def main():
"""
Merge files.
Accumulate all reads / observations from multiple (>=2) input files,
and output a single file of the same format.
Supported formats: pat.gz, beta
"""
args = parse_args()
# validate input files
input_files = args.input_files
validate_files_list(input_files, min_len=2)
# construct output path
out_path = args.prefix + splitextgz(args.input_files[0])[1]
if not delete_or_skip(out_path, args.force):
return
files_type = splitextgz(input_files[0])[1][1:]
if files_type in ('beta', 'bin'):
merge_betas(input_files, out_path)
elif files_type == 'pat.gz':
MergePats(input_files, args.prefix + '.pat', args.labels, args).merge_pats()
elif files_type == 'unq.gz':
merge_unqs()
else:
print('Unknown input format:', input_files[0])
return
def main():
"""
Collapse beta file to blocks binary file, of the same beta format
"""
args = parse_args()
files = args.input_files
validate_files_list(files, '.beta')
if not op.isfile(args.blocks_file):
eprint('Invalid blocks file:', args.blocks_file)
return
names = ['chr', 'sloc', 'eloc', 'ssite', 'esite']
df = pd.read_csv(args.blocks_file, sep='\t', usecols=[0, 1, 2, 3, 4], header=None, names=names)
nr_removed = df[df.ssite == df.esite].shape[0]
if nr_removed:
eprint('removed {} regions with no CpGs'.format(nr_removed))
if args.debug:
eprint(df[df.ssite == df.esite])
df = df[df.ssite < df.esite]
blocks_bins, filtered_indices = get_bins(df)
with Pool() as p:
for beta_path in files:
params = (args, blocks_bins,
filtered_indices, beta_path, df[['chr', 'sloc', 'eloc']])
p.apply_async(apply_filter_wrapper, params)
p.close()
p.join()
def main(args):
validate_files_list(args.input_files, '.pat.gz')
gr = GenomicRegion(args)
print(gr)
for pat_file in args.input_files:
print(splitextgz(op.basename(pat_file))[0]) # print file name
PatVis(args, pat_file).print_results()
def main():
"""
Plot histogram of reads lengths of unq file
Output to stdout the histogram values if requested
"""
args = parse_args()
validate_files_list(args.unq_paths, 'unq.gz')
multi_FragLen(args)
def main():
"""
Convert beta file[s] to bed file[s].
"""
args = parse_args()
validate_files_list(args.beta_paths, '.beta')
b = BetaToBigWig(args)
for beta in args.beta_paths:
b.run_beta_to_bed(beta)
def main():
"""
Compare between pairs of beta files, by plotting a 2d histogram
for every pair.
Drop sites with low coverage (< cov_thresh argument),
for performance and robustness.
"""
args = parse_args()
validate_files_list(args.betas, '.beta', min_len=2)
compare_all_paires(args.betas, args.min_cov, GenomicRegion(args).sites)
def main():
"""
Convert beta file[s] to Illumina-450K format.
Output: a csv file with ~480K rows, for the ~480K Illumina sites,
and with columns corresponding to the beta files.
all values are in range [0, 1], or NaN.
"""
args = parse_args()
validate_files_list(args.input_files, '.beta')
betas2csv(args)
def main():
"""
Convert bed[.gz] file[s] to beta file[s].
bed file should be of the format (tab-separated):
chr start end meth total
"""
# todo: bed or bedGraph?
args = parse_args()
validate_files_list(args.bed_paths)
bed2betas(args)
def main():
"""
Convert beta file[s] to bigwig file[s].
Assuming bedGraphToBigWig is installed and in PATH
"""
args = parse_args()
validate_files_list(args.beta_paths, '.beta')
b = BetaToBigWig(args)
for beta in args.beta_paths:
b.run_beta_to_bw(beta)
def main():
"""
Mix samples from K different pat files.
Output a single mixed pat.gz[.csi] file - sorted, bgzipped and indexed -
with an informative name.
"""
args = parse_args()
validate_files_list(args.pat_files, 'pat.gz', 2)
if args.bed_file and (args.region or args.sites):
eprint('-L, -s and -r are mutually exclusive')
return
mult_mix(args)
return
def main(args):
validate_files_list(args.input_files, '.beta')
BetaVis(args)
