def test_hmm(tag, pwm):
freqs, gaps = pwm
logo = L.pssm_as_image(freqs, size=None, transparencies=gaps)
logo_filename = '%s-logo.png' % tag
logo.save(logo_filename)
logging.info('%s: Created logo: %s', tag, logo_filename)
model = build_hmm_model(freqs, gaps, .1)
logging.debug('%s: Created model', tag)
hmm.graph_as_svg(model, '%s-states' % tag, neato_properties={'-Elen':3.})
logging.debug('%s: Graphed model', tag)
return model
def test_hmm(tag, pwm):
freqs, gaps = pwm
logo = L.pssm_as_image(freqs, size=None, transparencies=gaps)
logo_filename = '%s-logo.png' % tag
logo.save(logo_filename)
logging.info('%s: Created logo: %s', tag, logo_filename)
model = build_hmm_model(freqs, gaps, .1)
logging.debug('%s: Created model', tag)
hmm.graph_as_svg(model,
'%s-states' % tag,
neato_properties={'-Elen': 3.})
logging.debug('%s: Graphed model', tag)
return model
def run_pwm_viterbi(tag, freqs, gaps, positive_seqs, negative_seqs):
"""
Run the PWM using Viterbi algorithm to classify sequences.
"""
logging.info('Running PWM: %s', tag)
logo = L.pssm_as_image(freqs, size=None, transparencies=gaps)
logo_filename = '%s-logo.png' % tag
logo.save(logo_filename)
logging.info('%s: Created logo: %s', tag, logo_filename)
roc_points = []
for p_binding in p_binding_params:
# build model
model = build_hmm_model(freqs, gaps, p_binding)
hmm.graph_as_svg(model, '%s-states' % tag, neato_properties={'-Elen':1.4})
logging.debug('%s: Graphed model', tag)
pos_total_pos, pos_total_neg, pos_num_seqs_with_site = run_on_seqs(model, positive_seqs)
logging.debug(
'%s: p(binding)=%.1e: Positive sequences: Over all sequences: found %4d positive sites and %4d negative sites in %4d/%4d sequences',
tag,
p_binding,
pos_total_pos,
pos_total_neg,
pos_num_seqs_with_site,
len(positive_seqs)
)
neg_total_pos, neg_total_neg, neg_num_seqs_with_site = run_on_seqs(model, negative_seqs)
logging.debug(
'%s: p(binding)=%.1e: Negative sequences: Over all sequences: found %4d positive sites and %4d negative sites in %4d/%4d sequences',
tag,
p_binding,
neg_total_pos,
neg_total_neg,
neg_num_seqs_with_site,
len(negative_seqs)
)
tp = pos_num_seqs_with_site
fp = neg_num_seqs_with_site
fn = len(positive_seqs) - pos_num_seqs_with_site
tn = len(negative_seqs) - neg_num_seqs_with_site
roc_point = roc.RocCalculator(tp=tp, fp=fp, tn=tn, fn=fn)
logging.info('%s: p(binding)=%.1e; Specificity=%.3f; Sensitivity=%.3f',
tag,
p_binding,
roc_point.specificity(),
roc_point.sensitivity(),
)
roc_points.append(roc_point)
return roc_points
def run_pwm_forward_backward(tag, freqs, gaps, positive_seqs, negative_seqs):
"""
Run the PWM using forward-backward.
"""
logging.info('Running PWM: %s', tag)
logo = L.pssm_as_image(freqs, size=None, transparencies=gaps)
logo_filename = '%s-logo.png' % tag
logo.save(logo_filename)
logging.info('%s: Created logo: %s', tag, logo_filename)
# build model
model = build_hmm_model(freqs, gaps, .001)
hmm.graph_as_svg(model, '%s-states' % tag, neato_properties={'-Elen': 1.4})
logging.debug('%s: Graphed model', tag)
positive_scores = test_hmm_forward_backward(model, positive_seqs.values())
negative_scores = test_hmm_forward_backward(model, negative_seqs.values())
return roc.picked_rocs_from_thresholds(positive_scores, negative_scores)
def run_pwm_forward_backward(tag, freqs, gaps, positive_seqs, negative_seqs):
"""
Run the PWM using forward-backward.
"""
logging.info('Running PWM: %s', tag)
logo = L.pssm_as_image(freqs, size=None, transparencies=gaps)
logo_filename = '%s-logo.png' % tag
logo.save(logo_filename)
logging.info('%s: Created logo: %s', tag, logo_filename)
# build model
model = build_hmm_model(freqs, gaps, .001)
hmm.graph_as_svg(model, '%s-states' % tag, neato_properties={'-Elen':1.4})
logging.debug('%s: Graphed model', tag)
positive_scores = test_hmm_forward_backward(model, positive_seqs.values())
negative_scores = test_hmm_forward_backward(model, negative_seqs.values())
return roc.picked_rocs_from_thresholds(positive_scores, negative_scores)
def run_pwm_viterbi(tag, freqs, gaps, positive_seqs, negative_seqs):
"""
Run the PWM using Viterbi algorithm to classify sequences.
