def seq_err(self, member):
"""
Calculate the probability of sequencing error. Assume each chromosome
is equally-likely to be sequenced.
The probability is drawn from a Dirichlet multinomial distribution:
This is a point of divergence from the Cartwright et al. paper
mentioned in the other functions.
When the Dirichlet multinomial is called, the max element is stored in
max_elems, so that the scaling of the probability matrix can be
manipulated later.
Args:
member: Integer representing index of the read counts for a
family member in the trio model.
Returns:
1 x 16 probability vector that needs to be multiplied by a
transition matrix.
"""
# TODO: add bias when alpha freq are added
alpha_mat = ut.get_alphas(self.seq_err_rate) * self.dm_disp
prob_mat = np.zeros((ut.GENOTYPE_COUNT))
for i, alpha in enumerate(alpha_mat):
log_proba = ut.dirichlet_multinomial(alpha, self.reads[member])
prob_mat[i] = log_proba
prob_mat_rescaled, max_elem = ut.normalspace(prob_mat)
self.max_elems.append(max_elem)
return prob_mat_rescaled
def seq_err(self, member):
"""
Calculate the probability of sequencing error. Assume each chromosome
is equally-likely to be sequenced.
The probability is drawn from a Dirichlet multinomial distribution:
This is a point of divergence from the Cartwright et al. paper
mentioned in the other functions.
When the Dirichlet multinomial is called, the max element is stored in
max_elems, so that the scaling of the probability matrix can be
manipulated later.
Args:
member: Integer representing index of the read counts for a
family member in the trio model.
Returns:
1 x 16 probability vector that needs to be multiplied by a
transition matrix.
"""
# TODO: add bias when alpha freq are added
alpha_mat = ut.get_alphas(self.seq_err_rate) * self.dm_disp
prob_mat = np.zeros((ut.GENOTYPE_COUNT))
for i, alpha in enumerate(alpha_mat):
log_proba = ut.dirichlet_multinomial(alpha, self.reads[member])
prob_mat[i] = log_proba
prob_mat_rescaled, max_elem = ut.normalspace(prob_mat)
self.max_elems.append(max_elem)
return prob_mat_rescaled
def pop_sample(self):
"""
The multinomial component of the model generates the nucleotide
frequency parameter vector (alpha_A, alpha_C, alpha_G, alpha_T) based
on the nucleotide count input data.
Probabilities are drawn from a Dirichlet multinomial distribution.
The Dirichlet component of our models uses this frequency parameter
vector in addition to the mutation rate (theta), nucleotide
frequencies [alpha_A, alpha_C, alpha_G, alpha_T], and genome
nucleotide counts [n_A, n_C, n_G, n_T].
For example: The genome mutation rate (theta) may be the small scalar
quantity \theta = 0.00025, the frequency parameter vector
(alpha_A, alpha_C, alpha_G, alpha_T) = (0.25, 0.25, 0.25, 0.25),
the genome nucleotide counts (n_A, n_C, n_G, n_T) = (4, 0, 0, 0), for
the event that both the mother and the father have genotype AA,
resulting in N = 4.
Note: This model does not follow that of the Cartwright paper
mentioned in other functions.
Set geno as the 1 x 16 probability matrix for a single parent.
Returns:
1 x 256 probability matrix in log e space where the (i, j)
element in the matrix is the probability that the mother has
genotype i and the father has genotype j where i, j in
{AA, AC, AG, AT,
CA, CC, CG, CT,
GA, GC, GG, GT,
TA, TC, TG, TT}.
The matrix is an order-relevant representation of the possible
events in the sample space that covers all possible parent
genotype combinations. For example:
[P(AAAA), P(AAAC), P(AAAG), P(AAAT), P(AACA), P(AACC), P(AACG)...]
"""
# combine parameters for call to dirichlet multinomial
muta_nt_freq = np.array([0.25 * self.pop_muta_rate for i in range(4)])
gt_count = ut.two_parent_counts()
prob_mat = np.zeros(( ut.GENOTYPE_COUNT, ut.GENOTYPE_COUNT ))
for i in range(ut.GENOTYPE_COUNT):
for j in range(ut.GENOTYPE_COUNT):
nt_count = gt_count[i, j, :] # count per 2-allele genotype
log_proba = ut.dirichlet_multinomial(muta_nt_freq, nt_count)
prob_mat[i, j] = np.exp(log_proba)
self.geno = np.sum(prob_mat, axis=0) # set one parent prob mat
return prob_mat.flatten()
def pop_sample(self):
"""
The multinomial component of the model generates the nucleotide
frequency parameter vector (alpha_A, alpha_C, alpha_G, alpha_T) based
on the nucleotide count input data.
Probabilities are drawn from a Dirichlet multinomial distribution.
The Dirichlet component of our models uses this frequency parameter
vector in addition to the mutation rate (theta), nucleotide
frequencies [alpha_A, alpha_C, alpha_G, alpha_T], and genome
nucleotide counts [n_A, n_C, n_G, n_T].
For example: The genome mutation rate (theta) may be the small scalar
quantity \theta = 0.00025, the frequency parameter vector
(alpha_A, alpha_C, alpha_G, alpha_T) = (0.25, 0.25, 0.25, 0.25),
the genome nucleotide counts (n_A, n_C, n_G, n_T) = (4, 0, 0, 0), for
the event that both the mother and the father have genotype AA,
resulting in N = 4.
Note: This model does not follow that of the Cartwright paper
mentioned in other functions.
Set geno as the 1 x 16 probability matrix for a single parent.
Returns:
1 x 256 probability matrix in log e space where the (i, j)
element in the matrix is the probability that the mother has
genotype i and the father has genotype j where i, j in
{AA, AC, AG, AT,
CA, CC, CG, CT,
GA, GC, GG, GT,
TA, TC, TG, TT}.
The matrix is an order-relevant representation of the possible
events in the sample space that covers all possible parent
genotype combinations. For example:
[P(AAAA), P(AAAC), P(AAAG), P(AAAT), P(AACA), P(AACC), P(AACG)...]
"""
# combine parameters for call to dirichlet multinomial
muta_nt_freq = np.array([0.25 * self.pop_muta_rate for i in range(4)])
gt_count = ut.two_parent_counts()
prob_mat = np.zeros(( ut.GENOTYPE_COUNT, ut.GENOTYPE_COUNT ))
for i in range(ut.GENOTYPE_COUNT):
for j in range(ut.GENOTYPE_COUNT):
nt_count = gt_count[i, j, :] # count per 2-allele genotype
log_proba = ut.dirichlet_multinomial(muta_nt_freq, nt_count)
prob_mat[i, j] = np.exp(log_proba)
self.geno = np.sum(prob_mat, axis=0) # set one parent prob mat
return prob_mat.flatten()
