def parse_all(pdb_dataset, output_dir, num_cpus):
"""Parse pdb dataset (pdb files) to pandas dataframes."""
requested_filenames = db.get_structures_filenames(pdb_dataset)
produced_filenames = db.get_structures_filenames(
output_dir, extension='.pkl')
requested_keys = [db.get_pdb_name(x) for x in requested_filenames]
produced_keys = [db.get_pdb_name(x) for x in produced_filenames]
work_keys = [key for key in requested_keys if key not in produced_keys]
work_filenames = [x[0] for x in
db.get_all_filenames(work_keys, pdb_dataset, enforcement=2)]
logging.info("{:} requested keys, {:} produced keys, {:} work keys"
.format(len(requested_keys), len(produced_keys),
len(work_keys)))
output_filenames = []
for pdb_filename in work_filenames:
sub_dir = output_dir + '/' + db.get_pdb_code(pdb_filename)[1:3]
if not os.path.exists(sub_dir):
os.makedirs(sub_dir)
output_filenames.append(
sub_dir + '/' + db.get_pdb_name(pdb_filename) + ".pkl")
inputs = [(key, output)
for key, output in zip(work_filenames, output_filenames)]
par.submit_jobs(parse, inputs, num_cpus)
def map_all_pssms(pdb_dataset, blastdb, output_dir, num_cpus):
ext = '.pkl'
requested_filenames = \
db.get_structures_filenames(pdb_dataset, extension=ext)
requested_keys = [db.get_pdb_name(x) for x in requested_filenames]
produced_filenames = db.get_structures_filenames(output_dir,
extension='.pkl')
produced_keys = [db.get_pdb_name(x) for x in produced_filenames]
work_keys = [key for key in requested_keys if key not in produced_keys]
work_filenames = [
x[0] for x in db.get_all_filenames(work_keys,
pdb_dataset,
extension=ext,
keyer=lambda x: db.get_pdb_name(x))
]
output_filenames = []
for pdb_filename in work_filenames:
sub_dir = output_dir + '/' + db.get_pdb_code(pdb_filename)[1:3]
if not os.path.exists(sub_dir):
os.makedirs(sub_dir)
output_filenames.append(sub_dir + '/' + db.get_pdb_name(pdb_filename) +
".pkl")
logging.info("{:} requested keys, {:} produced keys, {:} work keys".format(
len(requested_keys), len(produced_keys), len(work_keys)))
inputs = [(key, blastdb, output)
for key, output in zip(work_filenames, output_filenames)]
par.submit_jobs(map_pssms, inputs, num_cpus)
def main(pair_dir, tfrecord_dir, num_cpus):
"""Run write_pairs on all provided complexes."""
requested_filenames = \
db.get_structures_filenames(pair_dir, extension='.dill')
requested_keys = [db.get_pdb_name(x) for x in requested_filenames]
produced_filenames = \
db.get_structures_filenames(tfrecord_dir, extension='.tfrecord')
produced_keys = [db.get_pdb_name(x) for x in produced_filenames]
work_keys = [key for key in requested_keys if key not in produced_keys]
logging.info("{:} requested keys, {:} produced keys, {:} work keys".format(
len(requested_keys), len(produced_keys), len(work_keys)))
work_filenames = [
x[0]
for x in db.get_all_filenames(work_keys, pair_dir, extension='.dill')
]
output_filenames = []
for pdb_filename in work_filenames:
sub_dir = tfrecord_dir + '/' + db.get_pdb_code(pdb_filename)[1:3]
if not os.path.exists(sub_dir):
os.makedirs(sub_dir)
output_filenames.append(sub_dir + '/' + db.get_pdb_name(pdb_filename) +
".tfrecord")
inputs = [(i, o) for i, o in zip(work_filenames, output_filenames)]
par.submit_jobs(pairs_to_tfrecord, inputs, num_cpus)