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 slk_chrom(chromlist, lag_max, acfs, z=True):
"""
calculate the slk for a given chromosome
"""
for xbed, xneighbors in walk(chromlist, lag_max):
sigma = gen_sigma_matrix(xneighbors, acfs)
pvals = [g['p'] for g in xneighbors]
r = z_score_combine(pvals, sigma)
# NOTE: this commented out line show slightly better performance on
# simulated data with largish changes.
# take the min of the original and the smoothed pvalue.
#p = 1 - (1 - min(xbed['p'], r['p']))**2
#yield (xbed["chrom"], xbed["start"], xbed["end"], xbed["p"], p)
yield (xbed["chrom"], xbed["start"], xbed["end"], xbed["p"], r["p"])
def slk_chrom(chromlist, lag_max, acfs, z=True):
"""
calculate the slk for a given chromosome
"""
for xbed, xneighbors in walk(chromlist, lag_max):
sigma = gen_sigma_matrix(xneighbors, acfs)
pvals = [g['p'] for g in xneighbors]
r = z_score_combine(pvals, sigma)
# NOTE: this commented out line show slightly better performance on
# simulated data with largish changes.
# take the min of the original and the smoothed pvalue.
#p = 1 - (1 - min(xbed['p'], r['p']))**2
#yield (xbed["chrom"], xbed["start"], xbed["end"], xbed["p"], p)
yield (xbed["chrom"], xbed["start"], xbed["end"], xbed["p"], r["p"])
def slk_chrom(chromlist, lag_max, acfs, z=True):
"""
calculate the slk for a given chromosome
"""
arr = np.empty((len(chromlist), ),
dtype=np.dtype([('start', np.uint32), ('end', np.uint32),
('p', np.float32), ('slk_p', np.float32)]))
for i, (xbed, xneighbors) in enumerate(walk(chromlist, lag_max)):
sigma = gen_sigma_matrix(xneighbors, acfs)
pvals = np.array([g['p'] for g in xneighbors])
r = z_score_combine(pvals, sigma)
arr[i] = (xbed["start"], xbed["end"], xbed["p"], r["p"])
return xbed['chrom'], arr
def slk_chrom(chromlist, lag_max, acfs, z=True):
"""
calculate the slk for a given chromosome
"""
arr = np.empty((len(chromlist),), dtype=np.dtype([
('start', np.uint32),
('end', np.uint32),
('p', np.float32),
('slk_p', np.float32)]))
for i, (xbed, xneighbors) in enumerate(walk(chromlist, lag_max)):
sigma = gen_sigma_matrix(xneighbors, acfs)
pvals = np.array([g['p'] for g in xneighbors])
r = z_score_combine(pvals, sigma)
arr[i] = (xbed["start"], xbed["end"], xbed["p"], r["p"])
return xbed['chrom'], arr
def slk_chrom(chromlist, lag_max, acfs, z=False):
"""
calculate the slk for a given chromosome
"""
n_bad = 0
for xbed, xneighbors in walk(chromlist, lag_max):
sigma = gen_sigma_matrix(xneighbors, acfs)
pvals = [g['p'] for g in xneighbors]
# stringetn is True/False
if z:
r = z_score_combine(pvals, sigma)
else:
r = stouffer_liptak(pvals, sigma)
yield (xbed["chrom"], xbed["start"], xbed["end"], xbed["p"],
r["p"])
if not r["OK"] and n_bad < 20:
print >>sys.stderr, "# non-invertible %s\t%i\t%i" % \
(xbed["chrom"], xbed["start"], xbed["end"])
print >>sys.stderr, "# pvals:", ",".join(map(str, pvals[:10])) + "..."
n_bad += 1
if n_bad == 20:
print >>sys.stderr, "not reporting further un-invertibles"
