help="indent GO terms")
(opts, args) = p.parse_args()
bad = check_bad_args(args)
if bad:
print(bad)
sys.exit(p.print_help())
min_ratio = opts.ratio
if min_ratio is not None:
assert 1 <= min_ratio <= 2
assert 0 < opts.alpha < 1, "Test-wise alpha must fall between (0, 1)"
study_fn, pop_fn, assoc_fn = args
study, pop = read_geneset(study_fn, pop_fn, compare=opts.compare)
assoc = read_associations(assoc_fn)
methods = ["bonferroni", "sidak", "holm"]
if opts.fdr:
methods.append("fdr")
obo_dag = GODag(obo_file="go-basic.obo")
g = GOEnrichmentStudy(pop,
assoc,
obo_dag,
alpha=opts.alpha,
study=study,
methods=methods)
g.print_summary(min_ratio=min_ratio, indent=opts.indent, pval=opts.pval)
study, pop = read_geneset(study_fn, pop_fn, compare=args.compare)
assoc = read_associations(assoc_fn)
methods = ["bonferroni", "sidak", "holm"]
if args.fdr:
methods.append("fdr")
starttime = time.clock()
# obo_dag = GODag(obo_file=args.obo)
obo_dag = read_data()
endtime = time.clock()
f = open('E:/time.txt', 'w')
f.write(str(endtime - starttime))
f.close()
print(str(endtime - starttime))
# save_data(obo_dag)
# obo_dag=read_data()
g = GOEnrichmentStudy(pop,
assoc,
obo_dag,
alpha=args.alpha,
study=study,
methods=methods)
endtime = time.clock()
f = open('E:/time1.txt', 'w')
f.write(str(endtime - starttime))
f.close()
# print (endtime - starttime)
g.print_summary(min_ratio=min_ratio, indent=args.indent, pval=args.pval)
action='store_true',
help="Calculate the false discovery rate (alt. to the "
"Bonferroni but slower)")
p.add_option('--indent', dest='indent', default=False,
action='store_true', help="indent GO terms")
(opts, args) = p.parse_args()
bad = check_bad_args(args)
if bad:
print bad
sys.exit(p.print_help())
min_ratio = opts.ratio
if min_ratio is not None:
assert 1 <= min_ratio <= 2
assert 0 < opts.alpha < 1, "Test-wise alpha must fall between (0, 1)"
study_fn, pop_fn, assoc_fn = args
study, pop = read_geneset(study_fn, pop_fn, compare=opts.compare)
assoc = read_associations(assoc_fn)
methods = ["bonferroni", "sidak", "holm"]
if opts.fdr:
methods.append("fdr")
obo_dag = GODag(obo_file="gene_ontology.1_2.obo")
g = GOEnrichmentStudy(pop, assoc, obo_dag, alpha=opts.alpha,
study=study, methods=methods)
g.print_summary(min_ratio=min_ratio, indent=opts.indent, pval=opts.pval)
p.add_option('--fdr', dest='fdr', default=False,
action='store_true',
help="calculate the false discovery rate (alternative to the Bonferroni correction)")
p.add_option('--indent', dest='indent', default=False,
action='store_true', help="indent GO terms")
(opts, args) = p.parse_args()
bad = check_bad_args(args)
if bad:
print bad
sys.exit(p.print_help())
alpha = float(opts.alpha) if opts.alpha else 0.05
min_ratio = opts.ratio
if not min_ratio is None:
assert 1 <= min_ratio <= 2
study_fn, pop_fn, assoc_fn = args
study, pop = read_geneset(study_fn, pop_fn, compare=opts.compare)
assoc = read_associations(assoc_fn)
methods=["bonferroni", "sidak", "holm"]
if opts.fdr:
methods.append("fdr")
obo_dag = GODag(obo_file="gene_ontology.1_2.obo")
g = GOEnrichmentStudy(pop, assoc, obo_dag, alpha=alpha, study=study, methods=methods)
g.print_summary(min_ratio=min_ratio, indent=opts.indent)
study, pop = read_geneset(study_fn, pop_fn, compare=args.compare)
print("Study: {0} vs. Population {1}".format(len(study), len(pop)), file=sys.stderr)
if not args.compare: # sanity check
if len(pop) < len(study):
exit("\nERROR: The study file contains more elements than the population file. "
"Please check that the study file is a subset of the population file.\n")
# check the fraction of genomic ids that overlap between study
# and population
overlap = float(len(study & pop)) / len(study)
if 0.7 < overlap < 0.95:
sys.stderr.write("\nWARNING: only {} fraction of genes/proteins in study are found in "
