def lc_to_lens(sequence, k, lca, lce):
"""Returns a list of the lengths of the LC intervals"""
ind_in = lc_to_indexes(sequence, k, lca, lce)
intervals = tools.ints_to_ranges(sorted(list(ind_in)))
lens = []
for inter in intervals:
lens.append((inter[1] - inter[0]) + 1)
return lens
def lce_to_interval(sequence, k, lce):
kmers = seq_to_kmers(sequence, k)
indexes = set()
for i, kmer in enumerate(kmers):
if lce_motif(kmer, lce):
for j in range(i, i + k):
indexes.add(j)
intervals = tools.ints_to_ranges(sorted(list(indexes)))
return intervals
def form_seq(self, seqs):
form_seqs = []
for seq in seqs:
inds = tools_lc.lc_to_indexes(seq, self.k, self.lca, self.lce)
ranges = list(tools.ints_to_ranges(sorted(list(inds))))
es = self.format_string(seq, ranges)
if self.color:
ns = self.add_colors(es)
form_seqs.append(ns)
else:
form_seqs.append(es)
return form_seqs
def lca_to_interval(sequence, k, lca):
"""
Returns inclusive interval, where all numbers are in the motif, ie (0, 6)
and not (0, 7)
"""
kmers = seq_to_kmers(sequence, k)
indexes = set()
for i, kmer in enumerate(kmers):
if lca_motif(kmer, lca):
for j in range(i, i + k):
indexes.add(j)
intervals = tools.ints_to_ranges(sorted(list(indexes)))
return intervals
def read_seq(self):
df = pd.read_csv(self.bc_dp, sep='\t', index_col=0)
df = df[df['Organism'] == 'HUMAN']
seqs = df['Sequence']
scores = list(df['LC Score'])
form_seqs = []
for seq in seqs:
inds = tools_lc.lc_to_indexes(seq, self.k, self.lca, self.lce)
ranges = list(tools.ints_to_ranges(sorted(list(inds))))
es = self.format_string(seq, ranges)
ns = self.add_colors(es)
#ns = self.color_aromatics(es)
form_seqs.append(ns)
return form_seqs, scores