def main():
#Read command line options
opt = parse_args()
if opt.logo:
ccmpred.logo.logo()
#set OMP environment variable for number of threads
os.environ['OMP_NUM_THREADS'] = str(opt.num_threads)
print("Using {0} threads for OMP parallelization.".format(
os.environ["OMP_NUM_THREADS"]))
ccm = CCMpred(opt.alnfile, opt.matfile)
##############################
### Setup
##############################
#read alignment and compute amino acid counts and frequencies
ccm.read_alignment(opt.aln_format, opt.max_gap_ratio)
ccm.compute_sequence_weights(opt.weight, opt.wt_ignore_gaps, opt.wt_cutoff)
ccm.compute_frequencies(opt.pseudocounts, opt.pseudocount_single,
opt.pseudocount_pair)
#if alternative scores are specified: compute these and exit
if opt.omes:
ccm.compute_omes(opt.omes_fodoraldrich)
ccm.write_matrix()
sys.exit(0)
if opt.mi:
ccm.compute_mutual_info(opt.mi_normalized, opt.mi_pseudocounts)
ccm.write_matrix()
sys.exit(0)
#setup L2 regularization
ccm.specify_regularization(opt.lambda_single,
opt.lambda_pair_factor,
reg_type=opt.reg_type,
scaling=opt.scaling)
#intialise single and pair potentials either:
# - according to regularization priors
# - from file
ccm.intialise_potentials(opt.initrawfile)
##############################
### Optimize objective function (pLL or CD) with optimization algorithm (CG, GD or ADAM)
##############################
if opt.optimize:
# specify objective function
objfun = OBJ_FUNC[opt.objfun](opt, ccm)
# specify optimizer
alg = ALGORITHMS[opt.algorithm](opt, ccm)
#minimize objective function with optimizer
ccm.minimize(objfun, alg)
else:
print(
"\nDo not optimize but load couplings from binary raw file {0}\n".
format(opt.initrawfile))
##############################
### Post Processing
##############################
# Compute contact score (frobenius norm) by possibly recentering potentials
# TODO: other scores can be added ...
ccm.compute_contact_matrix(recenter_potentials=opt.centering_potentials,
frob=opt.frob)
# and bias correction to contact score
ccm.compute_correction(apc=opt.apc,
entropy_correction=opt.entropy_correction)
#specify meta data, and write (corrected) contact matrices to files
ccm.write_matrix()
if opt.cd_alnfile and hasattr(ccm.f, 'msa_sampled'):
ccm.write_sampled_alignment(opt.cd_alnfile)
if opt.out_binary_raw_file:
ccm.write_binary_raw(opt.out_binary_raw_file)
exitcode = 0
if opt.optimize:
if ccm.algret['code'] < 0:
exitcode = -ccm.algret['code']
sys.exit(exitcode)
def main():
# read command line options
opt = parse_args()
# print logo
if opt.logo:
ccmpred.logo.logo()
# set OMP environment variable for number of threads
os.environ['OMP_NUM_THREADS'] = str(opt.num_threads)
print("Using {0} threads for OMP parallelization.".format(
os.environ["OMP_NUM_THREADS"]))
# instantiate CCMpred
ccm = CCMpred()
# specify possible file paths
ccm.set_alignment_file(opt.alnfile)
ccm.set_matfile(opt.matfile)
ccm.set_pdb_file(opt.pdbfile)
ccm.set_initraw_file(opt.initrawfile)
# read alignment and possible remove gapped sequences and positions
ccm.read_alignment(opt.aln_format, opt.max_gap_pos, opt.max_gap_seq)
# compute sequence weights (in order to reduce sampling bias)
ccm.compute_sequence_weights(opt.weight, opt.wt_cutoff)
# compute amino acid counts and frequencies adding pseudo counts for non-observed amino acids
ccm.compute_frequencies(opt.pseudocounts, opt.pseudocount_single,
opt.pseudocount_pair)
# read pdb file if CCMpred is setup as a constrained run
if opt.pdbfile:
ccm.read_pdb(opt.contact_threshold)
# if alternative scores are specified: compute these and exit
if opt.omes:
ccm.compute_omes(opt.omes_fodoraldrich)
ccm.write_matrix()
sys.exit(0)
if opt.mi:
ccm.compute_mutual_info(opt.mi_normalized, opt.mi_pseudocounts)
ccm.write_matrix()
sys.exit(0)
# setup L2 regularization
ccm.specify_regularization(opt.lambda_single,
opt.lambda_pair_factor,
reg_type="L2",
scaling="L",
single_prior=opt.single_prior)
# intialise single and pair potentials either:
# - according to regularization priors
# - from initrawfile (accounting for removal of many gapped positions, if applicable)
ccm.intialise_potentials()
# optimize objective function (pLL or CD/PCD) with optimization algorithm (LBFGS, CG, GD or ADAM)
if opt.optimize:
#initialize log object
ccm.initiate_logging(opt.plot_opt_progress)
#minimize objective function with corresponding optimization algorithm
ccm.minimize(opt)
else:
print("\nDo not optimize but use model parameters provided by {0}\n".
