class StrandedBigWigExtractor:
"""Big-wig file extractor
NOTE: The extractor is not thread-save.
If you with to use it with multiprocessing,
create a new extractor object in each process.
# Arguments
bigwig_file: path to the bigwig file
"""
def __init__(self,
bigwig_file,
interval_transform=None,
use_strand=False,
nan_as_zero=True):
self.nan_as_zero = nan_as_zero
self.use_strand = use_strand
self.bigwig_file = bigwig_file
self.interval_transform = interval_transform
self.batch_extractor = None
def extract_single(self, interval):
if self.batch_extractor is None:
from genomelake.extractors import BigwigExtractor
self.batch_extractor = BigwigExtractor(self.bigwig_file)
if self.interval_transform is not None:
interval = self.interval_transform(interval)
arr = self.batch_extractor([interval], nan_as_zero=self.nan_as_zero)[0]
if self.use_strand and interval.strand == '-':
arr = arr[::-1]
return arr
def extract(self, intervals, progbar=False):
return np.stack([
self.extract_single(interval)
for interval in tqdm(intervals, disable=not progbar)
])
def close(self):
return self.batch_extractor.close()
def test_bigwig_extractor(test_bigwig_and_intervals):
bw_path, intervals, expected_data = test_bigwig_and_intervals
extractor = BigwigExtractor(bw_path)
data = extractor(intervals)
extractor.close()
assert (data == expected_data).all()