def main(args):
# Set revcomp parameter.
if args.r != 1:
args.r = False
elif args.r == 1 and args.alphabet != 'DNA':
print("Error, the -r parameter can only be used in DNA.")
elif args.r == 1 and args.alphabet == 'DNA':
args.r = True
# Set alphabet parameter.
if args.alphabet == 'DNA':
args.alphabet = index_list.DNA
elif args.alphabet == 'RNA':
args.alphabet = index_list.RNA
elif args.alphabet == 'Protein':
args.alphabet = index_list.PROTEIN
res = make_kmer_vector(k=args.k, alphabet=args.alphabet, filename=args.inputfile, revcomp=args.r)
# Write correspond res file.
if args.f == 'svm':
from util import write_libsvm
write_libsvm(res, [args.l] * len(res), args.outputfile)
elif args.f == 'tab':
from util import write_tab
write_tab(res, args.outputfile)
elif args.f == 'csv':
from util import write_csv
write_csv(res, args.outputfile)
def main(args):
# Set revcomp parameter.
if args.r != 1:
args.r = False
elif args.r == 1 and args.alphabet != 'DNA':
print("Error, the -r parameter can only be used in DNA.")
elif args.r == 1 and args.alphabet == 'DNA':
args.r = True
# Set alphabet parameter.
if args.alphabet == 'DNA':
args.alphabet = index_list.DNA
elif args.alphabet == 'RNA':
args.alphabet = index_list.RNA
elif args.alphabet == 'Protein':
args.alphabet = index_list.PROTEIN
res = make_kmer_vector(k=args.k, alphabet=args.alphabet, filename=args.inputfile, revcomp=args.r)
# Write correspond res file.
if args.f == 'svm':
from util import write_libsvm
write_libsvm(res, [args.l] * len(res), args.outputfile)
elif args.f == 'tab':
from util import write_tab
write_tab(res, args.outputfile)
elif args.f == 'csv':
from util import write_csv
write_csv(res, args.outputfile)
def main(args):
#TODO:args.method will be finished
#TODO:args.inputfile, name
if args.alphabet == "RNA":
if args.method.upper() == 'TRIPLET':
res = get_triplet_matrix(args.inputfile)
elif args.method.upper() == 'PSESSC':
if args.k is None:
print "parameters k is required. The default value of k is 2."
args.k = 2
if args.r is None:
print "parameters r is required. The default value of r is 2."
args.r = 2
if args.w is None:
print "parameters w is required. The default value of w is 0.1."
args.w = 0.1
res = get_psessc_matrix(args.inputfile, args.k, args.r, args.w)
elif args.method.upper() == 'PSEDPC':
if args.n is None:
print "parameters n is required. The default value of d is 0."
args.n = 0
if args.r is None:
print "parameters r is required. The default value of r is 2."
args.r = 2
if args.w is None:
print "parameters w is required. The default value of w is 0.1."
args.w = 0.1
res = get_psedpc_matrix(args.inputfile, args.n, args.r, args.w)
else:
print("Method error!")
else:
print("sequence type error!")
# Write correspond res file.
if args.f == 'tab':
from util import write_tab
write_tab(res, args.outputfile)
elif args.f == 'svm':
if args.multi == 0 and args.l is None:
args.l = '+1'
elif args.multi == 0 and (args.l != '+1' and args.l != '-1'):
print "For binary classification, the label should be either '+1' or '-1'."
return False
elif args.multi == 1 and args.l is None:
args.l = '0'
elif args.multi == 1 and args.l is not None:
try:
label = int(args.l)
except ValueError:
print 'The labels should be integer.'
