def psm(p, s0, c = 2, highResMs2 = False,
dripLearnedMeans = 'dripLearned.means',
dripLearnedCovars = 'dripLearned.covars',
mods = '', ntermMods = '', ctermMods = '', varModSequence = '',
precursor_filter = False,
high_res_gauss_dist = 0.05):
""" Inputs:
p = peptide string
s = observed spectrum, instance of class MS2Spectrum
c = psm charge
mods = static mods
ntermMods = static nterm-mods
ctermMods = static cterm-mods
"""
s = copy.deepcopy(s0)
args = dripGaussianCollectionNames()
sid = s.spectrum_id
# parse modifications
mods, varMods = parse_var_mods(mods, True)
ntermMods, ntermVarMods = parse_var_mods(ntermMods, False)
ctermMods, ctermVarMods = parse_var_mods(ctermMods, False)
if precursor_filter:
normalize = 'top300TightSequest'
else:
normalize = 'top300Sequest'
preprocess = pipeline(normalize)
preprocess(s)
# get original intensity values to plot
s0.mz = list(s.mz)
mz_vals = set(s.mz)
z = max(s0.intensity)
s0.intensity = [i/z for mz, i in zip(s0.mz, s0.intensity)
if mz in mz_vals]
num_psms = 1
max_obs_mass = 2001
dirBase = 'dtk'
# output_dir = os.path.abspath('dripEncode_' + dirBase)
output_dir = os.path.abspath('encode')
if not os.path.exists(output_dir):
os.mkdir(output_dir)
obs_dir = 'obs' # sub directory of output_dir
pfile_dir = os.path.join(output_dir, obs_dir)
if not os.path.exists(pfile_dir):
os.mkdir(pfile_dir)
# log_dir = os.path.abspath('dripLog_' + dirBase)
log_dir = os.path.abspath('log')
if not os.path.exists(log_dir):
os.mkdir(log_dir)
if not highResMs2:
dripMeans = load_drip_means(dripLearnedMeans)
if varMods or ntermVarMods or ctermVarMods:
assert varModSequence, "Variable mod enzyme options specified, but empty string denoting which amino acids are var mods supplied. Exitting"
bNy = interleave_b_y_ions_var_mods_lowres(Peptide(p), c,
mods, ntermMods, ctermMods,
varMods, varNtermMods, varCtermMods,
varModSequence)
else:
bNy = interleave_b_y_ions_lowres(Peptide(p), c, mods,
ntermMods, ctermMods)
l = len(bNy)
filter_theoretical_peaks_lowres(bNy,
dripMeans, s.mz[0], s.mz[-1])
else:
# calculate b- and y-ions, filter peaks outside of spectrum range
if varMods or ntermVarMods or ctermVarMods:
assert varModSequence, "Variable mod enzyme options specified, but empty string denoting which amino acids are var mods supplied. Exitting"
bNy = interleave_b_y_ions_var_mods(Peptide(p), c,
mods, ntermMods, ctermMods,
varMods, varNtermMods, varCtermMods,
varModSequence)
else:
bNy = interleave_b_y_ions(Peptide(p), c, mods,
ntermMods, ctermMods)
l = len(bNy)
filter_theoretical_peaks(bNy, s.mz[0], s.mz[-1], high_res_gauss_dist)
# now construct means based on this
dripMeans = {}
for i, ion in enumerate(bNy):
dripMeans[i] = ion
ion_to_index_map = {} # reverse mapping, from ions to indices
for ind in dripMeans:
ion_to_index_map[dripMeans[ind]] = ind
# make collection per spectrum
make_master_parameters_lowres(args, dripMeans)
peptide_obs_file = os.path.join(pfile_dir,'pep-lengths')
spectrum_obs_file = os.path.join(pfile_dir,'spectrum')
pep_dt = open(os.path.join(output_dir, 'iterable.dts'), "w")
pep_dt.write('%d\n\n' % (num_psms))
# write peptide database to parse and identify GMTK segments later
pepdb_list = open(os.path.join(output_dir, 'pepDB.txt'), "w")
