from pomegranate import HiddenMarkovModel
import calculator
from converter_to import converter_to
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 equal_distribution
from matrix_from_aln import matrix_from_exa
matrixAcceptor0 = numpy.array(matrix_from_exa('new_acceptor1.exa'))
acceptor0_data = classify(matrixAcceptor0, 2)
model = HiddenMarkovModel('intron_acceptor')
intron = State(DiscreteDistribution(
calculator.intron_calculator('cuts_intron.txt').p),
name='in')
acceptor0_states = sequence_state_factory(acceptor0_data, 'acceptor0')
post = State(DiscreteDistribution(equal_distribution), name='post')
model.add_state(intron)
add_sequence(model, acceptor0_states)
model.add_state(post)
model.add_transition(model.start, intron, 1)
model.add_transition(intron, intron, 0.9)
model.add_transition(intron, acceptor0_states[0], 0.1)
model.add_transition(acceptor0_states[-1], post, 1)
model.add_transition(post, post, 0.5)
model.add_transition(post, model.end, 0.5)
donor2_data = classify(matrixDonor2, 2)
donor2_states = sequence_state_factory(donor2_data, 'donor2')
acceptor0_data = classify(matrixAcceptor0, 2)
acceptor0_states = sequence_state_factory(acceptor0_data, 'acceptor0')
acceptor1_data = classify(matrixAcceptor1, 2)
acceptor1_states = sequence_state_factory(acceptor1_data, 'acceptor1')
acceptor2_data = classify(matrixAcceptor2, 2)
acceptor2_states = sequence_state_factory(acceptor2_data, 'acceptor2')
coding_model = HiddenMarkovModel()
intron_distribution = calculator.intron_calculator('cuts_intron.txt')
back = State(DiscreteDistribution(
calculator.intron_calculator('cuts_intron.txt').p),
name='back')
fake_back = State(DiscreteDistribution(intron_distribution.p), name='back2')
in0 = State(DiscreteDistribution(intron_distribution.p), name='in0')
in1 = State(DiscreteDistribution(intron_distribution.p), name='in1')
in2 = State(DiscreteDistribution(intron_distribution.p), name='in2')
in0_spacers = spacer_states_maker(64, intron_distribution.p, 'in0 spacer')
in1_spacers = spacer_states_maker(64, intron_distribution.p, 'in1 spacer')
in2_spacers = spacer_states_maker(64, intron_distribution.p, 'in2 spacer')
coding_state0 = State(DiscreteDistribution(c0.p), 'coding state 0')
from pomegranate import DiscreteDistribution
matrix_TATA = numpy.array(matrix_from_fasta('tata_-5_11_completa.seq'))
matrix_GC = numpy.array(matrix_from_fasta('gc_completo.seq'))
matrix_CCAAT = numpy.array(matrix_from_fasta('CCAAT_completa.seq'))
matrix_Inr = numpy.array(matrix_from_fasta('Inr_completo.seq'))
matrix_no_inr = numpy.array(matrix_from_fasta('no_inr.fa'))
gc_data = classify(matrix_GC, 2)
tata_data = classify(matrix_TATA, 2)
cat_data = classify(matrix_CCAAT, 2)
inr_data = classify(matrix_Inr, 2)
no_inr_data = classify(matrix_no_inr, 2)
no_coding = calculator.intron_calculator('cuts_intron.txt')
# Model
promoter_utr_model = HiddenMarkovModel('promoter')
# States
back = State(DiscreteDistribution(no_coding.p), name='back')
gc_states = sequence_state_factory(gc_data, 'GC')
post_gc_var_spacers_tss = spacer_states_maker(151, no_coding.p, 'post gc var spacer tss')
post_gc_spacers_tss = spacer_states_maker(38, no_coding.p, 'post gc spacer tss')
post_gc_var_spacers_tata = spacer_states_maker(151, no_coding.p, 'post gc var spacer tata')
post_gc_spacers_tata = spacer_states_maker(18, no_coding.p, 'post gc spacer tata')
import calculator
from converter_to import converter_to
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 equal_distribution
from matrix_from_aln import matrix_from_exa
matrixAcceptor0 = numpy.array(
matrix_from_exa('../data extractors/new_acceptor1.exa'))
acceptor0_data = classify(matrixAcceptor0, 2)
model = HiddenMarkovModel('intron_acceptor')
intron = State(DiscreteDistribution(
calculator.intron_calculator('../data extractors/new_cuts_intron.txt').p),
name='in')
acceptor0_states = sequence_state_factory(acceptor0_data, 'acceptor0')
post = State(DiscreteDistribution(equal_distribution), name='post')
model.add_state(intron)
add_sequence(model, acceptor0_states)
model.add_state(post)
model.add_transition(model.start, intron, 1)
model.add_transition(intron, intron, 0.9)
model.add_transition(intron, acceptor0_states[0], 0.1)
model.add_transition(acceptor0_states[-1], post, 1)
model.add_transition(post, post, 0.5)
model.add_transition(post, model.end, 0.5)
from pomegranate import State
from pomegranate import HiddenMarkovModel
from pomegranate import DiscreteDistribution
from matrix_from_aln import matrix_from_exa
with open('promoter_utr_model_base.json') as base_model_file:
promoter_model_json = base_model_file.read()
promoter_model = HiddenMarkovModel.from_json(promoter_model_json)
matrixDonor0 = numpy.array(matrix_from_exa('new_donor0.exa'))
matrixAcceptor0 = numpy.array(matrix_from_exa('new_acceptor0.exa'))
donor0_data = classify(matrixDonor0, 2)
acceptor0_data = classify(matrixAcceptor0, 2)
no_coding_dist = calculator.intron_calculator('cuts_intron.txt').p
donor_states = sequence_state_factory(donor0_data, 'donor0')
acceptor_states = sequence_state_factory(acceptor0_data, 'acceptor0')
intron_spacer_states = spacer_states_maker(10, no_coding_dist, 'intron spacer')
utr_model = HiddenMarkovModel('utr_model')
# States
exon_state = State(DiscreteDistribution(calculator.utr_exon_5('mcutsa.txt').p),
name='utr exon')
intron_state = State(DiscreteDistribution(no_coding_dist), name='utr intron')
utr_model.add_model(promoter_model)
utr_model.add_state(exon_state)
utr_model.add_state(intron_state)