return False
from util import write_libsvm
write_libsvm(res, [args.l] * len(res), args.outputfile)
elif args.f == 'csv':
from util import write_csv
write_csv(res, args.outputfile)
def main(args):
with open(args.inputfile) as f:
k = read_k(args.alphabet, args.method, 0)
# Get index_list.
if args.i is not None:
from pse import read_index
ind_list = read_index(args.i)
else:
ind_list = []
default_e = []
# Set Pse default index_list.
if args.alphabet == 'DNA':
args.alphabet = index_list.DNA
if k == 2:
default_e = const.DI_INDS_6_DNA
elif k == 3:
default_e = const.TRI_INDS_DNA
elif args.alphabet == 'RNA':
args.alphabet = index_list.RNA
default_e = const.DI_INDS_RNA
elif args.alphabet == 'Protein':
args.alphabet = index_list.PROTEIN
default_e = const.INDS_3_PROTEIN
theta_type = 1
if args.method in const.METHODS_AC:
theta_type = 1
elif args.method in const.METHODS_CC:
theta_type = 2
elif args.method in const.METHODS_ACC:
theta_type = 3
else:
print("Method error!")
# ACC.
if args.e is None and len(ind_list) == 0 and args.a is False:
# Default Pse.
res = acc(f, k, args.lag, default_e, args.alphabet,
extra_index_file=args.e, all_prop=args.a, theta_type=theta_type)
else:
res = acc(f, k, args.lag, ind_list, args.alphabet,
extra_index_file=args.e, all_prop=args.a, theta_type=theta_type)
# Write correspond res file.
if args.f == 'tab':
from util import write_tab
write_tab(res, args.outputfile)
elif args.f == 'svm':
from util import write_libsvm
write_libsvm(res, [args.l] * len(res), args.outputfile)
elif args.f == 'csv':
from util import write_csv
write_csv(res, args.outputfile)
def main(args):
#TODO:args.method will be finished
#TODO:args.inputfile, name
if args.alphabet == "RNA":
if args.method.upper() == 'TRIPLET':
res = get_triplet_matrix(args.inputfile)
elif args.method.upper() == 'PSESSC':
if args.k is None:
print "parameters k is required. The default value of k is 2."
args.k = 2
if args.r is None:
print "parameters r is required. The default value of r is 2."
args.r = 2
if args.w is None:
print "parameters w is required. The default value of w is 0.1."
args.w = 0.1
res = get_psessc_matrix(args.inputfile, args.k, args.r, args.w)
elif args.method.upper() == 'PSEDPC':
if args.n is None:
print "parameters n is required. The default value of d is 0."
args.n = 0
if args.r is None:
print "parameters r is required. The default value of r is 2."
args.r = 2
if args.w is None:
print "parameters w is required. The default value of w is 0.1."
args.w = 0.1
res = get_psedpc_matrix(args.inputfile, args.n, args.r, args.w)
else:
print("Method error!")
else:
print("sequence type error!")
# Write correspond res file.
if args.f == 'tab':
from util import write_tab
write_tab(res, args.outputfile)
elif args.f == 'svm':
from util import write_libsvm
write_libsvm(res, [args.l] * len(res), args.outputfile)
elif args.f == 'csv':
from util import write_csv
write_csv(res, args.outputfile)
def main(args):
with open(args.inputfile) as f:
# Get index_list.
if args.i is not None:
ind_list = read_index(args.i)
else:
ind_list = []
default_e = []
# Set Pse default index_list.
if args.alphabet == 'DNA':
args.alphabet = index_list.DNA
if args.k == 2:
default_e = const.DI_INDS_6_DNA
elif args.k == 3:
default_e = const.TRI_INDS_DNA
elif args.alphabet == 'RNA':
args.alphabet = index_list.RNA
default_e = const.DI_INDS_RNA
elif args.alphabet == 'Protein':
args.alphabet = index_list.PROTEIN
default_e = const.INDS_3_PROTEIN
theta_type = 1
if args.method in const.THETA_1_METHODS:
theta_type = 1
elif args.method in const.THETA_2_METHODS:
theta_type = 2
elif args.method == 'PseKNC':
theta_type = 3
else:
print("Method error!")
