def _load_encode_rna(self, class_files):
self.data, self.labels = [], []
replacer_seq = lambda x: choice(self.alpha_coder.alph0)
replacer_struct = lambda x: choice(self.alpha_coder.alph1)
pattern_seq = r"[^{}]".format(re.escape(self.alpha_coder.alph0))
pattern_struct = r"[^{}]".format(re.escape(self.alpha_coder.alph1))
for class_id, file_name in enumerate(class_files):
handle = io.get_handle(file_name, "rt")
for header, block in io.parse_fasta(handle, "_"):
lines = block.split("_")
sequence = re.sub(pattern_seq, replacer_seq, lines[0].upper())
if True == self.is_rna_pwm:
pwm = np.zeros(
(len(sequence), len(self.alpha_coder.alph1)),
dtype=np.float32)
for x in range(1, pwm.shape[1] + 1):
pwm[:, x - 1] = list(map(float, lines[x].split()))
self.data.append(self._join_seq_pwm(sequence, pwm))
else:
structure = re.sub(pattern_struct, replacer_struct,
lines[1].split(" ")[0].upper())
joined = self.alpha_coder.encode((sequence, structure))
self.data.append(self.one_hot_encoder.encode(joined))
if self.multilabel:
self.labels.append(list(map(int, header.split(','))))
else:
self.labels.append([class_id])
handle.close()
def _load_encode_dna(self, class_files):
self.data, self.labels = [], []
replacer = lambda x: choice(self.one_hot_encoder.alphabet)
for class_id, file_name in enumerate(class_files):
handle = io.get_handle(file_name, "rt")
for header, sequence in io.parse_fasta(handle):
sequence = re.sub(r"[NYMRWK]", replacer, sequence.upper())
self.data.append(self.one_hot_encoder.encode(sequence))
if self.multilabel:
self.labels.append(list(map(int, header.split(','))))
else:
self.labels.append([class_id])
handle.close()
def _load_encode_rna(self, class_files):
self.data, self.labels = [], []
replacer_seq = lambda x: choice(self.alpha_coder.alph0)
replacer_struct = lambda x: choice(self.alpha_coder.alph1)
if self.alpha_coder.alph1 == "HIMS":
idx = 2
else:
idx = 1
for class_id, file_name in enumerate(class_files):
handle = io.get_handle(file_name, "rt")
for header, block in io.parse_fasta(handle, "_"):
lines = block.split("_")
sequence = re.sub(r"[NYMRWK]", replacer_seq, lines[0])
structure = re.sub(r"[FT]", replacer_struct,
lines[idx].split(" ")[0].upper())
joined = self.alpha_coder.encode((sequence, structure))
self.data.append(self.one_hot_encoder.encode(joined))
if self.multilabel:
self.labels.append(list(map(int, header.split(','))))
else:
self.labels.append([class_id])
handle.close()