def load_spectra(spectra):
"""
"""
# currently ignore ident file input for spectra filtering
spectra, minMz, maxMz, validcharges, _ = load_spectra_ret_dict(spectra, 'all')
return spectra
##################################### start runDripExtract for multithreading
####################################################################################
# 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
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:
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 load_spectra(spectra):
"""
"""
# currently ignore ident file input for spectra filtering
spectra, minMz, maxMz, validcharges, _ = load_spectra_ret_dict(spectra, 'all')
return spectra