"""
logging.info('Running PWM: %s', tag)
logo = L.pssm_as_image(freqs, size=None, transparencies=gaps)
logo_filename = '%s-logo.png' % tag
logo.save(logo_filename)
logging.info('%s: Created logo: %s', tag, logo_filename)
roc_points = []
for p_binding in p_binding_params:
# build model
model = build_hmm_model(freqs, gaps, p_binding)
hmm.graph_as_svg(model,
'%s-states' % tag,
neato_properties={'-Elen': 1.4})
logging.debug('%s: Graphed model', tag)
pos_total_pos, pos_total_neg, pos_num_seqs_with_site = run_on_seqs(
model, positive_seqs)
logging.debug(
'%s: p(binding)=%.1e: Positive sequences: Over all sequences: found %4d positive sites and %4d negative sites in %4d/%4d sequences',
tag, p_binding, pos_total_pos, pos_total_neg,
pos_num_seqs_with_site, len(positive_seqs))
neg_total_pos, neg_total_neg, neg_num_seqs_with_site = run_on_seqs(
model, negative_seqs)
logging.debug(
'%s: p(binding)=%.1e: Negative sequences: Over all sequences: found %4d positive sites and %4d negative sites in %4d/%4d sequences',
tag, p_binding, neg_total_pos, neg_total_neg,
neg_num_seqs_with_site, len(negative_seqs))
tp = pos_num_seqs_with_site
fp = neg_num_seqs_with_site
fn = len(positive_seqs) - pos_num_seqs_with_site
tn = len(negative_seqs) - neg_num_seqs_with_site
roc_point = roc.RocCalculator(tp=tp, fp=fp, tn=tn, fn=fn)
logging.info(
'%s: p(binding)=%.1e; Specificity=%.3f; Sensitivity=%.3f',
tag,
p_binding,
roc_point.specificity(),
roc_point.sensitivity(),
)
roc_points.append(roc_point)
return roc_points
TRANSITION:4;5;1
TRANSITION:5;6;1
TRANSITION:6;7;1
TRANSITION:7;8;1
# EMISSIONS:i;b1,b2,b3,b4 - where p(state i emits base i) = bi
EMISSIONS:0;.5,.5,0,0
EMISSIONS:1;0,0,.5,.5
EMISSIONS:2;1,0,0,0
EMISSIONS:3;0,0,0,1
EMISSIONS:4;0,0,1,0
EMISSIONS:5;0,1,0,0
EMISSIONS:6;1,0,0,0
EMISSIONS:7;1,0,0,0
EMISSIONS:8;0,0,1,0
"""
model = build_model( to_parse.split('\n') )
m = hmm.model_states_2_model(model)
if False:
hmm.graph_as_svg(
m,
'test',
'model_io_test',
graphing_keywords = {
'show_dists' : lambda l: True,
'state_labels' : None
},
neato_properties = { '-Elen' : '2' }
)
with open('model.mdl', 'w') as f: write_model(model, f)
TRANSITION:3;5;.9
TRANSITION:4;5;1
TRANSITION:5;6;1
TRANSITION:6;7;1
TRANSITION:7;8;1
# EMISSIONS:i;b1,b2,b3,b4 - where p(state i emits base i) = bi
EMISSIONS:0;.5,.5,0,0
EMISSIONS:1;0,0,.5,.5
EMISSIONS:2;1,0,0,0
EMISSIONS:3;0,0,0,1
EMISSIONS:4;0,0,1,0
EMISSIONS:5;0,1,0,0
EMISSIONS:6;1,0,0,0
EMISSIONS:7;1,0,0,0
EMISSIONS:8;0,0,1,0
"""
model = build_model(to_parse.split('\n'))
m = hmm.model_states_2_model(model)
if False:
hmm.graph_as_svg(m,
'test',
'model_io_test',
graphing_keywords={
'show_dists': lambda l: True,
'state_labels': None
},
neato_properties={'-Elen': '2'})
with open('model.mdl', 'w') as f:
write_model(model, f)
[ 1., 0., 0., 0. ],
[ 0., 1., 0., 0. ],
[ 0., 0., 0., 1. ],
]
K = 7
test_seq = 'acgtgat' # matches dist above
test_seq_order_0 = hmm.pssm.seq_to_numpy(test_seq)
# for various different orders
for order in [0, 1, 2]:
# build a model of distribution above
traits = GappedPssmTraits(K, p_binding_site, order, num_background_states, create_background_model, emission_dists=emission_dists)
model = traits.new_model()
converted = hmm.model_states_2_model(model)
B = converted.B
hmm.graph_as_svg(converted, 'gapped_pssm')
# check the reverse complement states are correct
for n in xrange(model.N):
for o in xrange(model.M):
rev_comp_state, rev_comp_obs = traits.get_non_reverse_complement(n,o)
assert check_is_close_2(B[rev_comp_state,rev_comp_obs], B[n,o]), ('%d,%d %d,%d: %f %f' % (rev_comp_state,rev_comp_obs,n,o,B[rev_comp_state,rev_comp_obs],B[n,o]))
# check viterbi gives correct result
test_seq_order_n = converted.converter.to_order_n(test_seq_order_0)
LL, states = converted.viterbi(test_seq_order_n)
for i, state in enumerate(states):
assert (state-num_background_states)/2 == i
hmm.dirichlet_draw(numpy.ones(builder.M) * .1)
for k in xrange(builder.K)
])
emissions[builder.gap_index] = hmm.dirichlet_draw(
