def P_number_true_obs_slow(args): param = Param(args.mean, args.stddev, args.cov, args.readlen, args.soft, args.soft) E_true_links = 0 # the diagonal of the square (i_1 = i_2) i.e. do not multiply by two p_at_least_one_bp_at_given_position = 1- P_breakpoints_in_interval(1, args.bp_ratio, 0) for i in range((args.readlen - args.soft),args.mean + 4*args.stddev +1): print i p = P_breakpoints_in_interval(i, args.bp_ratio, 0) if i != args.mean + 4*args.stddev: E_true_links += p**2 * p_at_least_one_bp_at_given_position**2 * mean_span_coverage(i, i, args.insertion_size, param) else: E_true_links += p**2 * mean_span_coverage(i, i, args.insertion_size, param) for i_1 in range((args.readlen - args.soft),args.mean + 4*args.stddev): for i_2 in range(i_1+1, args.mean + 4*args.stddev + 1): #print i_1,i_2 p_1 = P_breakpoints_in_interval(i_1, args.bp_ratio, 0) p_2 = P_breakpoints_in_interval(i_2, args.bp_ratio, 0) # symmetrical probabilities if i_2 != args.mean + 4*args.stddev: E_true_links += 2 * p_1 * p_2 * p_at_least_one_bp_at_given_position**2 * mean_span_coverage(i_1, i_2, args.insertion_size, param) else: E_true_links += 2 * p_1 * p_2 * p_at_least_one_bp_at_given_position * mean_span_coverage(i_1, i_2, args.insertion_size, param) return E_true_links
def P_number_true_obs_slow(args):
param = Param(args.mean, args.stddev, args.cov, args.readlen, args.soft,
args.soft)
E_true_links = 0
# the diagonal of the square (i_1 = i_2) i.e. do not multiply by two
p_at_least_one_bp_at_given_position = 1 - P_breakpoints_in_interval(
1, args.bp_ratio, 0)
for i in range((args.readlen - args.soft),
args.mean + 4 * args.stddev + 1):
print i
p = P_breakpoints_in_interval(i, args.bp_ratio, 0)
if i != args.mean + 4 * args.stddev:
E_true_links += p**2 * p_at_least_one_bp_at_given_position**2 * mean_span_coverage(
i, i, args.insertion_size, param)
else:
E_true_links += p**2 * mean_span_coverage(
i, i, args.insertion_size, param)
for i_1 in range((args.readlen - args.soft), args.mean + 4 * args.stddev):
for i_2 in range(i_1 + 1, args.mean + 4 * args.stddev + 1):
#print i_1,i_2
p_1 = P_breakpoints_in_interval(i_1, args.bp_ratio, 0)
p_2 = P_breakpoints_in_interval(i_2, args.bp_ratio, 0)
# symmetrical probabilities
if i_2 != args.mean + 4 * args.stddev:
E_true_links += 2 * p_1 * p_2 * p_at_least_one_bp_at_given_position**2 * mean_span_coverage(
i_1, i_2, args.insertion_size, param)
else:
E_true_links += 2 * p_1 * p_2 * p_at_least_one_bp_at_given_position * mean_span_coverage(
i_1, i_2, args.insertion_size, param)
return E_true_links
def coverage_probability(self,nr_obs, a, mean_lib, stddev_lib,z, coverage_mean, read_len, s_inner,s_outer, b=None, coverage_model = False):
''' Distribution P(o|c,z) for prior probability over coverage.
This probability distribution is implemented as an poisson
distribution.
Attributes:
c -- coverage
mean -- mean value of poisson distribution.
Returns probability P(c)
'''
if not b:
# only one reference sequence.
# We split the reference sequence into two equal
# length sequences to fit the model.
a = a/2
b = a/2
param = Param(mean_lib, stddev_lib, coverage_mean, read_len, s_inner,s_outer)
lambda_ = mean_span_coverage(a, b, z, param)
if coverage_model == 'Poisson':
return poisson.pmf(nr_obs, lambda_, loc=0)
elif coverage_model == 'NegBin':
p = 0.01
n = (p*lambda_)/(1-p)
return nbinom.pmf(nr_obs, n, p, loc=0)
else:
# This is equivalent to uniform coverage
return 1 #uniform.pdf(nr_obs, loc=lambda_- 0.3*lambda_, scale=lambda_ + 0.3*lambda_ )
def coverage_probability(self,
nr_obs,
a,
mean_lib,
stddev_lib,
z,
coverage_mean,
read_len,
s_inner,
s_outer,
b=None,
coverage_model=False):
''' Distribution P(o|c,z) for prior probability over coverage.
This probability distribution is implemented as an poisson
distribution.
Attributes:
c -- coverage
mean -- mean value of poisson distribution.
Returns probability P(c)
'''
if not b:
# only one reference sequence.
# We split the reference sequence into two equal
# length sequences to fit the model.
a = a / 2
b = a / 2
param = Param(mean_lib, stddev_lib, coverage_mean, read_len, s_inner,
s_outer)
lambda_ = mean_span_coverage(a, b, z, param)
if coverage_model == 'Poisson':
return poisson.pmf(nr_obs, lambda_, loc=0)
elif coverage_model == 'NegBin':
p = 0.01
n = (p * lambda_) / (1 - p)
return nbinom.pmf(nr_obs, n, p, loc=0)
else:
# This is equivalent to uniform coverage
return 1 #uniform.pdf(nr_obs, loc=lambda_- 0.3*lambda_, scale=lambda_ + 0.3*lambda_ )
