def generate_conditional_ps(self):
# p(TiN|Somatic) and p(TiN|Germline)
t_het_direction = np.ones([self.number_of_sites, len(self.af)])
t_het_direction[:, 0:np.int(np.round(np.true_divide(len(self.af), 2)))] = -1
self.afexp = np.repeat(np.expand_dims(self.af, 1), self.number_of_sites, axis=1).T
t_af_w = beta._cdf(self.afexp, np.expand_dims(self.t_alt_count + 1, 1),
np.expand_dims(self.t_ref_count + 1, 1)) - beta._cdf(self.afexp - 0.005,
np.expand_dims(self.t_alt_count + 1, 1),
np.expand_dims(self.t_ref_count + 1, 1))
f_t_af = self.skew - np.abs(self.skew - self.afexp)
t_af = np.multiply(self.afexp, np.expand_dims(self.n_depth, 1))
psi_t_af = self.skew - f_t_af
psi_t_af = np.multiply(psi_t_af, t_het_direction)
for TiN_idx, TiN in enumerate(self.TiN_range):
n_ac_given_tin = np.multiply(t_af, np.expand_dims(self.CN_ratio[:, TiN_idx], 1))
exp_f = self.skew + np.multiply(psi_t_af, np.expand_dims(self.CN_ratio[:, TiN_idx], 1))
n_het_ac_given_tin = np.multiply(exp_f, self.n_depth[:, np.newaxis])
self.p_TiN_given_S[:, TiN_idx] += np.sum(
np.multiply(beta._cdf(np.expand_dims(self.normal_f[:] + .01, 1), n_ac_given_tin + 1,
self.n_depth[:, np.newaxis] - n_ac_given_tin + 1) -
beta._cdf(np.expand_dims(self.normal_f[:], 1), n_ac_given_tin + 1,
self.n_depth[:, np.newaxis] - n_ac_given_tin + 1), t_af_w), axis=1)
self.p_TiN_given_het[:, TiN_idx] += np.sum(
np.multiply(beta._cdf(np.expand_dims(self.normal_f[:] + .01, 1), n_het_ac_given_tin + 1,
self.n_depth[:, np.newaxis] - n_het_ac_given_tin + 1) -
beta._cdf(np.expand_dims(self.normal_f[:], 1), n_het_ac_given_tin + 1,
self.n_depth[:, np.newaxis] - n_het_ac_given_tin + 1), t_af_w), axis=1)
self.p_artifact = beta._cdf(self.normal_f + .01, self.t_alt_count + 1, self.t_ref_count + 1) - beta._cdf(
self.normal_f, self.t_alt_count + 1, self.t_ref_count + 1)
self.p_TiN_given_G = np.multiply(1 - self.p_artifact[:, np.newaxis], self.p_TiN_given_het) + np.multiply(
self.p_artifact[:, np.newaxis], 1 - self.p_TiN_given_het)
def calculate_TiN_likelihood(self):
self.t_alt_count = self.hets.as_matrix(['ALT_COUNT_T'])
self.t_ref_count = self.hets.as_matrix(['REF_COUNT_T'])
self.afexp = np.repeat(np.expand_dims(self.af, 1), len(self.hets), axis=1).T
t_af_w = beta._cdf(self.afexp, self.t_alt_count + 1, self.t_ref_count + 1) - beta._cdf(self.afexp-0.005, self.t_alt_count + 1, self.t_ref_count + 1)
f_t_af = self.mu_af_n - np.abs(self.mu_af_n - self.afexp)
psi_t_af = self.mu_af_n - f_t_af
psi_t_af = np.multiply(psi_t_af, np.expand_dims(self.hets['d'], 1))
self.n_alt_count = np.squeeze(self.hets.as_matrix(['ALT_COUNT_N']))
self.n_ref_count = np.squeeze(self.hets.as_matrix(['REF_COUNT_N']))
self.p_TiN = np.zeros([len(self.hets), self.resolution])
for i, f in enumerate(self.af):
exp_f = self.mu_af_n + np.multiply(np.expand_dims(psi_t_af[:, i], 1), self.CN_ratio)
exp_f[exp_f < 0] = 0
self.p_TiN += np.multiply(beta._pdf(exp_f, np.expand_dims(self.n_alt_count + 1, 1),
np.expand_dims(self.n_ref_count + 1, 1)) * 0.01,
np.expand_dims(t_af_w[:, i], 1))
seg_var = np.zeros([len(self.segs), 1])
TiN_MAP = np.zeros([len(self.segs), 1], dtype=int)
TiN_likelihood = np.zeros([len(self.segs), self.resolution])
TiN_post = np.zeros([len(self.segs), self.resolution])
counter = 0
for seg_id, seg in self.segs.iterrows():
self.seg_likelihood[seg_id] = np.sum(
np.log(self.p_TiN[np.array(self.hets['seg_id'] == seg_id, dtype=bool)]), axis=0)
seg_var[counter] = np.nanvar(
np.argmax(self.p_TiN[np.array(self.hets['seg_id'] == seg_id, dtype=bool)], axis=0))
TiN_MAP[counter] = np.nanargmax(self.seg_likelihood[seg_id])
TiN_likelihood[counter, :] = np.sum(np.log(self.p_TiN[np.array(self.hets['seg_id'] == seg_id, dtype=bool)]),
axis=0)
prior = np.true_divide(np.ones([1, self.resolution]), self.resolution)
TiN_post[counter, :] = TiN_likelihood[counter, :] + np.log(prior)
TiN_post[counter, :] = TiN_post[counter, :] + (1 - np.max(TiN_post[counter, :]))
TiN_post[counter, :] = np.exp(TiN_post[counter, :])
TiN_post[counter, :] = np.true_divide(TiN_post[counter, :], np.sum(TiN_post[counter, :]))
counter += 1
self.TiN_post_seg = TiN_post
self.segs.loc[:, ('TiN_var')] = seg_var
self.segs.loc[:, ('TiN_MAP')] = self.TiN_range[TiN_MAP] * 100
self.TiN_likelihood_matrix = TiN_likelihood