def run(args):
# get rid of N, just keep the correlation.
col_num = get_col_num(args.c)
col_null = get_col_num(args.null) if args.null else None
if args.qvality:
for qval, pep, l in _qvality(args.bed_file, col_num, col_null):
print "%s\t%.4g\t%4g" % (l.rstrip("\r\n"), qval, pep)
else:
for qval, l in obs_fdr(args.bed_file, col_num, col_null):
print "%s\t%.4g" % (l.rstrip("\r\n"), qval)
def run(args):
# get rid of N, just keep the correlation.
col_num = get_col_num(args.c)
col_null = get_col_num(args.null) if args.null else None
if args.qvality:
for qval, pep, l in _qvality(args.bed_file, col_num, col_null):
print "%s\t%.4g\t%4g" % (l.rstrip("\r\n"), qval, pep)
else:
for qval, l in obs_fdr(args.bed_file, col_num, col_null):
print "%s\t%.4g" % (l.rstrip("\r\n"), qval)
def run(args):
acf_vals = read_acf(args.acf)
col_num = get_col_num(args.c)
for chrom, results in adjust_pvals(args.files, col_num, acf_vals):
fmt = chrom + "\t%i\t%i\t%.5g\t%.5g\n"
for row in results:
sys.stdout.write(fmt % tuple(row))
def run(args):
acf_vals = read_acf(args.acf)
col_num = get_col_num(args.c)
for chrom, results in adjust_pvals(args.files, col_num, acf_vals):
fmt = chrom + "\t%i\t%i\t%.5g\t%.5g\n"
for row in results:
sys.stdout.write(fmt % tuple(row))
def run(args):
col_num = get_col_num(args.c)
file_iter = (l.rstrip("\r\n").split("\t")
for l in open(args.file) if l[0] != "#")
pvals = np.array([float(b[col_num]) for b in file_iter])
kwargs = {"bins": args.n} if args.n else {}
hist, bins = np.histogram(pvals, normed=True, **kwargs)
xlabels = "|".join("%.2f-%.2f" % b for b in pairwise(bins))
print "#", chart(hist, xlabels)
hist, bins = np.histogram(pvals, normed=False, **kwargs)
print "# median: %.3f mean:%.3f; std: %.3f min:%.3f; max:%.3f" % (
np.median(pvals), pvals.mean(), pvals.std(), pvals.min(), pvals.max())
try:
from scipy.stats import chisquare
chisq, p = chisquare(hist)
print "#chi-square test of uniformity. p: %.3g " \
"(low value means reject null of uniformity)" % p
except ImportError:
pass
print "#bin_start\tbin_end\tn"
for bin, val in zip(pairwise(bins), hist):
print "%.2f\t%.2f\t%i" % (bin[0], bin[1], val)
def run(args):
col_num = get_col_num(args.c)
# order in results is slk, uniform, sample
for region_line, slk, slk_sidak, sim_p in region_p(args.pvals, args.regions,
col_num, args.N, args.step, mlog=args.mlog, z=args.z):
#if sim_p != "NA":
# sim_p = "%.4g" % (sim_p)
print "%s\t%.4g\t%.4g" % (region_line, slk, slk_sidak)
def run(args):
col_num = get_col_num(args.c)
# order in results is slk, uniform, sample
for region_line, slk, slk_sidak, sim_p in region_p(args.pvals, args.regions,
col_num, args.step, z=True):
#if sim_p != "NA":
# sim_p = "%.4g" % (sim_p)
print "%s\t%.4g\t%.4g" % (region_line, slk, slk_sidak)
def run(args):
col_num = get_col_num(args.c)
# order in results is slk, uniform, sample
#for region_line, slk, slk_sidak, sim_p in region_p(args.pvals, args.regions,
for region_line, slk, slk_sidak, sim_p in region_p(args.pvals, args.regions,
col_num, args.N, args.step):
if sim_p != "NA":
sim_p = "%.4g" % (sim_p)
print "%s\t%.4g\t%.4g\t%s" % (region_line, slk, slk_sidak, sim_p)
"""
def run(args):
"""
general function that takes an args object (from argparse)
with the necessary options and calls acf()
"""
d = map(int, args.d.split(":"))
d[1] += 1 # adjust for non-inclusive end-points...