pepdb_list.write("Kind\tSid\tPeptide\tNumBY\tCharge\n")
pep_num = 0
# create iterable dt and peptide pfile
peptide_sentence_flatascii(pep_dt, p, bNy,
pep_num, sid, max_obs_mass,
peptide_obs_file, True, len(bNy))
# create spectrum pfile
spectrum_sentence_flatascii(spectrum_obs_file, s.mz, s.intensity)
pepdb_list.write("t\t%d\t%s\t%d\t%d\n" % (sid,
p, l, c))
# close streams for this spectrum
pep_dt.close()
pepdb_list.close()
# compile dt using gmtkDTIndex
call(['gmtkDTindex', '-decisionTreeFiles',
os.path.join(output_dir,'iterable.dts')],
stdout = stdo, stderr = stde)
# stdout = sys.stderr, stderr = sys.stderr)
# create structure and master files then triangulate
try:
create_drip_structure(highResMs2, args.structure_file,
max_obs_mass, False, False,
high_res_gauss_dist)
except:
print "Could not create DRIP structure file %s, exitting" % args.structure_file
exit(-1)
try:
create_drip_master(highResMs2, args.master_file,
max_obs_mass,
"DRIP_MZ",
"drip_collection/covar.txt",
"DRIP_GAUSSIAN_COMPONENTS",
"DRIP_GAUSSIAN_MIXTURES",
"DRIP_MZ_GAUSSIANS")
except:
print "Could not create DRIP master file %s, exitting" % args.master_file
exit(-1)
try:
triangulate_drip(args.structure_file, args.master_file)
except:
print "Could not create triangulate structure file %s, exitting" % args.structure_file
exit(-1)
try:
write_covar_file(highResMs2, args.covar_file,
dripLearnedCovars, True,
high_res_gauss_dist)
except:
print "Could not create covariance file %s, exitting" % args.covar_file
exit(-1)
# run GMTK
dtFile = os.path.join(output_dir, 'iterable.dts')
cppCommand = '\'-DITERABLE_DT=' + dtFile \
+ ' -DDRIP_MZ=' + args.mean_file \
+ ' -DDRIP_GAUSSIAN_COMPONENTS=' + args.gauss_file \
+ ' -DDRIP_GAUSSIAN_MIXTURES=' + args.mixture_file \
+ ' -DDRIP_MZ_GAUSSIANS=' + args.collection_file \
+ '\''
# call gmtkViterbi
vitStr0 = "gmtkViterbi -strFile " + args.structure_file \
+ " -triFile " + args.structure_file + ".trifile -ni1 0 -nf1 2 -ni2 1 -nf2 0" \
+ " -fdiffact2 rl" \
+ " -inputMasterFile " + args.master_file + " -inputTrainableParameters trained.params -failOnZeroClique F"
# gmtkViterbi command line
vitValsFile = os.path.join(log_dir, 'vitVals.txt')
vitStr = vitStr0 + ' -vitValsFile ' + vitValsFile \
+ ' -of1 ' + spectrum_obs_file \
+ ' -fmt1 flatascii ' \
+ ' -of2 ' + peptide_obs_file \
+ ' -fmt2 flatascii ' \
+ ' -cppCommand ' + cppCommand
# call(shlex.split(vitStr), stdout = sys.stdout, stderr = sys.stdout)
call(shlex.split(vitStr), stdout = stdo, stderr = stde)
# parse output
t,d = ppsm.parse_dripExtract(vitValsFile, os.path.join(output_dir, 'pepDB.txt'))
t = t[sid,c][0]
# calculate insertions and deletions
t.add_obs_spectrum(s0)
t.calculate_drip_features(dripMeans)
t.calc_by_sets(c, mods,
ntermMods, ctermMods, highResMs2,
ion_to_index_map,
varMods, ntermVarMods, ctermVarMods,
varModSequence)
return t
exit(-1)
try:
create_drip_master(args.high_res_ms2, args.master_file,
args.max_obs_mass,
"DRIP_MZ",
"drip_collection/covar.txt",
"DRIP_GAUSSIAN_COMPONENTS",
"DRIP_GAUSSIAN_MIXTURES",
"DRIP_MZ_GAUSSIANS")
except:
print "Could not create DRIP structure file %s, exitting" % args.structure_file
exit(-1)
try:
