def calc_qval(study_n, pop_n, pop, assoc, term_pop, obo_dag, T=500):
"""Generate p-value distribution for FDR based on resampling."""
import fisher
from goatools.ratio import count_terms
print(("Generate p-value distribution for FDR "
"based on resampling (this might take a while)"),
file=sys.stderr)
distribution = []
for i in range(T):
new_study = random.sample(pop, study_n)
new_term_study = count_terms(new_study, assoc, obo_dag)
smallest_p = 1
for term, study_count in list(new_term_study.items()):
pop_count = term_pop[term]
p = fisher.pvalue_population(study_count, study_n, pop_count,
pop_n)
if p.two_tail < smallest_p:
smallest_p = p.two_tail
distribution.append(smallest_p)
if i % 10 == 0:
print("Sample {0} / {1}: p-value {2}".\
format(i, T, smallest_p), file=sys.stderr)
return distribution
def calc_qval(study_n, pop_n,
pop, assoc, term_pop, obo_dag, T=500):
"""Generate p-value distribution for FDR based on resampling."""
import fisher
from goatools.ratio import count_terms
print(("Generate p-value distribution for FDR "
"based on resampling (this might take a while)"), file=sys.stderr)
distribution = []
for i in range(T):
new_study = random.sample(pop, study_n)
new_term_study = count_terms(new_study, assoc, obo_dag)
smallest_p = 1
for term, study_count in list(new_term_study.items()):
pop_count = term_pop[term]
p = fisher.pvalue_population(study_count,
study_n,
pop_count,
pop_n)
if p.two_tail < smallest_p:
smallest_p = p.two_tail
distribution.append(smallest_p)
if i % 10 == 0:
print("Sample {0} / {1}: p-value {2}".\
format(i, T, smallest_p), file=sys.stderr)
return distribution
def calc_qval(study_n, pop_n,
pop, assoc, term_pop, obo_dag, T=500):
"""Generate p-value distribution for FDR based on resampling."""
from goatools.pvalcalc import FisherFactory
from goatools.ratio import count_terms
sys.stderr.write("Generate p-value distribution for FDR "
"based on resampling (this might take a while)\n")
distribution = []
calc_pvalue = FisherFactory().pval_obj.calc_pvalue
for i in range(T):
new_study = random.sample(pop, study_n)
new_term_study = count_terms(new_study, assoc, obo_dag)
smallest_p = 1
for term, study_count in list(new_term_study.items()):
pop_count = term_pop[term]
p_uncorrected = calc_pvalue(study_count,
study_n,
pop_count,
pop_n)
if p_uncorrected < smallest_p:
smallest_p = p_uncorrected
distribution.append(smallest_p)
if i % 10 == 0:
sys.stderr.write("Sample {0} / {1}: "
"p-value {2}\n".format(i, T, smallest_p))
return distribution
def _run_multitest_local(self, ntmt):
"""Use multitest mthods that have been implemented locally."""
corrected_pvals = None
method = ntmt.nt_method.method
if method == "bonferroni":
corrected_pvals = Bonferroni(
ntmt.pvals, ntmt.alpha).corrected_pvals
elif method == "sidak":
corrected_pvals = Sidak(ntmt.pvals, ntmt.alpha).corrected_pvals
elif method == "holm":
corrected_pvals = HolmBonferroni(
ntmt.pvals, ntmt.alpha).corrected_pvals
elif method == "fdr":
# get the empirical p-value distributions for FDR
term_pop = getattr(self, 'term_pop', None)
if term_pop is None:
term_pop = count_terms(self.pop, self.assoc, self.obo_dag)
p_val_distribution = calc_qval(len(ntmt.study),
self.pop_n,
self.pop, self.assoc,
term_pop, self.obo_dag)
corrected_pvals = FDR(p_val_distribution,
ntmt.results, ntmt.alpha).corrected_pvals
self._update_pvalcorr(ntmt, corrected_pvals)
def _run_multitest_local(self, ntmt):
"""Use multitest mthods that have been implemented locally."""
corrected_pvals = None
method = ntmt.nt_method.method
if method == "bonferroni":
corrected_pvals = Bonferroni(ntmt.pvals, ntmt.alpha).corrected_pvals
elif method == "sidak":
corrected_pvals = Sidak(ntmt.pvals, ntmt.alpha).corrected_pvals
elif method == "holm":
corrected_pvals = HolmBonferroni(ntmt.pvals, ntmt.alpha).corrected_pvals
elif method == "fdr":
# get the empirical p-value distributions for FDR
term_pop = getattr(self, 'term_pop', None)
if term_pop is None:
term_pop = count_terms(self.pop, self.assoc, self.obo_dag)
p_val_distribution = calc_qval(len(ntmt.study),
self.pop_n,
self.pop, self.assoc,
term_pop, self.obo_dag)
corrected_pvals = FDR(p_val_distribution,
ntmt.results, ntmt.alpha).corrected_pvals
self._update_pvalcorr(ntmt, corrected_pvals)