assert len(d) == 3
lags = range(*d)
acf_vals = acf(args.files, lags, get_col_num(args.c), partial=(not
args.full))
write_acf(acf_vals, sys.stdout)
def run(args):
"""
general function that takes an args object (from argparse)
with the necessary options and calls acf()
"""
d = map(int, args.d.split(":"))
assert len(d) == 3, ("-d argument must in in the format start:end:step")
d[1] += 1 # adjust for non-inclusive end-points...
lags = range(*d)
acf_vals = acf(args.files, lags, get_col_num(args.c), partial=(not
args.full))
write_acf(acf_vals, sys.stdout)
def main():
import argparse
from _common import get_col_num
p = argparse.ArgumentParser(description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
p.add_argument("-c", dest="c", help="column number that has the value to"
"take the acf", default='4')
p.add_argument("--dist", dest="dist", help="Maximum dist to extend the"
" ACF calculation", type=int)
p.add_argument("--step", dest="step", help="step size for bins in the"
" ACF calculation", type=int)
p.add_argument("--seed", dest="seed", help="A value must be at least this"
" large/small in order to seed a region.", type=float,
default=0.1)
p.add_argument("--threshold", dest="threshold", help="After seeding, a value"
" of at least this number can extend a region. ",
type=float)
p.add_argument("-p", "--prefix", dest="prefix",
help="prefix for output files", default=None)
p.add_argument("--mlog", dest="mlog", action="store_true",
default=False, help="do the correlation on the -log10 of"
"the p-values. Default is to do it on the raw values")
p.add_argument("--region-filter-p", help="max adjusted region-level p-value to be reported"
"in final output", type=float, default=1)
p.add_argument("--region-filter-n", help="require at least this many probes"
"for a region to be reported in final output", type=int, default=1)
p.add_argument('bed_files', nargs='+', help='sorted bed file to process')
args = p.parse_args()
if not (args.prefix):
sys.exit(p.print_help())
if not args.threshold:
args.threshold = args.seed
assert op.exists(args.bed_files[0])
col_num = get_col_num(args.c, args.bed_files[0])
return pipeline(col_num, args.step, args.dist, args.prefix,
args.threshold, args.seed,
args.bed_files, mlog=args.mlog,
region_filter_p=args.region_filter_p,
region_filter_n=args.region_filter_n)
def run(args):
col_num = get_col_num(args.c)
file_iter = (l.rstrip("\r\n").split("\t")
for l in ts.nopen(args.file) if l[0] != "#")
pvals = np.array([float(b[col_num]) for b in file_iter])
kwargs = {"bins": args.n} if args.n else {}
hist, bins = np.histogram(pvals, normed=True, **kwargs)
xlabels = "|".join("%.2f-%.2f" % b for b in pairwise(bins))
hist, bins = np.histogram(pvals, normed=False, **kwargs)
print("# median: %.3f mean:%.3f; std: %.3f min:%.3f; max:%.3f" % (
np.median(pvals), pvals.mean(), pvals.std(), pvals.min(), pvals.max()))
try:
from scipy.stats import chisquare
chisq, p = chisquare(hist)
print("#chi-square test of uniformity. p: %.3g " \
"(low value means reject null of uniformity)" % p)
except ImportError:
pass
print("#bin_start\tbin_end\tn")
for bin, val in zip(pairwise(bins), hist):
print("%.2f\t%.2f\t%i" % (bin[0], bin[1], val))
def main():
import argparse
from _common import get_col_num
p = argparse.ArgumentParser(description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
p.add_argument("-c", dest="c", help="column number that has the value to"
"take the acf", default='4')
p.add_argument("--dist", "--distance", dest="dist", help="Maximum dist to extend the"
" ACF calculation", type=int)
p.add_argument("--step", dest="step", help="step size for bins in the"
" ACF calculation", type=int)
p.add_argument("--seed", dest="seed", help="A value must be at least this"
" large/small in order to seed a region.", type=float,
default=0.1)