numpy.ones(builder.M) * .3)
model_by_states, in_states, out_states = builder.create(
p_gap=.6, emissions=emissions)
# create a background model and add the single gapped pssm to it
complete_model = add_to_simple_background_model(model_by_states,
in_states,
out_states,
p_binding_site=.01)
# convert to other type of model
model = hmm.as_model(complete_model)
# write as a graph
hmm.graph_as_svg(model,
'single-gapped-hmm',
graphing_keywords={'include_emissions': False},
neato_properties={'-Elen': 2})
# get the emissions and gap probabilities and write a logo
emissions_copy, gap_probs = builder.get_emissions_and_gap_probabilities(
model, offset=1)
assert (emissions_copy - emissions).sum() < 1e-10
import hmm.pssm.logo as logo
image = logo.pssm_as_image(emissions, transparencies=gap_probs)
image.save("single-gapped-pssm-logo.png", "PNG")
sp1_pssms = all_sp1_pssms()
for tag in methods:
score_pickle_file = '%s-scores.pickle' % tag
try:
positive_scores, negative_scores = cPickle.load(open(score_pickle_file))
logging.info('%s: Unpickled ROCs from %s.', tag, score_pickle_file)
except:
logging.info('%s: Could not ROCs from unpickle %s, calculating from scratch.', tag, score_pickle_file)
freqs, gaps = sp1_pssms[tag]
freqs = (freqs.T / freqs.sum(axis=1)).T
logo = L.pssm_as_image(freqs, size=None, transparencies=gaps)
logo_filename = '%s-logo.png' % tag
logo.save(logo_filename)
logging.info('%s: Created logo: %s', tag, logo_filename)
model = build_hmm_model(freqs, gaps, .001)
hmm.graph_as_svg(model, '%s-states' % tag, neato_properties={'-Elen':1.4})
logging.debug('%s: Graphed model', tag)
positive_scores = test_hmm_forward_backward(model, sequences['positive'].values())
negative_scores = dict(
(bg, test_hmm_forward_backward(model, sequences[bg].values()))
for bg in backgrounds
)
cPickle.dump((positive_scores, negative_scores), open(score_pickle_file, 'wb'))
scores[(tag,)] = positive_scores
for bg, score in negative_scores.iteritems():
scores[(tag, bg)] = score
#
# Generate ROCs
#
positive_scores, negative_scores = cPickle.load(
open(score_pickle_file))
logging.info('%s: Unpickled ROCs from %s.', tag, score_pickle_file)
except:
logging.info(
'%s: Could not ROCs from unpickle %s, calculating from scratch.',
tag, score_pickle_file)
freqs, gaps = sp1_pssms[tag]
freqs = (freqs.T / freqs.sum(axis=1)).T
logo = L.pssm_as_image(freqs, size=None, transparencies=gaps)
logo_filename = '%s-logo.png' % tag
logo.save(logo_filename)
logging.info('%s: Created logo: %s', tag, logo_filename)
model = build_hmm_model(freqs, gaps, .001)
hmm.graph_as_svg(model,
'%s-states' % tag,
neato_properties={'-Elen': 1.4})
logging.debug('%s: Graphed model', tag)
positive_scores = test_hmm_forward_backward(
model, sequences['positive'].values())
negative_scores = dict(
(bg, test_hmm_forward_backward(model, sequences[bg].values()))
for bg in backgrounds)
cPickle.dump((positive_scores, negative_scores),
open(score_pickle_file, 'wb'))
scores[(tag, )] = positive_scores
for bg, score in negative_scores.iteritems():
scores[(tag, bg)] = score
#
# Generate ROCs
emissions[builder.gap_index] = hmm.dirichlet_draw(numpy.ones(builder.M) * .3)
model_by_states, in_states, out_states = builder.create(
p_gap=.6,
emissions=emissions
)
# create a background model and add the single gapped pssm to it
complete_model = add_to_simple_background_model(
model_by_states,
in_states,
out_states,
p_binding_site=.01)
# convert to other type of model
model = hmm.as_model(complete_model)
# write as a graph
hmm.graph_as_svg(
model,
'single-gapped-hmm',
graphing_keywords={'include_emissions':False},
neato_properties={'-Elen':2}
)
# get the emissions and gap probabilities and write a logo
emissions_copy, gap_probs = builder.get_emissions_and_gap_probabilities(model, offset=1)
assert (emissions_copy - emissions).sum() < 1e-10
import hmm.pssm.logo as logo
image = logo.pssm_as_image(emissions, transparencies=gap_probs)
image.save("single-gapped-pssm-logo.png", "PNG")