triangulate_drip(args.structure_file, args.master_file)
except:
print "Could not create triangulate structure file %s, exitting" % args.structure_file
exit(-1)
try:
write_covar_file(args.high_res_ms2, args.covar_file,
args.learned_covars, True,
args.high_res_gauss_dist)
except:
print "Could not create covariance file %s, exitting" % args.covar_file
exit(-1)
# run GMTK
dtFile = os.path.join(args.output_dir, 'iterable.dts')
cppCommand = '\'-DITERABLE_DT=' + dtFile \
def runDripExtract(args, stdo, stde):
""" Run drip once per spectrum, collapsing all charge-varying candidates into a single GMTK call
"""
# create constant gmtkViterbi command line string
# don't need frame/segment difference actions since each PSM corresponds to a specific spectrum,
# so that there isn't much redudandancy to exploit
vitStr0 = "gmtkViterbi -strFile " + args.structure_file \
+ " -triFile " + args.structure_file + ".trifile -ni1 0 -nf1 2 -ni2 1 -nf2 0" \
+ " -fdiffact2 rl" \
+ " -inputMasterFile " + args.master_file + " -inputTrainableParameters trained.params -failOnZeroClique F"
# for now, don't worry about checking whether peptide is in valid (i.e., present in the digested
# set of peptide candidates given the protein database)
# currently ignore ident file input for spectra filtering
spectra, minMz, maxMz, validcharges, _ = load_spectra_ret_dict(args.spectra, args.charges)
# update encountered charges
args.charges = validcharges
args.mz_lb = minMz
args.mz_ub = maxMz
# create GMTK observation files
# add in support for cluster usage later; assume standalone with multithreading
if args.high_res_ms2:
spec_dict, num_psms = make_drip_data_highres(args, spectra, stdo, stde)
else:
spec_dict, num_psms = make_drip_data_lowres(args, spectra, stdo, stde)
pfile_dir = os.path.join(args.output_dir, args.obs_dir)
# create structure and master files then triangulate
try:
create_drip_structure(args.high_res_ms2, args.structure_file,
args.max_obs_mass, False, False,
args.high_res_gauss_dist)
except:
print "Could not create DRIP structure file %s, exitting" % args.structure_file
exit(-1)
try:
create_drip_master(args.high_res_ms2, args.master_file,
args.max_obs_mass,
"DRIP_MZ",
"drip_collection/covar.txt",
"DRIP_GAUSSIAN_COMPONENTS",
"DRIP_GAUSSIAN_MIXTURES",
"DRIP_MZ_GAUSSIANS")
except:
print "Could not create DRIP master file %s, exitting" % args.master_file
exit(-1)
try:
triangulate_drip(args.structure_file, args.master_file)
except:
print "Could not create triangulate structure file %s, exitting" % args.structure_file
exit(-1)
try:
write_covar_file(args.high_res_ms2, args.covar_file,
args.learned_covars, True,
args.high_res_gauss_dist)
except:
print "Could not create covariance file %s, exitting" % args.covar_file
exit(-1)
# run GMTK
dtFile = os.path.join(args.output_dir, 'iterable.dts')
cppCommand = '\'-DITERABLE_DT=' + dtFile \
+ ' -DDRIP_MZ=' + args.mean_file \
+ ' -DDRIP_GAUSSIAN_COMPONENTS=' + args.gauss_file \
+ ' -DDRIP_GAUSSIAN_MIXTURES=' + args.mixture_file \
+ ' -DDRIP_MZ_GAUSSIANS=' + args.collection_file \
+ '\''
# call gmtkViterbi
# gmtkViterbi command line
vitValsFile = os.path.join(args.logDir, 'vitVals.txt')
vitStr = vitStr0 + ' -vitValsFile ' + vitValsFile \
