def test_get_p_value_lofs(self):
""" check for loss of function rates
"""
# construct two different tx objects, for the same gene, since otherwise
# the p-values from different runs are the same
tx1 = self.construct_gene()
rates1 = self.get_rates(tx1)
iterations = 10000
cq = 'loss_of_function'
de_novos = [5, 6]
(obs_1, p_1) = get_p_value(tx1, rates1, iterations, cq, de_novos)
tx2 = self.construct_gene()
rates2 = self.get_rates(tx2)
# make sure we can use the string 'lof' to get loss-of-function rates.
# NOTE: due to randomly sampling, this will fail ~0.1% of the time,
# purely by chance. If this fails, first try rerunning the tests.
iterations = 10000
cq = 'lof'
(obs_2, p_2) = get_p_value(tx2, rates2, iterations, cq, de_novos)
self.assertEqual(obs_1, obs_2)
self.assertTrue(abs(p_1 - p_2) < 0.017)
def test_get_p_value(self):
"""
"""
iterations = 10000
cq = 'missense'
de_novos = [5, 5]
(obs, p_value) = get_p_value(self.transcript, self.rates, iterations, cq, de_novos)
self.assertTrue(p_value < 0.04)
self.assertEqual(obs, '0.0')
def test_get_p_value_single_de_novo(self):
""" check that get_p_value() works correctly
"""
# check that we don't assess transcripts with a single de novo
iterations = 10000
cq = 'missense'
de_novos = [5]
(obs, p_value) = get_p_value(self.transcript, self.rates, iterations, cq, de_novos)
self.assertEqual((obs, p_value), ('NA', 'NA'))
def test_get_p_value_nonsignificant(self):
""" check for de novos spread across the gene
"""
iterations = 10000
cq = 'missense'
de_novos = [5, 58]
(obs, p_value) = get_p_value(self.transcript, self.rates, iterations, cq, de_novos)
self.assertTrue(p_value == 1.0)
self.assertEqual(obs, '53.0')
def test_get_p_value_single_de_novo(self):
""" check that get_p_value() works correctly
"""
# check that we don't assess transcripts with a single de novo
iterations = 10000
cq = 'missense'
de_novos = [5]
(obs, p_value) = get_p_value(self.transcript, self.rates, iterations, cq, de_novos)
self.assertTrue(math.isnan(obs))
self.assertTrue(math.isnan(p_value))
async def cluster_de_novos(symbol, de_novos, ensembl, iterations=1000000, mut_dict=None):
""" analysis proximity cluster of de novos in a single gene
Args:
symbol: HGNC symbol for a gene
de_novos: dictionary of de novo positions for the HGNC gene,
indexed by functional type
iterations: number of simulations to run
ensembl: EnsemblRequest object, for obtaing info from ensembl
mut_dict: dictionary of mutation rates, indexed by trinuclotide sequence
Returns:
a dictionary containing P values, and distances for missense, nonsense,
and synonymous de novos events. Missing data is represented by "NA".
"""
if mut_dict is None:
mut_dict = load_mutation_rates()
missense = de_novos["missense"]
nonsense = de_novos["nonsense"]
# load the set of transcripts that are the minimum set of transcripts
# required to contain all the de novos, unless we can't find any coding
# transcripts that contain the de novos.
try:
transcripts = await load_gene(ensembl, symbol, missense + nonsense)
except IndexError as e:
print(e)
return None
probs = {"miss_prob": [], "nons_prob": []}
dists = {"miss_dist": [], "nons_dist": []}
for transcript in transcripts:
missense_events = get_de_novos_in_transcript(transcript, missense)
nonsense_events = get_de_novos_in_transcript(transcript, nonsense)
rates = SiteRates(transcript, mut_dict)
(miss_dist, miss_prob) = get_p_value(transcript, rates, iterations, "missense", missense_events)
(nons_dist, nons_prob) = get_p_value(transcript, rates, iterations, "lof", nonsense_events)
dists["miss_dist"].append(miss_dist)
dists["nons_dist"].append(nons_dist)
probs["miss_prob"].append(miss_prob)
probs["nons_prob"].append(nons_prob)
# remove the de novos analysed in the current transcript, so that
# analysis of subsequent transcripts uses independent events. NOTE THAT
# THIS MIGHT MISS SOME CLUSTERING ACROSS MUTUALLY EXCLUSIVE TRANSCRIPTS
# IF THE DE NOVO EVENTS ARE NEAR THE TRANSCRIPT DIVERGENCE.
missense = [x for x in missense if x not in missense_events]
nonsense = [x for x in nonsense if x not in nonsense_events]
for key in dists:
dists[key] = ",".join([ str(x) for x in dists[key] ])
probs = {k: fishers_method(probs[k]) for k in probs}
probs.update(dists)
return probs
def cluster_de_novos(symbol, de_novos, iterations=1000000, ensembl=None, mut_dict=None):
""" analysis proximity cluster of de novos in a single gene
Args:
symbol: HGNC symbol for a gene
de_novos: dictionary of de novo positions for the HGNC gene,
indexed by functional type
iterations: number of simulations to run
ensembl: EnsemblRequest object, for obtaing info from ensembl
mut_dict: dictionary of mutation rates, indexed by trinuclotide sequence
Returns:
a dictionary containing P values, and distances for missense, nonsense,
and synonymous de novos events. Missing data is represented by "NA".
"""
if ensembl is None:
ensembl = EnsemblRequest('cache', 'grch37')
if mut_dict is None:
mut_dict = load_mutation_rates()
missense = de_novos["missense"]
nonsense = de_novos["nonsense"]
# load the set of transcripts that are the minimum set of transcripts
# required to contain all the de novos, unless we can't find any coding
# transcripts that contain the de novos.
try:
transcripts = load_gene(ensembl, symbol, missense + nonsense)
except IndexError as e:
print(e)
return None
probs = {"miss_prob": [], "nons_prob": []}
dists = {"miss_dist": [], "nons_dist": []}
for transcript in transcripts:
missense_events = get_de_novos_in_transcript(transcript, missense)
nonsense_events = get_de_novos_in_transcript(transcript, nonsense)
rates = SiteRates(transcript, mut_dict)
(miss_dist, miss_prob) = get_p_value(transcript, rates, iterations, "missense", missense_events)
(nons_dist, nons_prob) = get_p_value(transcript, rates, iterations, "lof", nonsense_events)
dists["miss_dist"].append(miss_dist)
dists["nons_dist"].append(nons_dist)
probs["miss_prob"].append(miss_prob)
probs["nons_prob"].append(nons_prob)
# remove the de novos analysed in the current transcript, so that
# analysis of subsequent transcripts uses independent events. NOTE THAT
# THIS MIGHT MISS SOME CLUSTERING ACROSS MUTUALLY EXCLUSIVE TRANSCRIPTS
# IF THE DE NOVO EVENTS ARE NEAR THE TRANSCRIPT DIVERGENCE.
missense = [x for x in missense if x not in missense_events]
nonsense = [x for x in nonsense if x not in nonsense_events]
for key in dists:
dists[key] = ",".join([ str(x) for x in dists[key] ])
probs = combine_p_values(probs)
probs.update(dists)
return probs