# PseKNC.
if args.method != 'PseKNC':
if args.e is None and len(ind_list) == 0 and args.a is False:
# Default Pse.
res = pseknc(f, args.k, args.w, args.lamada, default_e, args.alphabet,
extra_index_file=args.e, all_prop=args.a, theta_type=theta_type)
else:
res = pseknc(f, args.k, args.w, args.lamada, ind_list, args.alphabet,
extra_index_file=args.e, all_prop=args.a, theta_type=theta_type)
# iPseKNC.
else:
if args.e is None and len(ind_list) == 0 and args.a is False:
# Default iPse.
res = ipseknc(f, args.k, args.w, args.lamada, const.DI_INDS_6_DNA, args.alphabet,
extra_index_file=args.e, all_prop=args.a)
else:
res = ipseknc(f, args.k, args.w, args.lamada, ind_list, args.alphabet,
extra_index_file=args.e, all_prop=args.a)
# Write correspond res file.
if args.f == 'tab':
from util import write_tab
write_tab(res, args.outputfile)
elif args.f == 'svm':
from util import write_libsvm
write_libsvm(res, [args.l] * len(res), args.outputfile)
elif args.f == 'csv':
from util import write_csv
write_csv(res, args.outputfile)
def main(args):
# Set revcomp parameter.
if args.r != 1:
args.r = False
elif args.r == 1 and args.alphabet != 'DNA':
print("Error, the -r parameter can only be used in DNA.")
elif args.r == 1 and args.alphabet == 'DNA':
args.r = True
# Set alphabet parameter.
if args.alphabet == 'DNA':
args.alphabet = index_list.DNA
elif args.alphabet == 'RNA':
args.alphabet = index_list.RNA
elif args.alphabet == 'Protein':
args.alphabet = index_list.PROTEIN
if args.method.upper() == 'KMER':
if args.k is None:
print "parameters k is required. The default value of k is 2."
args.k = 2
if args.r is None:
print "parameters r is required. The default value of r is 0."
args.r = 0
res = make_kmer_vector(k=args.k, alphabet=args.alphabet, filename=args.inputfile, revcomp=args.r)
elif args.method.upper() == 'IDKMER':
if args.k is None:
print "parameters k is required. The default value of k is 6."
args.k = 6
if args.ps is None or args.ns is None:
print 'The positive and the negative source files are required.'
return False
res = idkmer(k=args.k, filename=args.inputfile, pos_src_name=args.ps, neg_src_name=args.ns)
elif args.method.upper() == "MISMATCH":
if args.k is None:
print "parameters k is required. The default value of k is 3."
args.k = 3
if args.m is None:
print "parameters m is required. The default value of m is 1."
args.m = 1
if args.m >= args.k:
print "parameters m should be less than parameter k."
else:
res = getMismatchProfileMatrix(args.inputfile, args.alphabet, args.k, args.m)
elif args.method.upper() == "SUBSEQUENCE":
if args.delta is None:
print "parameters delta is required. The default value of delta is 1."
args.delta = 1
elif args.delta > 1 or args.delta < 0:
print "delta should be greater than or equal to 0 and less than or equal to 1."
if args.k is None:
print "parameters k is required. The default value of k is 3."
args.k = 3
res = getSubsequenceProfileByParallel(filename=args.inputfile, alphabet=args.alphabet, k=args.k, delta=args.delta)
elif args.method.upper() == 'DR':
if args.alphabet != index_list.PROTEIN:
print 'DR method is only available for Protein.'
return False
elif args.max_dis < 0 or args.max_dis > 10:
print 'The max distance can not be negative integer and should be smaller than 11.'
return False
else:
res = dr_method(inputfile=args.inputfile, max_dis=args.max_dis)
print res
elif args.method.upper() == 'DP':
if args.alphabet != index_list.PROTEIN:
print 'Distance Pair method is only available for Protein.'
return False
elif args.max_dis < 0 or args.max_dis > 10:
print 'The max distance can not be negative integer and should be smaller than 11.'
return False
else:
if args.cp == 'cp_13':
reduce_alphabet_scheme = const.cp_13
elif args.cp == 'cp_14':
reduce_alphabet_scheme = const.cp_14
elif args.cp == 'cp_19':
reduce_alphabet_scheme = const.cp_19
elif args.cp == 'cp_20':
reduce_alphabet_scheme = const.cp_20
res = get_pseaacdis_matrix(filename=args.inputfile, reduce_alphabet_scheme=reduce_alphabet_scheme,
max_distance=args.max_dis, alphabet=args.alphabet)
else:
print("Method error!")