+ ' -of1 ' + pfile_dir + '/spectrum.pfile' \
+ ' -of2 ' + pfile_dir + '/pep-lengths.pfile' \
+ ' -cppCommand ' + cppCommand
call(shlex.split(vitStr), stdout = stdo, stderr = stde)
t,d = psm.parse_dripExtract(vitValsFile, os.path.join(args.output_dir, 'pepDB.txt'))
return t,d, spec_dict
def psm(p, s0, c = 2, highResMs2 = False,
dripLearnedMeans = 'dripLearned.means',
dripLearnedCovars = 'dripLearned.covars',
mods = '', ntermMods = '', ctermMods = '', varModSequence = '',
precursor_filter = False,
high_res_gauss_dist = 0.05):
""" Inputs:
p = peptide string
s = observed spectrum, instance of class MS2Spectrum
c = psm charge
mods = static mods
ntermMods = static nterm-mods
ctermMods = static cterm-mods
"""
s = copy.deepcopy(s0)
args = dripGaussianCollectionNames()
sid = s.spectrum_id
# parse modifications
mods, varMods = parse_var_mods(mods, True)
ntermMods, ntermVarMods = parse_var_mods(ntermMods, False)
ctermMods, ctermVarMods = parse_var_mods(ctermMods, False)
if precursor_filter:
normalize = 'top300TightSequest'
else:
normalize = 'top300Sequest'
preprocess = pipeline(normalize)
preprocess(s)
# get original intensity values to plot
s0.mz = list(s.mz)
mz_vals = set(s.mz)
z = max(s0.intensity)
s0.intensity = [i/z for mz, i in zip(s0.mz, s0.intensity)
if mz in mz_vals]
num_psms = 1
max_obs_mass = 2001
dirBase = 'dtk'
# output_dir = os.path.abspath('dripEncode_' + dirBase)
output_dir = os.path.abspath('encode')
if not os.path.exists(output_dir):
os.mkdir(output_dir)
obs_dir = 'obs' # sub directory of output_dir
pfile_dir = os.path.join(output_dir, obs_dir)
if not os.path.exists(pfile_dir):
os.mkdir(pfile_dir)
# log_dir = os.path.abspath('dripLog_' + dirBase)
log_dir = os.path.abspath('log')
if not os.path.exists(log_dir):
os.mkdir(log_dir)
if not highResMs2:
dripMeans = load_drip_means(dripLearnedMeans)
if varMods or ntermVarMods or ctermVarMods:
assert varModSequence, "Variable mod enzyme options specified, but empty string denoting which amino acids are var mods supplied. Exitting"
bNy = interleave_b_y_ions_var_mods_lowres(Peptide(p), c,
mods, ntermMods, ctermMods,
varMods, varNtermMods, varCtermMods,
varModSequence)
else:
bNy = interleave_b_y_ions_lowres(Peptide(p), c, mods,
ntermMods, ctermMods)
l = len(bNy)
filter_theoretical_peaks_lowres(bNy,
dripMeans, s.mz[0], s.mz[-1])
else:
# calculate b- and y-ions, filter peaks outside of spectrum range
if varMods or ntermVarMods or ctermVarMods:
assert varModSequence, "Variable mod enzyme options specified, but empty string denoting which amino acids are var mods supplied. Exitting"
bNy = interleave_b_y_ions_var_mods(Peptide(p), c,
mods, ntermMods, ctermMods,
varMods, varNtermMods, varCtermMods,
varModSequence)
else:
bNy = interleave_b_y_ions(Peptide(p), c, mods,
ntermMods, ctermMods)
l = len(bNy)
filter_theoretical_peaks(bNy, s.mz[0], s.mz[-1], high_res_gauss_dist)
# now construct means based on this
dripMeans = {}
for i, ion in enumerate(bNy):
dripMeans[i] = ion
ion_to_index_map = {} # reverse mapping, from ions to indices
for ind in dripMeans:
ion_to_index_map[dripMeans[ind]] = ind
# make collection per spectrum
make_master_parameters_lowres(args, dripMeans)
peptide_obs_file = os.path.join(pfile_dir,'pep-lengths')
