return predictions
def add_options(option_parser):
"Add options for MEME to the option parser."
pass
if '__main__' == __name__:
#
# Set up the logging and options
#
import sys
options, args = parse_options(add_options)
# fasta = '/home/john/Data/NTNU-TF-search-dataset/datasets/model_real/M00724.fas'
# fasta = os.path.abspath(os.path.join(os.path.dirname(__file__), '../fasta/T00759trimRM-test-x2.fa'))
# fasta = os.path.abspath(os.path.join(os.path.dirname(__file__), '../fasta/T00759-tiny.fa'))
fasta = '/home/john/Data/Tompa-data-set/Real/hm22r.fasta'
# fasta = '/home/john/Data/GappedPssms/apr-2009/T99006trimRM.fa'
# fasta = '/home/john/Data/GappedPssms/apr-2009/T99004trimRM.fa'
options.output_dir = os.path.abspath(os.path.join('output', 'MEME'))
# del options.max_num_sites
# del options.min_num_sites
method = Algorithm(options)
predictions = method(fasta)
from Bio.Motif.Parsers.MEME import MEMEParser
parser = MEMEParser()
#
# Parse the options
#
from optparse import OptionParser
option_parser = OptionParser()
option_parser.add_option(
"--num-threads",
dest="num_threads",
default=3,
type='int',
help="Number of threads to run jobs on."
)
option_parser.add_option("--data-sets", action="append")
stem.add_options(option_parser)
meme.add_options(option_parser)
options = stem.parse_options(option_parser=option_parser)
stem.turn_on_google_profiling_if_asked_for(options)
# for each method and suite
for method_name in method_names:
for suite_name in suite_names:
suite = suite_for_name(suite_name)
method = method_for_name(method_name)
predictions_by_dataset = []
import cookbook.function_as_task as F
def do_work(task):
method_name, suite_name, data_set, options = task
logging.info('Running %s', task)
#
# Set up the logging
#
import logging
import sys
from cookbook.script_basics import setup_logging
setup_logging(__file__, level=logging.INFO)
# show_environment()
#
# Set up options
#
import stempy
options, args = stempy.parse_options(stempy.add_options)
if len(args) != 0:
raise RuntimeError('USAGE: %s <options>', sys.argv[0])
W = 8
fasta_file = '/home/john/Data/GappedPssms/apr-2009/T99006trimRM.fa'
algorithm = stempy.Algorithm(options)
algorithm.initialise(fasta_file)
model = algorithm.create_default_model(W)
model.prior_num_sites = 18.276144706645898
model.lambda_ = 0.00037315491488373951
model.bs.pssm.log_probs.values()[:] = [
[0.012967, 0.884511, 0.064057, 0.038465],
[0.021795, 0.875048, 0.023177, 0.079979],
[0.031394, 0.912065, 0.018154, 0.038387],
[0.22118, 0.486244, 0.067231, 0.225346],
def time_per_iteration_per_base(timings):
return timings['duration'] / timings['niters'] / test_data.get_num_w_mers(timings['dataset'], len(timings['seed']))
if '__main__' == __name__:
def add_options(parser):
parser.add_option("-f", "--force", action="store_true",
help="Always run even if already have results.")
#
# parse options
#
options, args = stempy.parse_options(
lambda parser: (add_options(parser), stempy.add_options(
parser), test_data.add_options(parser))
)
if len(args) != 0:
raise RuntimeError('USAGE: %s <options>', sys.argv[0])
run(options)
#
# Slice and dice data
#
h5file = tables.openFile(filename)
timings_table = h5file.root.EtaStability.timings
nsite_values = list(set(row['nsites'] for row in timings_table))
nsite_values.sort()
time_per_iteration_per_base = [