p.add_argument("--threshold", dest="threshold", help="After seeding, a value"
" of at least this number can extend a region. ",
type=float)
p.add_argument("-p", "--prefix", dest="prefix",
help="prefix for output files", default=None)
p.add_argument("-z", "--z-score", action="store_true", default=False,
help="use z-score correction instead of liptak")
p.add_argument("--genomic-control", dest="genomic_control",
help="perform the genomic control correction on the input"
" pvalues", action="store_true", default=False)
p.add_argument("--mlog", "--nlog", dest="mlog", action="store_true",
default=False, help="do the correlation on the -log10 of"
"the p-values. Default is to do it on the raw values")
p.add_argument("--region-filter-p", help="max adjusted region-level p-value"
" to be reported "
"in final output. this requires the input bed file to have"
" chrom, start, end, 't' columns", type=float, default=1)
p.add_argument("--region-filter-n", help="require at least this many probes"
"for a region to be reported in final output. "
" this requires the input bed file to have chrom, start, "
"end, 't' columns", type=int, default=None)
p.add_argument("--annotate", help="annotate with refGen from this db" \
"in UCSC (e.g. hg19) requires cruzdb", default=None)
p.add_argument('bed_files', nargs='+', help='sorted bed file to process')
args = p.parse_args()
if not (args.prefix):
sys.exit(p.print_help())
if not args.threshold:
args.threshold = args.seed
assert op.exists(args.bed_files[0])
col_num = get_col_num(args.c, args.bed_files[0])
return pipeline(col_num, args.step, args.dist, args.prefix,
args.threshold, args.seed,
args.bed_files, mlog=args.mlog,
region_filter_p=args.region_filter_p,
region_filter_n=args.region_filter_n,
genome_control=args.genomic_control,
db=args.annotate,
z=args.z_score)
def run(args):
acf_vals = read_acf(args.acf)
col_num = get_col_num(args.c)
for row in adjust_pvals(args.files, col_num, acf_vals, args.stringent):
sys.stdout.write("%s\t%i\t%i\t%.5g\t%.5g\n" % row)
def run(args):
col = get_col_num(args.c)
print(stepsize((args.bed_file,), col))
def main():
import argparse
from _common import get_col_num
p = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
p.add_argument("-c",
dest="c",
help="column number that has the value to"
"take the acf",
default='4')
p.add_argument("--dist", "--distance"
"--peak-dist",
dest="dist",
help="Maximum dist to "
" search for adjacent peaks.",
type=int)
p.add_argument("--acf-dist",
help="distance/window-size to use for "
" smoothing. Defaults to 1/3 * peak-dist ",
type=int,
default=None)
p.add_argument("--step",
dest="step",
help="step size for bins in the"
" ACF calculation",
type=int)
p.add_argument("--seed",
dest="seed",
help="A value must be at least this"
" large/small in order to seed a region.",
type=float,
default=0.05)
p.add_argument("--threshold",
dest="threshold",
help="After seeding, a value"
" of at least this number can extend a region. ",
type=float)
p.add_argument(
"--no-fdr",
dest="no_fdr",
help="Don't use FDR-corrected p-values "
"for finding peaks (either way, we still do multiple-testing correction "
"on the p-values for the regions).",
action='store_true',
default=False)
p.add_argument("-p",
"--prefix",
dest="prefix",
help="prefix for output files",
default=None)
p.add_argument("--genomic-control",
dest="genomic_control",
help="perform the genomic control correction on the input"
" pvalues",
action="store_true",
default=False)
p.add_argument("--region-filter-p",
help="max adjusted region-level p-value"
" to be reported "
"in final output. this requires the input bed file to have"
" chrom, start, end, 't' columns",
type=float,
default=1)
p.add_argument("--region-filter-n",
help="require at least this many probes"
"for a region to be reported in final output. "
" this requires the input bed file to have chrom, start, "
