def multiset_banded_genotype_combinations(sample_genotypes, bandwidth):
for index_combo in multiset.multichoose(len(samples), range(bandwidth)):
for index_permutation in multiset.permutations(index_combo):
yield [
genotypes[index] for index, genotypes in zip(
index_permutation, sample_genotypes)
]
def data_likelihood_exact(genotype, observed_alleles):
"""'Exact' data likelihood, sum of sampling probability * join Q score for
the observed alleles over all possible underlying 'true allele'
combinations."""
#print "probability that observations", [o['alt'] for o in observed_alleles], "arise from genotype", genotype
observation_count = len(observed_alleles)
ploidy = sum([count for allele, count in genotype])
allele_probs = [count / float(ploidy) for allele, count in genotype]
probs = []
# for all true allele combinations X permutations
for true_allele_combination in multiset.multichoose(observation_count, [x[0] for x in genotype]):
for true_allele_permutation in multiset.permutations(true_allele_combination):
# this mapping allows us to use sampling_prob the same way as we do when we use JSON allele observation records
true_alleles = [{'alt':allele} for allele in true_allele_permutation]
allele_groups = group_alleles(true_alleles)
observations = []
for allele, count in genotype:
if allele_groups.has_key(allele):
observations.append(len(allele_groups[allele]))
else:
observations.append(0)
#sprob = dirichlet_maximum_likelihood_ratio(allele_probs, observations) # distribution parameter here
lnsampling_prob = multinomialln(allele_probs, observations)
prob = lnsampling_prob + likelihood_given_true_alleles(observed_alleles, true_alleles)
#print math.exp(prob), sprob, genotype, true_allele_permutation
#print genotype, math.exp(prob), sprob, true_allele_permutation, [o['alt'] for o in observed_alleles]
probs.append(prob)
# sum the individual probability of all combinations
p = logsumexp(probs)
#print math.exp(p)
return p
def data_likelihood_exact(genotype, observed_alleles):
"""'Exact' data likelihood, sum of sampling probability * join Q score for
the observed alleles over all possible underlying 'true allele'
combinations."""
#print "probability that observations", [o['alt'] for o in observed_alleles], "arise from genotype", genotype
observation_count = len(observed_alleles)
ploidy = sum([count for allele, count in genotype])
allele_probs = [count / float(ploidy) for allele, count in genotype]
probs = []
# for all true allele combinations X permutations
for true_allele_combination in multiset.multichoose(
observation_count, [x[0] for x in genotype]):
for true_allele_permutation in multiset.permutations(
true_allele_combination):
# this mapping allows us to use sampling_prob the same way as we do when we use JSON allele observation records
true_alleles = [{
'alt': allele
} for allele in true_allele_permutation]
allele_groups = group_alleles(true_alleles)
observations = []
for allele, count in genotype:
if allele_groups.has_key(allele):
observations.append(len(allele_groups[allele]))
else:
observations.append(0)
#sprob = dirichlet_maximum_likelihood_ratio(allele_probs, observations) # distribution parameter here
lnsampling_prob = multinomialln(allele_probs, observations)
prob = lnsampling_prob + likelihood_given_true_alleles(
observed_alleles, true_alleles)
#print math.exp(prob), sprob, genotype, true_allele_permutation
#print genotype, math.exp(prob), sprob, true_allele_permutation, [o['alt'] for o in observed_alleles]
probs.append(prob)
# sum the individual probability of all combinations
p = logsumexp(probs)
#print math.exp(p)
return p
genotypes) in zip(index_permutation, sample_genotypes)]
def genotype_str(genotype):
return fold(operator.add, [allele * count for allele, count in genotype])
if __name__ == '__main__':
ploidy = 2 # assume ploidy 2 for all individuals and all positions
potential_alleles = ['A', 'T', 'G', 'C']
# genotypes are expressed as sets of allele frequencies
genotypes = list_genotypes_to_count_genotypes(
list(multiset.multichoose(ploidy, potential_alleles)))
for line in sys.stdin:
position = cjson.decode(line)
#print position['position']
samples = position['samples']
position['coverage'] = sum([
len(sample['alleles'])
for samplename, sample in samples.iteritems()
])
#potential_alleles = ['A','T','G','C']
potential_alleles = set()
for samplename, sample in samples.items():
# only process snps and reference alleles
def multiset_banded_genotype_combinations(sample_genotypes, bandwidth):
for index_combo in multiset.multichoose(len(samples), range(bandwidth)):
for index_permutation in multiset.permutations(index_combo):
yield [genotypes[index] for index, genotypes in zip(index_permutation, sample_genotypes)]
for j in range(1, band_depth): # band_depth is the depth to which we explore the bandwith... TODO explain better
indexes = j * [i] + (len(sample_genotypes) - j) * [0]
for index_permutation in multiset.permutations(indexes):
yield [(sample, genotypes[index]) for index, (sample, genotypes) in zip(index_permutation, sample_genotypes)]
def genotype_str(genotype):
return reduce(operator.add, [allele * count for allele, count in genotype])
if __name__ == '__main__':
ploidy = 2 # assume ploidy 2 for all individuals and all positions
potential_alleles = ['A','T','G','C']
# genotypes are expressed as sets of allele frequencies
genotypes = list_genotypes_to_count_genotypes(list(multiset.multichoose(ploidy, potential_alleles)))
for line in sys.stdin:
position = cjson.decode(line)
#print position['position']
samples = position['samples']
position['coverage'] = sum([len(sample['alleles']) for samplename, sample in samples.iteritems()])
#potential_alleles = ['A','T','G','C']
potential_alleles = set()
for samplename, sample in samples.items():
# only process snps and reference alleles
alleles = [allele for allele in sample['alleles'] if allele['type'] in ['reference', 'snp']]
alleles = alleles_quality_to_lnprob(alleles)
sample['alleles'] = alleles
