def main():
args = parse_args()
# Read input files
_logger.info('Reading input files')
peaks = pd.read_csv(args.input, sep='\t', header=None,
usecols=[0, 1, 2], skiprows=args.skip)
sizes = pd.read_csv(args.sizes, sep='\t', header=None)
# Subset to peaks in sizes file
# TODO: Move this test into the df_to_bedGraph function
peaks_filtered = peaks[peaks[0].isin(sizes[0])].copy()
_logger.info('Retaining ' + str(len(peaks_filtered)) + ' of ' +
str(len(peaks)) + ' peaks in given chromosomes.')
# Add score of 1 for all peaks
_logger.info('Adding score')
peaks_filtered[3] = 1
# Set prefix for output files
if args.prefix is None:
# Output file gets name from input
prefix = args.input
else:
prefix = args.prefix
# Write bedGraph
_logger.info('Writing peaks to bedGraph file')
df_to_bedGraph(peaks_filtered, prefix + '.bedGraph')
# Write bigWig and delete bedGraph
_logger.info('Writing peaks to bigWig file {}'.format(prefix + '.bw'))
bedgraph_to_bigwig(prefix + '.bedGraph', args.sizes, deletebg=True)
_logger.info('Done!')
def main():
"""Convert peak files to bigwig."""
args = parse_args()
# Set name for output file
if args.prefix is None:
# Output file gets name from input
prefix = os.path.basename(args.input)
else:
prefix = args.prefix
out_bg_name = os.path.join(args.out_dir, prefix + '.bedGraph')
# Read input files
_logger.info('Reading input file')
peaks = read_intervals(args.input, skip=args.skip)
_logger.info('Read ' + str(len(peaks)) + ' peaks.')
sizes = read_sizes(args.sizes)
# Add score of 1 for all peaks
_logger.info('Adding score')
peaks['score'] = 1
# Write bedGraph
_logger.info('Writing peaks to bedGraph file')
# Note: peaks will be subset to chromosomes in sizes file.
df_to_bedGraph(peaks, out_bg_name, sizes)
# Write bigWig and delete bedGraph
_logger.info('Writing peaks to bigWig file {}'.format(prefix + '.bw'))
bedgraph_to_bigwig(out_bg_name, args.sizes,
deletebg=True, sort=True)
_logger.info('Done!')
def save_to_bedgraph(batch_range,
item,
channel,
intervals,
outfile,
rounding=None,
threshold=None):
"""Write out the tracks and peaks to bedGraphs.
Args:
batch_range : List containing start and end position of batch to write.
item : Output from the queue.
channel : Channel to be written out.
intervals : pandas object containing inference intervals.
outfile : The output file to write the output to.
rounding : If not None, round the scores to given value.
threshold : if not None, threhsold the scores to given value.
"""
keys, batch = item
start = batch_range[0]
end = batch_range[1]
scores = batch[start:end, :, channel]
# Round scores - for regression output
if rounding is not None:
scores = scores.astype('float64')
# Sometimes np.around doesn't work with float32. To investigate.
scores = np.around(scores, decimals=rounding)
# Apply thresholding only to peaks
if threshold is not None and channel == 1:
scores = (scores > threshold).astype(int)
# if the batch contains values > 0, write them
if (scores > 0).any():
# Select intervals corresponding to batch
batch_intervals = intervals.iloc[keys.numpy()[start:end], :].copy()
# Add scores to each interval
batch_intervals['scores'] = np.split(scores, scores.shape[0])
batch_intervals['scores'] = [x[0] for x in batch_intervals['scores']]
# Select intervals with scores>0
batch_intervals = batch_intervals.loc[scores.sum(axis=1) > 0, :]
# Expand each interval, combine with scores, and contract to smaller
# intervals
batch_bg = intervals_to_bg(batch_intervals)
df_to_bedGraph(batch_bg, outfile)