"end, 't' columns",
type=int,
default=None)
p.add_argument("--annotate", help="annotate with refGen from this db" \
"in UCSC (e.g. hg19) requires cruzdb", default=None)
p.add_argument('bed_files', nargs='+', help='sorted bed file to process')
args = p.parse_args()
if not (args.prefix):
sys.exit(p.print_help())
if not args.threshold:
args.threshold = args.seed
assert op.exists(args.bed_files[0])
if args.acf_dist is None:
args.acf_dist = int(round(0.33333 * args.dist, -1))
sys.stderr.write("setting --acf-dist to 0.33 * --dist == %i\n" %
args.acf_dist)
col_num = get_col_num(args.c, args.bed_files[0])
return pipeline(col_num,
args.step,
args.dist,
args.acf_dist,
args.prefix,
args.threshold,
args.seed,
args.bed_files,
region_filter_p=args.region_filter_p,
region_filter_n=args.region_filter_n,
genome_control=args.genomic_control,
db=args.annotate,
use_fdr=not args.no_fdr)
def main():
import argparse
from _common import get_col_num
p = argparse.ArgumentParser(description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
p.add_argument("-c", dest="c", help="column number that has the value to"
"take the acf", default='4')
p.add_argument("--dist", "--distance" "--peak-dist", dest="dist", help="Maximum dist to "
" search for adjacent peaks.", type=int, required=True)
p.add_argument("--acf-dist", help="distance/window-size to use for "
" smoothing. Defaults to 1/3 * peak-dist ", type=int, default=None)
p.add_argument("--step", dest="step", help="step size for bins in the"
" ACF calculation", type=int)
p.add_argument("--seed", dest="seed", help="A value must be at least this"
" large/small in order to seed a region.", type=float,
default=0.05)
p.add_argument("--threshold", dest="threshold", help="After seeding, a value"
" of at least this number can extend a region. ",
type=float)
p.add_argument("--no-fdr", dest="no_fdr", help="Don't use FDR-corrected p-values "
"for finding peaks (either way, we still do multiple-testing correction "
"on the p-values for the regions).", action='store_true',
default=False)
p.add_argument("-p", "--prefix", dest="prefix",
help="prefix for output files", default=None)
p.add_argument("--genomic-control", dest="genomic_control",
help="perform the genomic control correction on the input"
" pvalues", action="store_true", default=False)
p.add_argument("--region-filter-p", help="max adjusted region-level p-value"
" to be reported "
"in final output. this requires the input bed file to have"
" chrom, start, end, 't' columns", type=float, default=1)
p.add_argument("--region-filter-n", help="require at least this many probes"
"for a region to be reported in final output. "
" this requires the input bed file to have chrom, start, "
"end, 't' columns", type=int, default=None)
p.add_argument("--annotate", help="annotate with refGen from this db" \
"in UCSC (e.g. hg19) requires cruzdb", default=None)
p.add_argument('bed_files', nargs='+', help='sorted bed file to process')
args = p.parse_args()
if not (args.prefix):
sys.exit(p.print_help())
if not args.threshold:
args.threshold = args.seed
assert op.exists(args.bed_files[0])
if args.acf_dist is None:
args.acf_dist = int(round(0.33333 * args.dist, -1))
sys.stderr.write("setting --acf-dist to 0.33 * --dist == %i\n" %
args.acf_dist)
col_num = get_col_num(args.c, args.bed_files[0])
return pipeline(col_num, args.step,
args.dist, args.acf_dist, args.prefix,
args.threshold, args.seed,
args.bed_files,
region_filter_p=args.region_filter_p,
region_filter_n=args.region_filter_n,
genome_control=args.genomic_control,
db=args.annotate,
use_fdr=not args.no_fdr)
def run(args):
col = get_col_num(args.c)
print(stepsize((args.bed_file, ), col))
def run(args):
acf_vals = read_acf(args.acf)
col_num = get_col_num(args.c)
for row in adjust_pvals(args.files, col_num, acf_vals):
sys.stdout.write("%s\t%i\t%i\t%.5g\t%.5g\n" % row)