def make_kmer_vec(self, data):
"""Make a kmer vector with options k, upto, revcomp, normalize.
:param data: file object or sequence list.
:return: kmer vector.
"""
sequence_list = get_data(data)
kmer_list = get_kmer_list(self.k, self.upto, self.alphabet)
rev_kmer_list = []
revcomp = False
vec = make_kmer_vector(sequence_list, kmer_list, rev_kmer_list, self.k, self.upto, revcomp, self.normalize)
return vec
def make_revckmer_vec(self, data):
"""Make a reverse compliment kmer vector with options k, upto, normalize.
:param data: file object or sequence list.
:return: reverse compliment kmer vector.
"""
sequence_list = get_data(data)
kmer_list = get_kmer_list(self.k, self.upto, self.alphabet)
# Use lexicographically first version of {kmer, revcomp(kmer)}.
rev_kmer_list = make_revcomp_kmer_list(kmer_list)
revcomp = True
vec = make_kmer_vector(sequence_list, kmer_list, rev_kmer_list, self.k,
self.upto, revcomp, self.normalize)
return vec
def make_idkmer_vec(self, data, hs, non_hs):
"""Make IDKmer vector.
:param data: Need to processed FASTA file.
:param hs: Positive FASTA file.
:param non_hs: Negative FASTA file.
"""
from nacutil import make_kmer_list
from nacutil import diversity
from nacutil import id_x_s
rev_kmer_list, upto, revcomp, normalize = [], False, False, False
pos_s_list = get_data(hs)
neg_s_list = get_data(non_hs)
# print self.k
if self.upto is False:
k_list = [self.k]
else:
k_list = list(range(1, self.k + 1))
# print 'k_list =', k_list
# Get all kmer ID from 1-kmer to 6-kmer.
# Calculate standard source S vector.
pos_s_vec, neg_s_vec = [], []
diversity_pos_s, diversity_neg_s = [], []
for k in k_list:
kmer_list = make_kmer_list(k, self.alphabet)
temp_pos_s_vec = make_kmer_vector(pos_s_list, kmer_list,
rev_kmer_list, k, upto, revcomp,
normalize)
temp_neg_s_vec = make_kmer_vector(neg_s_list, kmer_list,
rev_kmer_list, k, upto, revcomp,
normalize)
temp_pos_s_vec = [
sum(e) for e in zip(*[e for e in temp_pos_s_vec])
]
temp_neg_s_vec = [
sum(e) for e in zip(*[e for e in temp_neg_s_vec])
]
pos_s_vec.append(temp_pos_s_vec)
neg_s_vec.append(temp_neg_s_vec)
diversity_pos_s.append(diversity(temp_pos_s_vec))
diversity_neg_s.append(diversity(temp_neg_s_vec))
# Calculate Diversity(X) and ID(X, S).
sequence_list = get_data(data)
vec = []
for seq in sequence_list:
# print seq
temp_vec = []
for k in k_list:
kmer_list = make_kmer_list(k, self.alphabet)
seq_list = [seq]
kmer_vec = make_kmer_vector(seq_list, kmer_list, rev_kmer_list,
k, upto, revcomp, normalize)
# print 'k', k
# print 'kmer_vec', kmer_vec
# print diversity_pos_s
if upto is False:
k = 1
# print 'pos_vec', pos_s_vec
# print 'neg_vec', neg_s_vec
# print 'diversity_pos_s', diversity_pos_s
temp_vec.append(
round(
id_x_s(kmer_vec[0], pos_s_vec[k - 1],
diversity_pos_s[k - 1]), 3))
temp_vec.append(
round(
id_x_s(kmer_vec[0], neg_s_vec[k - 1],
diversity_neg_s[k - 1]), 3))
vec.append(temp_vec)
return vec