def main():
#print load_genome_metadata(1)
genome = pysam.FastaFile('hg19.genome.fa')
#models = load_selex_models_from_db()
models = load_binding_models_from_db()
peaks = load_peaks(sys.argv[1])
seqs_iter = ( genome.fetch(contig, start, stop+1)
for contig, start, stop in peaks )
seqs = FixedLengthDNASequences(seqs_iter)
with ThreadSafeFile("output.txt", "w") as ofp:
all_args = [(ofp, model, seqs, peaks) for model in models]
run_in_parallel(24, score_model_worker, all_args)
return
def main():
#print load_genome_metadata(1)
genome = pysam.FastaFile('hg19.genome.fa')
#models = load_selex_models_from_db()
models = load_binding_models_from_db()
peaks = load_peaks(sys.argv[1])
seqs_iter = (genome.fetch(contig, start, stop + 1)
for contig, start, stop in peaks)
seqs = FixedLengthDNASequences(seqs_iter)
with ThreadSafeFile("output.txt", "w") as ofp:
all_args = [(ofp, model, seqs, peaks) for model in models]
run_in_parallel(24, score_model_worker, all_args)
return
def load_model(factor_name):
"""Load models from the DB.
This isn't useful - I just keep it here to show where the models came from.
"""
try:
models = load_binding_models_from_db(tf_names=[factor_name,])
assert len(models) == 1, "Multiple binding models found for '{}'".format(factor_name)
except NoBindingModelsFoundError:
# if we couldnt find a good motif, just find any motif
# special case TAF1 because it doesnt exist in CISBP
if factor_name == 'TAF1':
models = [load_TAF1_binding_model(),]
else:
models = load_all_pwms_from_db(tf_names=factor_name)
model = models[0]
return model
def load_model(factor_name):
"""Load models from the DB.
This isn't useful - I just keep it here to show where the models came from.
"""
try:
models = load_binding_models_from_db(tf_names=[
factor_name,
])
assert len(
models) == 1, "Multiple binding models found for '{}'".format(
factor_name)
except NoBindingModelsFoundError:
# if we couldnt find a good motif, just find any motif
# special case TAF1 because it doesnt exist in CISBP
if factor_name == 'TAF1':
models = [
load_TAF1_binding_model(),
]
else:
models = load_all_pwms_from_db(tf_names=factor_name)
model = models[0]
return model
def score_multiple_fixed_len_seqs(seq_len=10000, n_seqs=100):
models = load_binding_models_from_db(TEST_MODEL_TF_NAME)
model = models[0]
seqs = FixedLengthDNASequences(['A' * seq_len] * n_seqs)
scores = model.score_seqs_binding_sites(seqs)
print 'PASS', model.motif_len, len(seqs), len(scores)
def score_multiple_seqs(seq_len=100000, n_seqs=10):
models = load_binding_models_from_db(TEST_MODEL_TF_NAME)
model = models[0]
seqs = DNASequences(['A' * seq_len] * n_seqs)
scores = seqs.score_binding_sites(model, 'FWD')
print 'PASS', model.motif_len, len(scores)
def score_model(seq_len=100000):
models = load_binding_models_from_db(TEST_MODEL_TF_NAME)
model = models[0]
seq = DNASequence('A' * seq_len)
score = model.score_binding_sites(seq)
print 'PASS', model.motif_len, score.shape
def score_multiple_fixed_len_seqs(seq_len=10000, n_seqs=100):
models = load_binding_models_from_db(TEST_MODEL_TF_NAME)
model = models[0]
seqs = FixedLengthDNASequences(['A'*seq_len]*n_seqs)
scores = model.score_seqs_binding_sites(seqs)
print 'PASS', model.motif_len, len(seqs), len(scores)
def score_multiple_seqs(seq_len=100000, n_seqs=10):
models = load_binding_models_from_db(TEST_MODEL_TF_NAME)
model = models[0]
seqs = DNASequences(['A'*seq_len]*n_seqs)
scores = seqs.score_binding_sites(model, 'FWD')
print 'PASS', model.motif_len, len(scores)
def score_model(seq_len=100000):
models = load_binding_models_from_db(TEST_MODEL_TF_NAME)
model = models[0]
seq = DNASequence('A'*seq_len)
score = model.score_binding_sites(seq)
print 'PASS', model.motif_len, score.shape