# Write correspond res file.
if args.f == 'svm':
if args.multi == 0 and args.l is None:
args.l = '+1'
elif args.multi == 0 and (args.l != '+1' and args.l != '-1'):
print "For binary classification, the label should be either '+1' or '-1'."
return False
elif args.multi == 1 and args.l is None:
args.l = '0'
elif args.multi == 1 and args.l is not None:
try:
label = int(args.l)
except ValueError:
print 'The labels should be integer.'
return False
from util import write_libsvm
write_libsvm(res, [args.l] * len(res), args.outputfile)
elif args.f == 'tab':
from util import write_tab
write_tab(res, args.outputfile)
elif args.f == 'csv':
from util import write_csv
write_csv(res, args.outputfile)
def main(args):
with open(args.inputfile) as f:
k = read_k(args.alphabet, args.method, 0)
# Get index_list.
if args.i is not None:
from pse import read_index
ind_list = read_index(args.i)
else:
ind_list = []
default_e = []
# Set Pse default index_list.
if args.alphabet == "DNA":
args.alphabet = index_list.DNA
if k == 2:
default_e = const.DI_INDS_6_DNA
elif k == 3:
default_e = const.TRI_INDS_DNA
elif args.alphabet == "RNA":
args.alphabet = index_list.RNA
default_e = const.DI_INDS_RNA
elif args.alphabet == "Protein":
args.alphabet = index_list.PROTEIN
default_e = const.INDS_3_PROTEIN
theta_type = 1
if args.method in const.METHODS_AC:
theta_type = 1
elif args.method in const.METHODS_CC:
theta_type = 2
elif args.method in const.METHODS_ACC:
theta_type = 3
else:
print("Method error!")
# ACC.
if args.e is None and len(ind_list) == 0 and args.a is False:
# Default Pse.
res = acc(
f,
k,
args.lag,
default_e,
args.alphabet,
extra_index_file=args.e,
all_prop=args.a,
theta_type=theta_type,
)
else:
res = acc(
f, k, args.lag, ind_list, args.alphabet, extra_index_file=args.e, all_prop=args.a, theta_type=theta_type
)
# Write correspond res file.
if args.f == "tab":
from util import write_tab
write_tab(res, args.outputfile)
elif args.f == "svm":
from util import write_libsvm
write_libsvm(res, [args.l] * len(res), args.outputfile)
elif args.f == "csv":
from util import write_csv
write_csv(res, args.outputfile)
def main(args):
with open(args.inputfile) as f:
if args.method.upper() not in ['MAC', 'GAC', 'NMBAC']:
k = read_k(args.alphabet, args.method, 0)
# Get index_list.
if args.i is not None:
from .pse import read_index
ind_list = read_index(args.i)
else:
ind_list = []
default_e = []
# Set Pse default index_list.
if args.alphabet == 'DNA':
args.alphabet = index_list.DNA
if k == 2:
default_e = const.DI_INDS_6_DNA
elif k == 3:
default_e = const.TRI_INDS_DNA
elif args.alphabet == 'RNA':
args.alphabet = index_list.RNA
default_e = const.DI_INDS_RNA
elif args.alphabet == 'Protein':
args.alphabet = index_list.PROTEIN
default_e = const.INDS_3_PROTEIN
theta_type = 1
if args.method in const.METHODS_AC:
theta_type = 1
elif args.method in const.METHODS_CC:
theta_type = 2
elif args.method in const.METHODS_ACC:
theta_type = 3
else:
print("Method error!")
# ACC.
if args.e is None and len(ind_list) == 0 and args.a is False:
# Default Pse.
res = acc(f,
k,
args.lag,
default_e,
args.alphabet,
extra_index_file=args.e,
all_prop=args.a,
theta_type=theta_type)
else:
res = acc(f,
k,
args.lag,
ind_list,
args.alphabet,
extra_index_file=args.e,
all_prop=args.a,
theta_type=theta_type)
if args.method.upper() in ['MAC', 'GAC', 'NMBAC']:
if args.lamada < 0 or args.lamada > 10:
print(
'The value of lamada should be larger than 0 and smaller than 10.'
