def prepare_run(self): # study_n should be the same in genome vs. observed vs. abundance_corrected
'''
:return: None
'''
if self.abcorr:
self.study_an_frset = self.ui.get_sample_an_frset()
self.term_study, self.go2ans_study_dict, study_n = ratio.count_terms_v2(self.study_an_frset, self.assoc_dict, self.obo_dag)
if self.randomSample:
self.pop_an_set = self.ui.get_background_an_set_random_sample()
pop_n = len(self.pop_an_set)
self.term_pop, self.go2ans_pop_dict = ratio.count_terms(self.pop_an_set, self.assoc_dict, self.obo_dag)
else:
pop_n = study_n
self.term_pop, self.go2ans_pop_dict = ratio.count_terms_abundance_corrected(self.ui, self.assoc_dict, self.obo_dag)
else:
if self.ui.col_background_an == 'Genome':
self.study_an_frset = self.ui.get_sample_an_frset_genome()
else:
self.study_an_frset = self.ui.get_sample_an_frset()
self.term_study, self.go2ans_study_dict, study_n = ratio.count_terms_v2(self.study_an_frset, self.assoc_dict, self.obo_dag)
self.pop_an_set = self.ui.get_background_an_all_set()
self.term_pop, self.go2ans_pop_dict, pop_n = ratio.count_terms_v2(self.pop_an_set, self.assoc_dict, self.obo_dag)
self.run_study_v2(self.term_study, self.term_pop, study_n, pop_n)
def calc_qval_dbl(study_n, pop_n, pop, assoc, term_pop, obo_dag, T=500):
"""
:param study_n: Integer (number of ANs from sample frequency)
:param pop_n: Integer (number of ANs from background frequency = sample freq.)
:param pop:
:param assoc:
:param term_pop:
:param obo_dag:
:param T:
:return:
"""
distribution = []
for i in range(T):
new_study = random.sample(pop, study_n) # add pop and study
new_term_study = count_terms(new_study, assoc, obo_dag)[0] #!!!
smallest_p = 1
for term, study_count in list(new_term_study.items()):
pop_count = term_pop[term]
a = study_count
b = study_n - study_count
c = pop_count
d = pop_n - pop_count
p_two_tail = stats.fisher_exact([[a, b], [c, d]], alternative='greater')[1]
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_dbl(study_n, pop_n, pop, assoc, term_pop, obo_dag, T=500):
"""
:param study_n: Integer (number of ANs from sample frequency)
:param pop_n: Integer (number of ANs from background frequency = sample freq.)
:param pop:
:param assoc:
:param term_pop:
:param obo_dag:
:param T:
:return:
"""
distribution = []
for i in range(T):
new_study = random.sample(pop, study_n) # add pop and study
new_term_study = count_terms(new_study, assoc, obo_dag)[0] #!!!
smallest_p = 1
for term, study_count in list(new_term_study.items()):
pop_count = term_pop[term]
a = study_count
b = study_n - study_count
c = pop_count
d = pop_n - pop_count
p_two_tail = stats.fisher_exact([[a, b], [c, d]], alternative='greater')[1]
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