format(opt.initrawfile))
### Post Processing
#specify meta data, and write (corrected) contact matrices to files
if opt.matfile:
# Compute contact score (frobenius norm) by recentering potentials
# TODO: other scores can be added ...
ccm.compute_contact_matrix(recenter_potentials=True, frob=True)
# compute corrected contact maps (removing entropy/phylogenetic biases)
# TODO: other corrections can be added ...
ccm.compute_correction(
apc_file=opt.apc_file,
entropy_correction_file=opt.entropy_correction_file)
ccm.write_matrix()
# write model parameters in binary format
if opt.out_binary_raw_file:
ccm.write_binary_raw(opt.out_binary_raw_file)
exitcode = 0
if opt.optimize:
if ccm.algret['code'] < 0:
exitcode = -ccm.algret['code']
sys.exit(exitcode)
def main(alnfile,outfile,pair_mat):
# read command line options
# print logo
ccmpred.logo.logo()
# set OMP environment variable for number of threads
os.environ['OMP_NUM_THREADS'] = str(opt.num_threads)
print("Using {0} threads for OMP parallelization.".format(os.environ["OMP_NUM_THREADS"]))
# instantiate CCMpred
ccm = CCMpred()
# specify possible file paths
ccm.set_alignment_file(alnfile)
ccm.set_matfile(oufile+'.ccmraw')
# read alignment and possible remove gapped sequences and positions
ccm.read_alignment()
# compute sequence weights (in order to reduce sampling bias)
ccm.compute_sequence_weights("simple", 0.8)
# compute amino acid counts and frequencies adding pseudo counts for non-observed amino acids
ccm.compute_frequencies("uniform_pseudocounts")
# setup L2 regularization
ccm.specify_regularization(10, 0.2,pair_mat)
# intialise single and pair potentials either:
# - according to regularization priors
# - from initrawfile (accounting for removal of many gapped positions, if applicable)
ccm.intialise_potentials()
# optimize objective function (pLL or CD/PCD) with optimization algorithm (LBFGS, CG, GD or ADAM)
#initialize log object
ccm.initiate_logging()
#minimize objective function with corresponding optimization algorithm
ccm.minimize()
### Post Processing
#specify meta data, and write (corrected) contact matrices to files
# Compute contact score (frobenius norm) by recentering potentials
# TODO: other scores can be added ...
ccm.compute_contact_matrix(recenter_potentials=True, frob=True)
# compute corrected contact maps (removing entropy/phylogenetic biases)
# TODO: other corrections can be added ...
ccm.compute_correction(
apc_file=outfile,
entropy_correction_file=None
)
ccm.write_matrix()
# write model parameters in binary format
exitcode = 0
if ccm.algret['code'] < 0:
exitcode =-ccm.algret['code']
sys.exit(exitcode)