"the population background.\n\n".format(overlap))
if overlap <= 0.7:
exit("\nERROR: only {} of genes/proteins in the study are found in the "
"background population. Please check.\n".format(overlap))
assoc = read_associations(assoc_fn)
methods = ["bonferroni", "sidak", "holm"]
if args.fdr:
methods.append("fdr")
obo_dag = GODag(obo_file=args.obo)
propagate_counts = not args.no_propagate_counts
g = GOEnrichmentStudy(pop, assoc, obo_dag,
propagate_counts=propagate_counts,
alpha=args.alpha,
study=study, methods=methods)
g.print_summary(min_ratio=min_ratio, indent=args.indent, pval=args.pval)
'$in': list(forward_loci)
}}, {'_id': True})
]
# One of Ana's Sample
study_indexDB = '/home/gstupp/01_2015_mass_spec/H1_11082014/1108_Gly1_2014_12_15_15_29205/dtaselect_results_sfp0.01_p2/DTASelect-filter.txt'
study_ps = build_proteins_from_peptides.main(study_indexDB)
study_loci = set(chain(*[x['forward_loci'] for x in study_ps]))
study = setup_study_pop(study_loci)
# One of Sandip's microbiome samples
pop_indexDB = '/home/gstupp/01_2015_mass_spec/120314_SC_sampleH1sol_HCD35/DTASelect-filter.txt'
pop_ps = build_proteins_from_peptides.main(pop_indexDB)
pop_loci = set(chain(*[x['forward_loci'] for x in pop_ps]))
pop = setup_study_pop(study_loci and pop_loci)
# set up hash -> GO matching
assoc = setup_association(study_loci and pop_loci)
obo_dag = GODag(obo_file=os.path.expanduser("~/go/go-basic.obo"))
study_sub = study[:1000]
g = GOEnrichmentStudy(pop,
assoc,
obo_dag,
alpha=0.05,
study=study,
methods=["fdr"])
g.print_summary(min_ratio=None, indent=False, pval=None)
def check_enrichment(study_fn,
pop_fn,
assoc_fn,
print_summary=False,
save_summary=True,
savepath=None,
obo_dag=None):
p = optparse.OptionParser(__doc__)
p.add_option('--alpha',
default=0.05,
type="float",
help="Test-wise alpha for multiple testing "
"[default: %default]")
p.add_option('--pval',
default=None,
type="float",
help="Family-wise alpha (whole experiment), only print out "
"Bonferroni p-value is less than this value. "
"[default: %default]")
p.add_option('--compare',
dest='compare',
default=False,
action='store_true',
help="the population file as a comparison group. if this "
"flag is specified, the population is used as the study "
"plus the `population/comparison`")
p.add_option('--ratio',
dest='ratio',
type='float',
default=None,
help="only show values where the difference between study "
"and population ratios is greater than this. useful for "
"excluding GO categories with small differences, but "
"containing large numbers of genes. should be a value "
"between 1 and 2. ")
p.add_option('--fdr',
dest='fdr',
default=False,
action='store_true',
help="Calculate the false discovery rate (alt. to the "
"Bonferroni but slower)")
p.add_option('--indent',
dest='indent',
default=False,
action='store_true',
help="indent GO terms")
(opts, args) = p.parse_args()
args = [study_fn, pop_fn, assoc_fn]
bad = check_bad_args(args)
if bad:
print(bad)
sys.exit(p.print_help())
min_ratio = opts.ratio
if min_ratio is not None:
assert 1 <= min_ratio <= 2
assert 0 < opts.alpha < 1, "Test-wise alpha must fall between (0, 1)"
study_fn, pop_fn, assoc_fn = args
study, pop = read_geneset(study_fn, pop_fn, compare=opts.compare)
assoc = read_associations(assoc_fn)
methods = ["bonferroni", "sidak", "holm"]
if opts.fdr:
methods.append("fdr")
if obo_dag is None:
obo_file = "go-basic.obo"
obo_dag = GODag(obo_file=obo_file)
g = GOEnrichmentStudy(pop,
assoc,
obo_dag,
alpha=opts.alpha,
methods=methods)
results = g.run_study(study)
if print_summary:
g.print_summary(results,
min_ratio=min_ratio,
indent=opts.indent,
pval=opts.pval)
if save_summary:
if savepath is None:
savepath = study_fn.replace(
study_fn.split("/")[-1],
"enrichment_" + study_fn.split("/")[-1])
g.wr_tsv(savepath, results)
