def infer_synthetic_energy_model(num_reads=100000):
"""the whole show: infer the energy model from true reads"""
G = len(genome)
w = 10
true_matrix = [[-2, 0, 0, 0] for _ in range(w)]
true_mu = -20
true_eps = score_genome_np(true_matrix, genome)
true_ps = fd_solve_np(true_eps, true_mu)
MFL = 250 #mean frag length = 250bp
lamb = 1/250.0
true_reads = reads_from_ps(true_ps, MFL, min_seq_len=75, num_reads=num_reads)
true_rdm = density_from_reads(true_reads, G)
init_matrix = random_energy_matrix(w)
init_mu = -20
init_scores = score_genome_np(init_matrix, genome)
init_state = ((init_matrix, init_mu), init_scores)
logf = lambda state:timestamp(complete_log_likelihood(state, true_rdm, lamb, num_reads=num_reads))
rprop = lambda state:complete_rprop(state, genome)
verbose = True
iterations = 50000
print "true_ll:", logf(((true_matrix, true_mu), true_eps))
matrix_chain = mh(logf, proposal=rprop, x0=init_state, dprop=log_dprop,
capture_state=capture_state, verbose=verbose,
use_log=True, iterations=iterations, modulus=100)
return matrix_chain
def infer_arca_energy_model(num_reads=1000000):
"""the whole show: infer the energy model from true reads"""
true_reads = get_arca_reads(num_reads)
G = len(genome)
lamb = 1/250.0
true_rdm = density_from_reads(true_reads, G)
w = 10
init_matrix = random_energy_matrix(w)
init_mu = -20
init_scores = score_genome_np(init_matrix, genome)
init_state = ((init_matrix, init_mu), init_scores)
logf = lambda state:timestamp(complete_log_likelihood(state, true_rdm, lamb, num_reads))
rprop = lambda state:complete_rprop(state, genome)
verbose = True
iterations = 50000
matrix_chain = mh(logf, proposal=rprop, x0=init_state, dprop=log_dprop,
capture_state=capture_state, verbose=verbose,
use_log=True, iterations=iterations, modulus=100)
return matrix_chain