spectrum_obs_file = os.path.join(pfile_dir,'spectrum')
pep_dt = open(os.path.join(output_dir, 'iterable.dts'), "w")
pep_dt.write('%d\n\n' % (num_psms))
# write peptide database to parse and identify GMTK segments later
pepdb_list = open(os.path.join(output_dir, 'pepDB.txt'), "w")
pepdb_list.write("Kind\tSid\tPeptide\tNumBY\tCharge\n")
pep_num = 0
# create iterable dt and peptide pfile
peptide_sentence_flatascii(pep_dt, p, bNy,
pep_num, sid, max_obs_mass,
peptide_obs_file, True, len(bNy))
# create spectrum pfile
spectrum_sentence_flatascii(spectrum_obs_file, s.mz, s.intensity)
pepdb_list.write("t\t%d\t%s\t%d\t%d\n" % (sid,
p, l, c))
# close streams for this spectrum
pep_dt.close()
pepdb_list.close()
# compile dt using gmtkDTIndex
call(['gmtkDTindex', '-decisionTreeFiles',
os.path.join(output_dir,'iterable.dts')],
stdout = stdo, stderr = stde)
# stdout = sys.stderr, stderr = sys.stderr)
# create structure and master files then triangulate
try:
create_drip_structure(highResMs2, args.structure_file,
max_obs_mass, False, False,
high_res_gauss_dist)
except:
print "Could not create DRIP structure file %s, exitting" % args.structure_file
exit(-1)
try:
create_drip_master(highResMs2, args.master_file,
max_obs_mass,
"DRIP_MZ",
"drip_collection/covar.txt",
"DRIP_GAUSSIAN_COMPONENTS",
"DRIP_GAUSSIAN_MIXTURES",
"DRIP_MZ_GAUSSIANS")
except:
print "Could not create DRIP master file %s, exitting" % args.master_file
exit(-1)
try:
triangulate_drip(args.structure_file, args.master_file)
except:
print "Could not create triangulate structure file %s, exitting" % args.structure_file
exit(-1)
try:
write_covar_file(highResMs2, args.covar_file,
dripLearnedCovars, True,
high_res_gauss_dist)
except:
print "Could not create covariance file %s, exitting" % args.covar_file
exit(-1)
# run GMTK
dtFile = os.path.join(output_dir, 'iterable.dts')
cppCommand = '\'-DITERABLE_DT=' + dtFile \
+ ' -DMAX_FRAGMENT_MASS=' + str(max_obs_mass) \
+ ' -DDRIP_MZ=' + args.mean_file \
+ ' -DDRIP_GAUSSIAN_COMPONENTS=' + args.gauss_file \
+ ' -DDRIP_GAUSSIAN_MIXTURES=' + args.mixture_file \
+ ' -DDRIP_MZ_GAUSSIANS=' + args.collection_file \
+ '\''
# call gmtkViterbi
vitStr0 = "gmtkViterbi -strFile " + args.structure_file \
+ " -triFile " + args.structure_file + ".trifile -ni1 0 -nf1 2 -ni2 1 -nf2 0" \
+ " -fdiffact2 rl" \
+ " -inputMasterFile " + args.master_file + " -inputTrainableParameters trained.params -failOnZeroClique F"
# gmtkViterbi command line
vitValsFile = os.path.join(log_dir, 'vitVals.txt')
vitStr = vitStr0 + ' -vitValsFile ' + vitValsFile \
+ ' -of1 ' + spectrum_obs_file \
+ ' -fmt1 flatascii ' \
+ ' -of2 ' + peptide_obs_file \
+ ' -fmt2 flatascii ' \
+ ' -cppCommand ' + cppCommand
# call(shlex.split(vitStr), stdout = sys.stdout, stderr = sys.stdout)
call(shlex.split(vitStr), stdout = stdo, stderr = stde)
# parse output
t,d = ppsm.parse_dripExtract(vitValsFile, os.path.join(output_dir, 'pepDB.txt'))
t = t[sid,c][0]
# calculate insertions and deletions
t.add_obs_spectrum(s0)
t.calculate_drip_features(dripMeans)
t.calc_by_sets(c, mods,
ntermMods, ctermMods, highResMs2,
ion_to_index_map,
varMods, ntermVarMods, ctermVarMods,
varModSequence)
return t