def region_p(fpvals, fregions, col_num, nsims, step, mlog=False, z=False):
# just use 2 for col_num, but dont need the p from regions.
if(sum(1 for _ in open(fregions) if _[0] != "#") == 0):
print >>sys.stderr, "no regions in %s" % (fregions, )
sys.exit()
process, total_coverage_sync = _get_total_coverage(fpvals, col_num, step)
region_info = _get_ps_in_regions(fregions, fpvals, col_num)
acfs = _gen_acf(region_info, (fpvals,), col_num, step, mlog=mlog)
process.join()
total_coverage = total_coverage_sync.value
# regions first and then create ACF for the longest one.
print >>sys.stderr, "%i bases used as coverage for sidak correction" % \
(total_coverage)
sample_distribution = np.array([b["p"] for b in bediter(fpvals,
col_num)])
for region_line, region_len, prows in region_info:
# gen_sigma expects a list of bed dicts.
sigma = gen_sigma_matrix(prows, acfs)
ps = np.array([prow["p"] for prow in prows])
if ps.shape[0] == 0:
print >>sys.stderr,("bad region", region_line)
continue
# calculate the SLK for the region.
if z:
region_slk = z_score_combine(ps, sigma)
else:
region_slk = stouffer_liptak(ps, sigma)
if not region_slk["OK"]:
print >>sys.stderr, "problem with:", region_slk, ps
slk_p = region_slk["p"]
sidak_slk_p = sidak(slk_p, region_len, total_coverage)
result = [region_line, slk_p, sidak_slk_p]
# corroborate those with p-values < 0.1 by simulation
#"""
if nsims > 0:
# adjust nsims so it's an adjusted p-value.
q_nsims = int(0.5 + total_coverage / float(region_len))
assert sample_distribution is not None
# trim sigma because we may have trimmed the ps above.
sim_p = sl_sim(sigma, ps, q_nsims, sample_distribution)
result.append(sim_p)
else:
result.append("NA")
#"""
#result.append("NA")
yield result
def region_p(fpvals, fregions, col_num, step, z=True):
# just use 2 for col_num, but dont need the p from regions.
tree = read_regions(fregions)
process, total_coverage_sync = _get_total_coverage(fpvals, col_num, step)
region_info = _get_ps_in_regions(tree, fpvals, col_num)
acfs = _gen_acf(region_info, (fpvals, ), col_num, step)
process.join()
total_coverage = total_coverage_sync.value
# regions first and then create ACF for the longest one.
print("%i bases used as coverage for sidak correction" % \
(total_coverage), file=sys.stderr)
sample_distribution = np.array([b["p"] for b in bediter(fpvals, col_num)])
combine = z_score_combine if z else stouffer_liptak
for region, prows in region_info.items():
# gen_sigma expects a list of bed dicts.
sigma = gen_sigma_matrix(prows, acfs)
ps = np.array([prow["p"] for prow in prows])
if ps.shape[0] == 0:
print("bad region", region, file=sys.stderr)
continue
# calculate the SLK for the region.
region_slk = combine(ps, sigma)
if not region_slk["OK"]:
print("problem with:", region_slk, ps, file=sys.stderr)
slk_p = region_slk["p"]
sidak_slk_p = sidak(slk_p,
int(region[2]) - int(region[1]), total_coverage)
result = ["\t".join(region), slk_p, sidak_slk_p, "NA"]
yield result
def region_p(fpvals, fregions, col_num, step, z=True):
# just use 2 for col_num, but dont need the p from regions.
tree = read_regions(fregions)
process, total_coverage_sync = _get_total_coverage(fpvals, col_num, step)
region_info = _get_ps_in_regions(tree, fpvals, col_num)
acfs = _gen_acf(region_info, (fpvals,), col_num, step)
process.join()
total_coverage = total_coverage_sync.value
# regions first and then create ACF for the longest one.
print >>sys.stderr, "%i bases used as coverage for sidak correction" % \
(total_coverage)
sample_distribution = np.array([b["p"] for b in bediter(fpvals,
col_num)])
combine = z_score_combine if z else stouffer_liptak
for region, prows in region_info.iteritems():
# gen_sigma expects a list of bed dicts.
sigma = gen_sigma_matrix(prows, acfs)
ps = np.array([prow["p"] for prow in prows])
if ps.shape[0] == 0:
print >>sys.stderr,("bad region", region)
continue
# calculate the SLK for the region.
region_slk = combine(ps, sigma)
if not region_slk["OK"]:
print >>sys.stderr, "problem with:", region_slk, ps
slk_p = region_slk["p"]
sidak_slk_p = sidak(slk_p, int(region[2]) - int(region[1]), total_coverage)
result = ["\t".join(region), slk_p, sidak_slk_p, "NA"]
yield result