def _consumer(input_queue, output_queue):
while True:
line = input_queue.get()
if line is None:
break
f = BEDFeature.from_string(line)
# retrieve conservation data
bigwig_file = chrom_bigwig_dict[f.chrom]
arr = extract_bigwig_data(f, bigwig_file)
# measure conservation at various sliding windows
window_scores = []
for window_size in window_sizes:
window_scores.append(best_sliding_window(arr, window_size, np.mean))
# measure average conservation
finitearr = arr[np.isfinite(arr)]
if len(finitearr) == 0:
mean_cons = np.nan
else:
mean_cons = np.mean(finitearr)
fields = [f.name, '%s:%d-%d[%s]' % (f.chrom, f.tx_start, f.tx_end, f.strand),
str(len(arr)), str(mean_cons)]
fields.extend(map(str,window_scores))
result = '\t'.join(fields)
output_queue.put(result)
output_queue.put(None)
def bed_feature_conservation(f, chrom_bigwig_dict, hists):
# retrieve conservation data
bigwig_file = chrom_bigwig_dict[f.chrom]
arr = extract_bigwig_data(f, bigwig_file)
# ignore missing values
finitearr = arr[np.isfinite(arr)]
if len(finitearr) == 0:
cons_str = 'NA'
else:
hists[f.name] += np.histogram(np.clip(finitearr, BIN_MIN, BIN_MAX), BINS)[0]
cons_str = str(np.sum(finitearr))
fields = f.name.split('|')
fields.extend([f.chrom, str(f.tx_start), str(f.tx_end), f.strand, str(len(finitearr)), cons_str])
return fields
def bed_feature_conservation(f, chrom_bigwig_dict, hists):
# retrieve conservation data
bigwig_file = chrom_bigwig_dict[f.chrom]
arr = extract_bigwig_data(f, bigwig_file)
# ignore missing values
finitearr = arr[np.isfinite(arr)]
if len(finitearr) == 0:
cons_str = 'NA'
else:
hists[f.name] += np.histogram(np.clip(finitearr, BIN_MIN, BIN_MAX),
BINS)[0]
cons_str = str(np.sum(finitearr))
fields = f.name.split('|')
fields.extend([
f.chrom,
str(f.tx_start),
str(f.tx_end), f.strand,
str(len(finitearr)), cons_str
])
return fields
def conservation_serial(bed_file, window_sizes, chrom_bigwig_dict):
# output header fields
fields = ['name', 'position', 'transcript_length', 'mean']
fields.extend(map(str,window_sizes))
print '\t'.join(fields)
# process bed file
for f in BEDFeature.parse(open(bed_file)):
# retrieve conservation data
bigwig_file = chrom_bigwig_dict[f.chrom]
arr = extract_bigwig_data(f, bigwig_file)
# measure conservation at various sliding windows
window_scores = []
for window_size in window_sizes:
window_scores.append(best_sliding_window(arr, window_size, np.mean))
# calc mean conservation
finitearr = arr[np.isfinite(arr)]
if len(finitearr) == 0:
mean_cons = np.nan
else:
mean_cons = np.mean(finitearr)
fields = [f.name, '%s:%d-%d[%s]' % (f.chrom, f.tx_start, f.tx_end, f.strand),
str(len(arr)), str(mean_cons)]
fields.extend(map(str,window_scores))
print '\t'.join(fields)