)
return False
if args.a is None:
args.a == False
elif args.alphabet == 'DNA':
args.alphabet = index_list.DNA
if args.oli == 0:
if args.a == True:
res = autocorrelation(autoc=args.method,
inputfile=args.inputfile,
props=const.ALL_DI_DNA_IND,
k=2,
l=args.lamada,
alphabet=args.alphabet)
elif args.a == False:
res = autocorrelation(autoc=args.method,
inputfile=args.inputfile,
props=const.DEFAULT_DI_DNA_IND,
k=2,
l=args.lamada,
alphabet=args.alphabet)
if args.oli == 1:
if args.a == True:
res = autocorrelation(autoc=args.method,
inputfile=args.inputfile,
props=const.ALL_TRI_DNA_IND,
k=3,
l=args.lamada,
alphabet=args.alphabet)
elif args.a == False:
res = autocorrelation(autoc=args.method,
inputfile=args.inputfile,
props=const.DEFAULT_TRI_DNA_IND,
k=3,
l=args.lamada,
alphabet=args.alphabet)
elif args.alphabet == 'RNA':
args.alphabet = index_list.RNA
if args.a == True:
res = autocorrelation(autoc=args.method,
inputfile=args.inputfile,
props=const.ALL_RNA_IND,
k=2,
l=args.lamada,
alphabet=args.alphabet)
elif args.a == False:
res = autocorrelation(autoc=args.method,
inputfile=args.inputfile,
props=const.DEFAULT_RNA_IND,
k=2,
l=args.lamada,
alphabet=args.alphabet)
#print res
# Write correspond res file.
if args.f == 'tab':
from util import write_tab
write_tab(res, args.outputfile)
elif args.f == 'svm':
if args.multi == 0 and args.l is None:
args.l = '+1'
elif args.multi == 0 and (args.l != '+1' and args.l != '-1'):
print(
"For binary classification, the label should be either '+1' or '-1'."
)
return False
elif args.multi == 1 and args.l is None:
args.l = '0'
elif args.multi == 1 and args.l is not None:
try:
label = int(args.l)
except ValueError:
print('The labels should be integer.')
return False
from util import write_libsvm
write_libsvm(res, [args.l] * len(res), args.outputfile)
elif args.f == 'csv':
from util import write_csv
write_csv(res, args.outputfile)
def main(args):
with open(args.inputfile) as f:
# Get index_list.
if args.i is not None:
ind_list = read_index(args.i)
else:
ind_list = []
default_e = []
# Set Pse default index_list.
if args.alphabet == 'DNA':
args.alphabet = index_list.DNA
if args.k == 2:
default_e = const.DI_INDS_6_DNA
elif args.k == 3:
default_e = const.TRI_INDS_DNA
elif args.alphabet == 'RNA':
args.alphabet = index_list.RNA
default_e = const.DI_INDS_RNA
elif args.alphabet == 'Protein':
args.alphabet = index_list.PROTEIN
default_e = const.INDS_3_PROTEIN
theta_type = 1
if args.method in const.THETA_1_METHODS:
theta_type = 1
elif args.method in const.THETA_2_METHODS:
theta_type = 2
elif args.method == 'PseKNC':
theta_type = 3
else:
print("Method error!")
# PseKNC.
if args.method != 'PseKNC':
if args.e is None and len(ind_list) == 0 and args.a is False:
# Default Pse.
res = pseknc(f,
args.k,
args.w,
args.lamada,
default_e,
args.alphabet,
extra_index_file=args.e,
all_prop=args.a,
theta_type=theta_type)
else:
res = pseknc(f,
args.k,
args.w,
args.lamada,
ind_list,
args.alphabet,
extra_index_file=args.e,
all_prop=args.a,
theta_type=theta_type)
# iPseKNC.
else:
if args.e is None and len(ind_list) == 0 and args.a is False:
# Default iPse.
res = ipseknc(f,
args.k,
args.w,
args.lamada,
const.DI_INDS_6_DNA,
args.alphabet,
extra_index_file=args.e,
all_prop=args.a)
else:
res = ipseknc(f,
args.k,
args.w,
args.lamada,
ind_list,
args.alphabet,
extra_index_file=args.e,
all_prop=args.a)
# Write correspond res file.
if args.f == 'tab':
from util import write_tab
write_tab(res, args.outputfile)
elif args.f == 'svm':
from util import write_libsvm
write_libsvm(res, [args.l] * len(res), args.outputfile)
elif args.f == 'csv':
from util import write_csv
write_csv(res, args.outputfile)
def main(args):
with open(args.inputfile) as f:
# Get index_list.
if args.i is not None:
ind_list = read_index(args.i)
else:
ind_list = []
default_e = []
# Set Pse default index_list.
if args.alphabet == 'DNA':
args.alphabet = index_list.DNA
if args.k == 2:
default_e = const.DI_INDS_6_DNA
elif args.k == 3:
default_e = const.TRI_INDS_DNA
elif args.alphabet == 'RNA':
args.alphabet = index_list.RNA
default_e = const.DI_INDS_RNA
elif args.alphabet == 'Protein':
args.alphabet = index_list.PROTEIN
default_e = const.INDS_3_PROTEIN
theta_type = 1
if args.method in const.THETA_1_METHODS:
theta_type = 1
elif args.method in const.THETA_2_METHODS:
theta_type = 2
elif args.method == 'PseKNC':
theta_type = 3
else:
print("Method error!")
# PseKNC.
if args.method != 'PseKNC':
if args.e is None and len(ind_list) == 0 and args.a is False:
# Default Pse.
res = pseknc(f,
args.k,
args.w,
args.lamada,
default_e,
args.alphabet,
extra_index_file=args.e,
all_prop=args.a,
theta_type=theta_type)
else:
res = pseknc(f,
args.k,
args.w,
args.lamada,
ind_list,
args.alphabet,
extra_index_file=args.e,
all_prop=args.a,
theta_type=theta_type)
# iPseKNC.
else:
if args.e is None and len(ind_list) == 0 and args.a is False:
# Default iPse.
res = ipseknc(f,
args.k,
args.w,
args.lamada,
const.DI_INDS_6_DNA,
args.alphabet,
extra_index_file=args.e,
all_prop=args.a)
else:
res = ipseknc(f,
args.k,
args.w,
args.lamada,
ind_list,
args.alphabet,
extra_index_file=args.e,
all_prop=args.a)
# Write correspond res file.
if args.f == 'tab':
from util import write_tab
write_tab(res, args.outputfile)
elif args.f == 'svm':
if args.multi == 0 and args.l is None:
args.l = '+1'
elif args.multi == 0 and (args.l != '+1' and args.l != '-1'):
print "For binary classification, the label should be either '+1' or '-1'."
return False
elif args.multi == 1 and args.l is None:
args.l = '0'
elif args.multi == 1 and args.l is not None:
try:
label = int(args.l)
except ValueError:
print 'The labels should be integer.'
return False
from util import write_libsvm
write_libsvm(res, [args.l] * len(res), args.outputfile)
elif args.f == 'csv':
from util import write_csv
write_csv(res, args.outputfile)
def main(args):
# Set revcomp parameter.
if args.r != 1:
args.r = False
elif args.r == 1 and args.alphabet != 'DNA':
print("Error, the -r parameter can only be used in DNA.")
elif args.r == 1 and args.alphabet == 'DNA':
args.r = True
# Set alphabet parameter.
if args.alphabet == 'DNA':
args.alphabet = index_list.DNA
elif args.alphabet == 'RNA':
args.alphabet = index_list.RNA
elif args.alphabet == 'Protein':
args.alphabet = index_list.PROTEIN
if args.method.upper() == 'KMER':
if args.k is None:
print "parameters k is required. The default value of k is 2."
args.k = 2
if args.r is None:
print "parameters r is required. The default value of r is 0."
