def preprocess_chipseq(num_jobs, bin_size):
datagen = DataGenerator()
processes = []
celltypes = datagen.get_celltypes()
transcription_factors = datagen.get_trans_fs()
for part in ['train']:
with open('../data/annotations/%s_regions.blacklistfiltered.merged.bed' % part) as fin:
lines = fin.read()
for celltype in celltypes:
for transcription_factor in transcription_factors:
if not os.path.exists('../data/chipseq_fold_change_signal/ChIPseq.%s.%s.fc.signal.train.bw'
% (celltype, transcription_factor)):
continue
fout_path = '../data/preprocess/CHIPSEQ_FEATURES/%s_%s_%d.gz' % (
celltype, transcription_factor, bin_size)
if not os.path.exists(fout_path):
processes.append(
Process(target=parralelChIPSeqSignalProcessor,
args=(lines, fout_path, celltype, transcription_factor, bin_size)))
for i in range(0, len(processes), num_jobs):
map(lambda x: x.start(), processes[i:i + num_jobs])
map(lambda x: x.join(), processes[i:i + num_jobs])
def preprocess_dnase(num_jobs, bin_size):
datagen = DataGenerator()
processes = []
celltypes = datagen.get_celltypes()
for part in ['train', 'ladder', 'test']:
with open('../data/annotations/%s_regions.blacklistfiltered.merged.bed' % part) as fin:
lines = fin.read()
for celltype in celltypes:
if not os.path.exists('../data/preprocess/DNASE_FEATURES/%s_%s_%d.txt' % (celltype, part, bin_size)):
fout_path = '../data/preprocess/DNASE_FEATURES/%s_%s_%d.gz' % (celltype, part, bin_size)
processes.append(
Process(
target=parralelDNAseSignalProcessor,
args=(lines, fout_path, celltype, bin_size)))
num_processes = num_jobs
for i in range(0, len(processes), num_processes):
map(lambda x: x.start(), processes[i:i + num_processes])
map(lambda x: x.join(), processes[i:i + num_processes])
