def parse_inputs(
samp1_bm_fns, samp2_bm_fns, strand_offset, samp_names, valid_pos_fn,
out_fp):
# parse valid positions
valid_pos = None
if valid_pos_fn is not None:
valid_pos = mh.parse_beds(
valid_pos_fn, ignore_strand=strand_offset is not None)
# parse bed methyl files
samp1_cov, samp1_mod_cov = mh.parse_bed_methyls(
samp1_bm_fns, strand_offset=strand_offset, valid_pos=valid_pos)
samp1_all_cov = np.array([cov for ctg_cov in samp1_cov.values()
for cov in ctg_cov.values()])
samp2_cov, samp2_mod_cov = mh.parse_bed_methyls(
samp2_bm_fns, strand_offset=strand_offset, valid_pos=valid_pos)
samp2_all_cov = np.array([cov for ctg_cov in samp2_cov.values()
for cov in ctg_cov.values()])
out_fp.write(
'{} coverage median: {:.2f} mean: {:.2f} sd: {:.2f}\n'.format(
samp_names[0], np.median(samp1_all_cov),
np.mean(samp1_all_cov), np.std(samp1_all_cov)))
out_fp.write(
'{} coverage median: {:.2f} mean: {:.2f} sd: {:.2f}\n'.format(
samp_names[1], np.median(samp2_all_cov),
np.mean(samp2_all_cov), np.std(samp2_all_cov)))
return (samp1_cov, samp1_mod_cov, samp1_all_cov,
samp2_cov, samp2_mod_cov, samp2_all_cov)
def parse_inputs(samp1_bm_fns, samp2_bm_fns, strand_offset, samp_names,
valid_pos_fn, out_fp):
# parse valid positions
valid_pos = None
if valid_pos_fn is not None:
LOGGER.info("Parsing valid sites bed")
valid_pos = mh.parse_beds(
valid_pos_fn,
ignore_strand=strand_offset is not None,
show_prog_bar=False,
)
# parse bed methyl files
LOGGER.info("Parsing bedmethyl files")
samp1_cov, samp1_mod_cov = mh.parse_bed_methyls(
samp1_bm_fns,
strand_offset=strand_offset,
valid_pos=valid_pos,
show_prog_bar=False,
)
samp1_all_cov = np.array(
[cov for ctg_cov in samp1_cov.values() for cov in ctg_cov.values()])
samp2_cov, samp2_mod_cov = mh.parse_bed_methyls(
samp2_bm_fns,
strand_offset=strand_offset,
valid_pos=valid_pos,
show_prog_bar=False,
)
samp2_all_cov = np.array(
[cov for ctg_cov in samp2_cov.values() for cov in ctg_cov.values()])
out_fp.write(
"{} coverage median: {:.2f} mean: {:.2f} sd: {:.2f}\n".format(
samp_names[0],
np.median(samp1_all_cov),
np.mean(samp1_all_cov),
np.std(samp1_all_cov),
))
out_fp.write(
"{} coverage median: {:.2f} mean: {:.2f} sd: {:.2f}\n".format(
samp_names[1],
np.median(samp2_all_cov),
np.mean(samp2_all_cov),
np.std(samp2_all_cov),
))
return (
samp1_cov,
samp1_mod_cov,
samp1_all_cov,
samp2_cov,
samp2_mod_cov,
samp2_all_cov,
)
def _main(args):
samp_cov, samp_mod_cov = mh.parse_bed_methyls(
args.bed_methyl_files, strand_offset=args.strand_offset)
with open(args.out_csv, 'w') as gt_fp:
for (chrom, strand), ctg_cov in samp_cov.items():
for pos, cov in ctg_cov.items():
if cov < args.coverage_threshold:
continue
pct_mod = 100 * samp_mod_cov[(chrom, strand)][pos] / cov
if pct_mod <= args.pct_mod_thresholds[0]:
gt_fp.write(','.join(
map(str, (chrom, mh.int_strand_to_str(strand), pos,
'False'))) + '\n')
if args.strand_offset is not None:
gt_fp.write(','.join(
map(str, (chrom, mh.int_strand_to_str(strand),
pos + args.strand_offset, 'False'))) +
'\n')
elif pct_mod >= args.pct_mod_thresholds[1]:
gt_fp.write(','.join(
map(str, (chrom, mh.int_strand_to_str(strand), pos,
'True'))) + '\n')
if args.strand_offset is not None:
gt_fp.write(','.join(
map(str, (chrom, mh.int_strand_to_str(strand),
pos + args.strand_offset, 'True'))) +
'\n')
def check_matching_attrs(ground_truth_bed,
strand_offset,
mod_db_fn,
target_mod_bases,
limit=10000):
mods_db = mods.ModsDb(mod_db_fn)
db_strands = (1, -1) if strand_offset is None else (None, )
db_chrms = set((chrm, strand) for _, chrm, _ in mods_db.iter_chrms()
for strand in db_strands)
cov, mod_cov = mh.parse_bed_methyls([
ground_truth_bed,
],
strand_offset,
show_prog_bar=False,
limit=limit)
if len(db_chrms.intersection(cov.keys())) == 0:
LOGGER.error(('Using first {} sites from {}, found zero overlapping ' +
'contig/chromosome names with the mod database.').format(
limit, ground_truth_bed))
LOGGER.info('Database contigs/chromosomes: {}'.format(', '.join(
map(str, db_chrms))))
LOGGER.info('BED methyl contigs/chromosomes: {}'.format(', '.join(
map(str, list(cov.keys())))))
raise mh.MegaError('No overlapping contigs found.')
db_mods = set(mod_base for mod_base, _ in mods_db.get_mod_long_names())
for tmb in target_mod_bases:
if tmb not in db_mods:
raise mh.MegaError(
('Target modified base, {}, not found in mods database ' +
'({}).').format(tmb, ', '.join(db_mods)))
mods_db.check_data_covering_index_exists()
mods_db.close()
def write_unsorted_merge(in_fns, out_fp, bar):
cov, mod_cov = mh.parse_bed_methyls(in_fns)
for chrm in sorted(
mh.RefName(chrm) for chrm in set(chrm for chrm, _ in cov)):
# convert back to string after sorting
chrm = str(chrm)
s_poss = []
if (chrm, 1) in cov:
s_poss.extend([(pos, 1) for pos in cov[(chrm, 1)]])
if (chrm, -1) in cov:
s_poss.extend([(pos, -1) for pos in cov[(chrm, -1)]])
for pos, strand in sorted(s_poss):
pcov = cov[(chrm, strand)][pos]
out_fp.write(
mods.BEDMETHYL_TMPLT.format(
chrom=chrm,
pos=pos,
end=pos + 1,
strand=mh.int_strand_to_str(strand),
cov=pcov,
score=min(int(pcov), 1000),
perc=np.around(mod_cov[(chrm, strand)][pos] / pcov *
100, 1),
) + "\n")
bar.update()
def parse_mod_sample(bm_files, strand_offset, cov_thresh, samp_name):
cov, mod_cov = mh.parse_bed_methyls(bm_files, strand_offset=strand_offset)
all_cov = np.array(
[cov for ctg_cov in cov.values() for cov in ctg_cov.values()])
LOGGER.info('{} coverage median: {:.2f} mean: {:.2f}'.format(
samp_name, np.median(all_cov), np.mean(all_cov)))
test_sites = {}
for ctg in mod_cov:
test_sites[ctg] = set(pos for pos, cov in cov[ctg].items()
if cov >= cov_thresh)
return MOD_SAMPLE(cov, mod_cov, test_sites)