args.r = 0
res = make_kmer_vector(k=args.k, alphabet=args.alphabet, filename=args.inputfile, revcomp=args.r)
elif args.method.upper() == "MISMATCH":
if args.k is None:
print "parameters k is required. The default value of k is 3."
args.k = 3
if args.m is None:
print "parameters m is required. The default value of m is 1."
args.m = 1
if args.m >= args.k:
print "parameters m should be less than parameter k."
else:
res = getMismatchProfileMatrix(args.inputfile, args.alphabet, args.k, args.m)
elif args.method.upper() == "SUBSEQUENCE":
if args.delta is None:
print "parameters delta is required. The default value of delta is 1."
args.delta = 1
elif args.delta > 1 or args.delta < 0:
print "delta should be greater than or equal to 0 and less than or equal to 1."
if args.k is None:
print "parameters k is required. The default value of k is 3."
args.k = 3
res = getSubsequenceProfileByParallel(filename=args.inputfile, alphabet=args.alphabet, k=args.k, delta=args.delta)
else:
print("Method error!")
# Write correspond res file.
if args.f == 'svm':
from util import write_libsvm
write_libsvm(res, [args.l] * len(res), args.outputfile)
elif args.f == 'tab':
from util import write_tab
write_tab(res, args.outputfile)
elif args.f == 'csv':
from util import write_csv
write_csv(res, args.outputfile)
def main(args):
names=[]
with open(args.inputfile) as af:
seq_list=read_fasta(af)
for e in seq_list:
names.append(e.name)
#kmer.py -f tab -l +1 -r 1 -k ',num2str(k),' TAIR10_DHSs.fas TAIR10_DHSs_reckmer_',num2str(k),'.txt DNA'
res_kmer = make_kmer_vector(k=2, alphabet=index_list.DNA, filename=args.inputfile, revcomp=True)
#acc.py -e user_indices.txt -f svm -l +1 -lag ',num2str(lag),' TAIR10_DHSs.fas TAIR10_DHSs_dac_',num2str(lag),'.txt DNA DAC'
if args.s==0:
model_file='pDHSdata_TAIR_model.txt'
lag=3
else:
model_file='pDHSdata_TIGR_model.txt'
lag=8
with open(args.inputfile) as f:
k = read_k('DNA', 'DAC', 0)
ind_list=[]
res_acc = acc(f, k, lag, ind_list, index_list.DNA, extra_index_file='user_indices.txt', all_prop=False, theta_type=1)
# features= revckmer+dac,formed by add each row
res=[]
for i in range(len(res_kmer)):
res.append(res_kmer[i]+res_acc[i])
featuresfile=args.inputfile+'_tmp_features.txt'
# Write correspond res file.
from util import write_libsvm
write_libsvm(res, ['+1'] * len(res), featuresfile)
#predict the result
tmp_predict_result_file=args.inputfile+'_tmp_result.txt'
if sys.platform == 'win32':
options='svm-predict -b 1 -q '+featuresfile+' '+model_file+' '+ tmp_predict_result_file
else:
options='./svm-predict -b 1 -q '+featuresfile+' '+model_file+' '+ tmp_predict_result_file
os.system(options)
pf=open(args.outputfile,'w')
with open(tmp_predict_result_file) as nf:
label, TrueProb, FalseProb= '', '',''
count = 0
while True:
line = nf.readline().strip()
if not line:
break
if count>len(names):
break
if 0==count:
pf.write('ID\t\tLabel\t\tProb\n')
count+=1
continue
label=int(line.split()[0])
TrueProb=line.split()[1]
FalseProb=line.split()[2]
if label==-1:
pf.write(names[count-1]+'\t\t'+'Non DHS'+'\t\t'+str(FalseProb)+'\n')
else:
pf.write(names[count-1]+'\t\t'+'DHS'+'\t\t'+str(TrueProb)+'\n')
count+=1
pf.close()
cwd = os.getcwd()
files = [x for x in os.listdir(os.getcwd()) if os.path.isfile(os.path.join(cwd,x))]
#print files
for file in files:
if -1 != file.find('tmp'):
os.remove(file)
