def load_data_inference(self):
"""Load data in using inference functions"""
f_signal = read_signal(self.file_path, normalize=True)
f_signal = f_signal[self.start_index:]
sig_len = len(f_signal)
for indx in range(0, sig_len, self.step):
segment_sig = f_signal[indx:indx + self.seq_len]
segment_len = len(segment_sig)
padded_segment_sig = self.padding(segment_sig, self.seq_len)
yield self.inference_labels(input=np.asarray(padded_segment_sig),
seq_len=np.asarray(segment_len))
def trim_signal(signal_file, label_file, outdir):
"""Trim signal file to only have signal aligned from label file"""
outpath = os.path.join(
outdir,
signal_file.split('/')[-1].split('.')[0] + ".trim.signal")
signal = read_signal(signal_file, normalize=False)
label = read_label(label_file)
start = label.start[0]
end = label.start[-1]
final_signal = signal[start:end]
with open(outpath, 'w+') as f_signal:
f_signal.write(" ".join(str(val) for val in final_signal))
return outpath
def trim_complement_signal(self, outdir):
"""Trim signal file to only have signal aligned from label file"""
assert os.path.isdir(outdir), "{} does not exist".format(outdir)
assert os.path.isfile(self.label_file), "{} does not exist".format(
self.label_file)
out_path = os.path.join(
outdir,
self.signal_file.split('/')[-1].split('.')[0] + ".trim.signal")
signal = read_signal(self.signal_file, normalize=False)
label = read_label(self.label_file)
start = label.start[0]
end = label.start[-1]
final_signal = signal[start:end]
out_path = self.write_signal(final_signal, out_path)
return out_path
def load_data(self):
"""Read in data from signal files and create specific motif comparisons"""
event = list()
event_length = list()
label = list()
label_length = list()
count = 0
file_count = 0
for name in self.file_list:
if name.endswith(".signal"):
try:
file_pre = os.path.splitext(name)[0]
f_signal = read_signal(name)
label_name = file_pre + '.label'
trim_signal = SignalLabel(name, label_name)
motif_generator = trim_signal.trim_to_motif(["CCAGG", "CCTGG", "CEAGG", "CETGG"],
prefix_length=0,
suffix_length=0,
methyl_index=1,
blank=self.blank)
for motif in motif_generator:
tmp_event, tmp_event_length, tmp_label, tmp_label_length = read_raw(f_signal, motif,
self.seq_len,
short=True)
event += tmp_event
event_length += tmp_event_length
label += tmp_label
label_length += tmp_label_length
count = len(event)
if file_count % 10 == 0:
sys.stdout.write("%d lines read. \n" % (count))
file_count += 1
except ValueError:
print("Error Reading Data from file {}".format(name))
continue
padded_labels = []
pad_len = max(label_length)
for i in range(len(label)):
padded_labels.append(np.lib.pad(label[i], (0, pad_len - label_length[i]), 'constant', constant_values=-1))
return self.training_labels(input=np.asarray(event), seq_len=np.asarray(event_length),
label=padded_labels)
def load_data(self):
"""Read in data from signal files and create specific motif comparisons"""
event = list()
event_length = list()
label = list()
label_length = list()
count = 0
file_count = 0
for name in self.file_list:
if name.endswith(".signal"):
try:
file_pre = os.path.splitext(name)[0]
f_signal = read_signal(name)
label_name = file_pre + '.label'
f_label = read_label(label_name, skip_start=10, window_n=(self.kmer - 1) / 2,
alphabet=self.len_y)
tmp_event, tmp_event_length, tmp_label, tmp_label_length = read_raw(f_signal, f_label,
self.seq_len,
max_event_length=
self.max_event_len)
event += tmp_event
event_length += tmp_event_length
label += tmp_label
label_length += tmp_label_length
count = len(event)
if file_count % 10 == 0:
sys.stdout.write("%d files read. \n" % (count))
file_count += 1
except ValueError:
print("Error Reading Data from file {}".format(name))
continue
padded_labels = []
pad_len = max(label_length)
for i in range(len(label)):
padded_labels.append(np.lib.pad(label[i], (0, pad_len - label_length[i]), 'constant', constant_values=-1))
return self.training_labels(input=np.asarray(event), seq_len=np.asarray(event_length),
label=padded_labels)
def read_signal(self, normalize):
return read_signal(self.signal_file, normalize=normalize)