def main():
parser = argparse.ArgumentParser(description="Nano-Align protein "
"identification", formatter_class= \
argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument("blockades_file", metavar="blockades_file",
help="path to blockades file (in mat format)")
parser.add_argument("model_file", metavar="model_file",
help="path to trained model file ('-' for MV model)")
parser.add_argument("-c", "--cluster-size", dest="cluster_size", type=int,
default=10, help="blockades cluster size")
parser.add_argument("-d", "--database", dest="database",
metavar="database", help="database file (in FASTA "
"format). If not set, random database is generated",
default=None)
parser.add_argument("-s", "--single-blockades", action="store_true",
default=False, dest="single_blockades",
help="print statistics for each blockade in a cluster")
parser.add_argument("--version", action="version", version=__version__)
args = parser.parse_args()
model = load_model(args.model_file)
pvalues_test(args.blockades_file, args.cluster_size, model,
args.database, args.single_blockades, sys.stderr)
return 0
def main():
parser = argparse.ArgumentParser(description="Nano-Align protein "
"identification", formatter_class= \
argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument("nanospectra_file",
metavar="nanospectra_file",
help="path to nanospectra file (in mat format)")
parser.add_argument("model_file",
metavar="model_file",
help="path to trained model file ('-' for MV model)")
parser.add_argument("-c",
"--cluster-size",
dest="cluster_size",
type=int,
default=10,
help="blockades cluster size")
parser.add_argument("-d",
"--database",
dest="database",
metavar="database",
help="database file (in FASTA "
"format). If not set, random database is generated",
default=None)
parser.add_argument(
"-s",
"--single-nanospectra",
action="store_true",
default=False,
dest="single_nanospectra",
help="print statistics for each nanospectra in a cluster")
parser.add_argument("--version", action="version", version=__version__)
args = parser.parse_args()
model = load_model(args.model_file)
pvalues_test(args.nanospectra_file, args.cluster_size, model,
args.database, args.single_nanospectra, sys.stderr)
return 0
def full_identify(blockades_file, model_file, db_file):
"""
Computes pvalues
"""
blockade_model = load_model(model_file)
#svr_model = SvrBlockade()
#svr_model.load_from_pickle(svr_file)
boxes = []
for avg in xrange(1, 21):
p_values = []
for _ in xrange(avg):
p_value, rank = pvalues_test(blockades_file, avg, blockade_model,
db_file, False, open(os.devnull, "w"))
p_values.append(p_value)
boxes.append(p_values)
print(avg, np.median(p_values), file=sys.stderr)
plot_pvalues(boxes)
def full_identify(blockades_file, model_file, db_file):
"""
Computes pvalues
"""
blockade_model = load_model(model_file)
#svr_model = SvrBlockade()
#svr_model.load_from_pickle(svr_file)
boxes = []
for avg in xrange(1, 21):
p_values = []
for _ in xrange(avg):
p_value, rank = pvalues_test(blockades_file, avg, blockade_model, db_file,
False, open(os.devnull, "w"))
p_values.append(p_value)
boxes.append(p_values)
print(avg, np.median(p_values), file=sys.stderr)
plot_pvalues(boxes)
def _cross_validate(train_mats, cv_mats, db_file, out_file):
"""
Choosing the best parameters through cross-validation
"""
CLUSTER_SIZE = 10
eps_vec = [0.01, 0.001, 0.0001, 0.00001]
C_vec = [1, 10, 100, 1000, 10000, 100000]
gamma_vec = [0.00001, 0.0001, 0.001, 0.01, 0.1, 1]
best_score = sys.maxint
best_params = None
print("C\tGam\tEps\tScore", file=sys.stderr)
for C in C_vec:
for gamma in gamma_vec:
for eps in eps_vec:
temp_model = _train_svr(train_mats, C, gamma, eps)
scores = []
for cv_mat in cv_mats:
pval, rank = pvalues_test(cv_mat, CLUSTER_SIZE, temp_model,
db_file, False,
open(os.devnull, "w"))
scores.append(rank)
score = np.mean(scores)
print("{0}\t{1}\t{2}\t{3}".format(C, gamma, eps, score),
file=sys.stderr)
if score < best_score:
best_score = score
best_params = (C, gamma, eps)
print(*best_params, file=sys.stderr)
best_model = _train_svr(train_mats, *best_params)
store_model(best_model, out_file)
def _cross_validate(train_mats, cv_mats, db_file, out_file):
"""
Choosing the best parameters through cross-validation
"""
CLUSTER_SIZE = 10
eps_vec = [0.01, 0.001, 0.0001, 0.00001]
C_vec = [1, 10, 100, 1000, 10000, 100000]
gamma_vec = [0.00001, 0.0001, 0.001, 0.01, 0.1, 1]
best_score = sys.maxint
best_params = None
print("C\tGam\tEps\tScore", file=sys.stderr)
for C in C_vec:
for gamma in gamma_vec:
for eps in eps_vec:
temp_model = _train_svr(train_mats, C, gamma, eps)
scores = []
for cv_mat in cv_mats:
pval, rank = pvalues_test(cv_mat, CLUSTER_SIZE, temp_model,
db_file, False,
open(os.devnull, "w"))
scores.append(rank)
score = np.mean(scores)
print("{0}\t{1}\t{2}\t{3}".format(C, gamma, eps, score),
file=sys.stderr)
if score < best_score:
best_score = score
best_params = (C, gamma, eps)
print(*best_params, file=sys.stderr)
best_model = _train_svr(train_mats, *best_params)
store_model(best_model, out_file)