def seq_not_lca_lce(self, seqs):
all_kmers = ''
for seq in seqs:
kmers = tools_lc.seq_to_kmers(seq, self.k)
for kmer in kmers:
if tools_lc.lce_motif(kmer, self.lce):
if not tools_lc.lca_motif(kmer, self.lca):
all_kmers += kmer
return all_kmers
def count_lca_and_lce(self, seqs):
all_counts = []
for seq in seqs:
count = 0
kmers = tools_lc.seq_to_kmers(seq, self.k)
for kmer in kmers:
if tools_lc.lce_motif(kmer, self.lce):
if tools_lc.lca_motif(kmer, self.lca):
count += 1
all_counts.append(count)
return all_counts
def count_lca_charge(self, seqs):
lca_counts = []
for seq in seqs:
lca_motifs = 0
kmers = tools_lc.seq_to_kmers(seq, self.k)
for kmer in kmers:
if tools_lc.lca_motif(kmer, self.lca):
if not tools_lc.lce_motif(kmer, self.lce):
if ('K' in kmer) and ('R' in kmer) and ('E' in kmer):
lca_motifs += 1
lca_counts.append(lca_motifs)
return lca_counts
def seq_lca(self, seqs):
seq_kmers = []
lca_counts = []
for seq in seqs:
lca_motifs = 0
kmer_str = ''
kmers = tools_lc.seq_to_kmers(seq, self.k)
for kmer in kmers:
if tools_lc.lca_motif(kmer, self.lca):
kmer_str += kmer
lca_motifs += 1
lca_counts.append(lca_motifs)
seq_kmers.append(kmer_str)
return lca_counts, seq_kmers
def create_lces(self, all_seqs):
"""
Return all the possible shannon entropies in my data set for the given
k-mer length, rounded up to the nearest 0.1.
"""
all_shannon = set()
for seq in all_seqs:
kmers = tools_lc.seq_to_kmers(seq, self.k)
for kmer in kmers:
s = tools_lc.shannon(kmer)
all_shannon.add(s)
new_scores = []
all_shannon = sorted(list(all_shannon), reverse=True)
for score in all_shannon[1:]:
new_score = self._round_up(score)
new_scores.append(new_score)
new_scores = sorted(list(set(new_scores)), reverse=True)
lce_labels = self.format_labels(new_scores)
return lce_labels
def process_seq(self, seq, k):
kmers = tools_lc.seq_to_kmers(seq, k)
qn = self.alph_fracs(kmers, 'QN')
st = self.alph_fracs(kmers, 'ST')
ag = self.alph_fracs(kmers, 'AG')
p = self.alph_fracs(kmers, 'P')
ed = self.alph_fracs(kmers, 'ED')
kr = self.alph_fracs(kmers, 'KR')
f = self.alph_fracs(kmers, 'F')
r = self.alph_fracs(kmers, 'R')
#plt.plot(qn, label='QN')
plt.plot(st, label='ST')
#plt.plot(ag, label='AG')
#plt.plot(r, label='R')
#plt.plot(f, label='F')
lca_x, lca_y, lce_x, lce_y = self.get_motif_index(seq)
plt.scatter(lca_x, lca_y, color='black', s=2)
plt.scatter(lce_x, lce_y, color='red', s=2)
#plt.plot(ed, label='ED')
#plt.plot(kr, label='KR')
plt.plot(p, label='P')
plt.legend()
plt.show()
def count_kmers(self, seqs):
total_kmers = 0
for seq in seqs:
kmers = tools_lc.seq_to_kmers(seq, self.k)
total_kmers += len(kmers)
return total_kmers