def train_and_test():
    with open('../data extractors/exons_start_1.txt') as in_file:
        total = []
        for line in in_file:
            no_p_line = line.replace('P', '').lower().replace('\n', '')
            total.append(no_p_line)

    converted_total = [converter_to(x, 2) for x in total]

    matrixDonor0 = numpy.array(
        matrix_from_exa('../data extractors/new_donor1.exa'))

    c0, c1, c2 = calculator.calculate_proba2('../data extractors/new_cuts.txt')
    print(c0.p, c1.p, c2.p)
    coding_state0 = State(DiscreteDistribution(c0.p), 'coding state 0')
    coding_state1 = State(DiscreteDistribution(c1.p), 'coding state 1')
    coding_state2 = State(DiscreteDistribution(c2.p), 'coding state 2')

    donor0_data = classify(matrixDonor0, 2)
    donor0_states = sequence_state_factory(donor0_data, 'donor0')

    post = State(DiscreteDistribution(equal_distribution), name='post')

    model = HiddenMarkovModel('coding to donor')

    model.add_state(coding_state0)
    model.add_state(coding_state1)
    model.add_state(coding_state2)

    add_sequence(model, donor0_states)

    model.add_state(post)

    model.add_transition(model.start, coding_state0, 1)

    model.add_transition(coding_state0, coding_state1, 0.6)
    model.add_transition(coding_state0, donor0_states[0], 0.4)

    model.add_transition(coding_state1, coding_state2, 0.6)
    model.add_transition(coding_state1, donor0_states[0], 0.4)

    model.add_transition(coding_state2, coding_state0, 0.6)
    model.add_transition(coding_state2, donor0_states[0], 0.4)

    model.add_transition(donor0_states[-1], post, 1)

    model.add_transition(post, post, 0.9)
    model.add_transition(post, model.end, 0.1)

    model.bake()
    test_model(model)

    model.fit(converted_total,
              transition_pseudocount=1,
              emission_pseudocount=1,
              verbose=True)

    test_model(model)

    with open('partial_model_coding_to_donor_model0.json', 'w') as out:
        out.write(model.to_json())
Example #2
0
from matrix_from_aln import matrix_from_exa
import itertools
import calculator
from model_maker_utils import sequence_state_factory
from model_maker_utils import classify
from model_maker_utils import add_sequence
from model_maker_utils import spacer_states_maker
from model_maker_utils import percentage_matrix_maker
from stop_example_divider import divider as stop_divider


def foo(l):
    yield from itertools.product(*([l] * 3))


c0, c1, c2 = calculator.calculate_proba2('cuts.txt')
matrixZE = numpy.array(matrix_from_exa('new_tss.exa'))

# matrixEZ = numpy.array(matrix_from_exa('new_tts.exa'))
taa_matrix, tga_matrix, tag_matrix = stop_divider('new_tts.exa')

matrixDonor0 = numpy.array(matrix_from_exa('new_donor0.exa'))
matrixDonor1 = numpy.array(matrix_from_exa('new_donor1.exa'))
matrixDonor2 = numpy.array(matrix_from_exa('new_donor2.exa'))
matrixAcceptor0 = numpy.array(matrix_from_exa('new_acceptor0.exa'))
matrixAcceptor1 = numpy.array(matrix_from_exa('new_acceptor1.exa'))
matrixAcceptor2 = numpy.array(matrix_from_exa('new_acceptor2.exa'))

polyASeqs = [('AATAAA', 592), ('ATTAAA', 149), ('AGTAAA', 27), ('TATAAA', 32),
             ('CATAAA', 13), ('GATAAA', 13), ('AATATA', 17), ('AATACA', 12),
             ('AATAGA', 7), ('ACTAAA', 6), ('AAGAAA', 11), ('AATGAA', 8)]
Example #3
0
import numpy
from pomegranate import State
from pomegranate import DiscreteDistribution
from pomegranate import HiddenMarkovModel
import calculator
from model_maker_utils import sequence_state_factory, classify, add_sequence, equal_distribution
from matrix_from_aln import matrix_from_exa
from converter_to import converter_to

c0, c1, c2 = calculator.calculate_proba2('../data extractors/new_cuts.txt')
matrixStop = numpy.array(matrix_from_exa('../data extractors/new_stops.exa'))
coding_state0 = State(DiscreteDistribution(c0.p), 'coding state 0')
coding_state1 = State(DiscreteDistribution(c1.p), 'coding state 1')
coding_state2 = State(DiscreteDistribution(c2.p), 'coding state 2')

post = State(DiscreteDistribution(equal_distribution), name='post')

model = HiddenMarkovModel('coding_to_stop')

stop_data = classify(matrixStop, 2)
stop_states = sequence_state_factory(stop_data, 'stop')

model.add_state(coding_state0)
model.add_state(coding_state1)
model.add_state(coding_state2)

add_sequence(model, stop_states)

model.add_state(post)

model.add_transition(model.start, coding_state1, 1)