Q],
[peph.HEADER_PEPTIDE, peph.HEADER_PROTEINS, peph.HEADER_QVAL])}
self.header = [switch_map[field] if field in switch_map else field
for field in header]
peptides = psmtopeptable.generate_peptides(self.fn, self.oldheader,
switch_map, self.scorecol, self.precurquantcol, self.spectracol)
# Remove quant data if not specified any way to summarize
if self.quantcolpattern and any([self.denomcols, self.denompatterns,
self.mediansweep, self.medianintensity]):
denomcols = False
if self.denomcols is not None:
denomcols = [self.number_to_headerfield(col, self.oldheader)
for col in self.denomcols]
elif self.denompatterns is not None:
denomcolnrs = [tsvreader.get_columns_by_pattern(self.oldheader, pattern)
for pattern in self.denompatterns]
denomcols = set([col for cols in denomcolnrs for col in cols])
quantcols = tsvreader.get_columns_by_pattern(self.oldheader,
self.quantcolpattern)
totalproteome, tpacc, tp_pepacc = False, False, False
if self.totalprotfn:
pep_tp_accs = [psmh.HEADER_MASTER_PROT, psmh.HEADER_SYMBOL,
psmh.HEADER_GENE, peph.HEADER_PROTEINS]
totalphead = tsvreader.get_tsv_header(self.totalprotfn)
totalpfield_found = False
for tpacc, tp_pepacc in zip(proth.TPROT_HEADER_ACCS, pep_tp_accs):
if totalphead[0] == tpacc and tp_pepacc in self.header:
totalpfield_found = True
break
if not totalpfield_found:
print('Could not find correct header field name in the total '
'proteome table passed. '
'Should be one of {}'.format(proth.TPROT_HEADER_ACCS))
sys.exit(1)
totalproteome = tsvreader.generate_split_tsv_lines(self.totalprotfn, totalphead)
mn_factors = False
if self.mednorm_factors:
mnhead = tsvreader.get_tsv_header(self.mednorm_factors)
mn_factors = tsvreader.generate_split_tsv_lines(self.mednorm_factors, mnhead)
nopsms = [isosummarize.get_no_psms_field(qf) for qf in quantcols]
self.header = self.header + quantcols + nopsms + [proth.HEADER_NO_FULLQ_PSMS]
peptides = isosummarize.get_isobaric_ratios(self.fn, self.oldheader,
quantcols, denomcols, self.mediansweep, self.medianintensity,
self.median_or_avg, self.minint, peptides, self.header[0],
psmh.HEADER_PEPTIDE, totalproteome, tpacc, tp_pepacc,
self.logisoquant, self.mediannormalize, mn_factors, self.keepnapsms)
if self.modelqvals:
qix = self.header.index(peph.HEADER_QVAL) + 1
self.header = self.header[:qix] + [peph.HEADER_QVAL_MODELED] + self.header[qix:]
scorecol = tsvreader.get_cols_in_file(self.scorecolpattern,
self.oldheader, True)
peptides = psmtopeptable.recalculate_qvals_linear_model(peptides,
scorecol, self.qvalthreshold, self.minpeptidenr)
self.features = peptides