def setup_db(work_dir, db_dir, target_org, fs, lfs):
"""Copy over BLAST database files, prepping them for map availability.
"""
(_, org_names, db_refs) = blast.get_org_dbs(db_dir, target_org)
work_dir = os.path.join(work_dir, db_dir)
fs.create_directory(work_dir)
db_refs = db_refs
ref_info = []
blast_dbs = []
for db_path in db_refs:
blast_dbs.append(os.path.basename(db_path))
for fname in glob.glob(db_path + ".[p|n]*"):
hdfs_ref = _hdfs_ref(work_dir, fname)
lfs.copy(fname, fs, hdfs_ref)
ref_info.append("%s#%s" % (hdfs_ref, os.path.basename(hdfs_ref)))
return ",".join(ref_info), blast_dbs, org_names
def main(org_config_file, config_file):
with open(config_file) as in_handle:
config = yaml.load(in_handle)
with open(org_config_file) as in_handle:
org_config = yaml.load(in_handle)
if not os.path.exists(config['work_dir']):
os.makedirs(config['work_dir'])
(_, org_names, db_refs) = blast.get_org_dbs(config['db_dir'],
org_config['target_org'])
id_file, score_file = setup_output_files(org_config['target_org'],
org_names)
file_info = [id_file, score_file]
pool = multiprocessing.Pool(int(config['num_cores']))
with open(org_config['search_file']) as in_handle:
pool.map(_process_wrapper,
((rec, db_refs, file_info, config['work_dir'])
for rec in SeqIO.parse(in_handle, "fasta")))
def main(org_config_file, config_file):
with open(config_file) as in_handle:
config = yaml.load(in_handle)
with open(org_config_file) as in_handle:
org_config = yaml.load(in_handle)
if not os.path.exists(config['work_dir']):
os.makedirs(config['work_dir'])
(_, org_names, db_refs) = blast.get_org_dbs(config['db_dir'],
org_config['target_org'])
id_file, score_file = setup_output_files(org_config['target_org'],
org_names)
file_info = [id_file, score_file]
pool = multiprocessing.Pool(int(config['num_cores']))
with open(org_config['search_file']) as in_handle:
pool.map(_process_wrapper,
((rec, db_refs, file_info, config['work_dir'], config.get("blast_cmd"))
for rec in SeqIO.parse(in_handle, "fasta")))
def setup_db(work_dir_base, db_dir, target_org):
"""Copy over BLAST database files, prepping them for map availability.
"""
(_, org_names, db_refs) = blast.get_org_dbs(db_dir, target_org)
work_dir = os.path.join(work_dir_base, db_dir)
cl = ["hadoop", "fs", "-mkdir", work_dir]
subprocess.check_call(cl)
ref_info = []
blast_dbs = []
for db_path in db_refs:
blast_dbs.append(os.path.basename(db_path))
for fname in glob.glob(db_path + ".[p|n]*"):
hdfs_ref = _hdfs_ref(work_dir, fname)
cl = ["hadoop", "fs", "-put", fname, hdfs_ref]
subprocess.check_call(cl)
ref_info.append("%s#%s" % (hdfs_ref, os.path.basename(hdfs_ref)))
return ref_info, blast_dbs, org_names
def main(org_config_file, config_file):
with open(config_file) as in_handle:
config = yaml.load(in_handle)
with open(org_config_file) as in_handle:
org_config = yaml.load(in_handle)
if not os.path.exists(config["work_dir"]):
os.makedirs(config["work_dir"])
(_, org_names, db_refs) = blast.get_org_dbs(config["db_dir"], org_config["target_org"])
id_file, score_file = setup_output_files(org_config["target_org"])
with open(org_config["search_file"]) as in_handle:
with open(id_file, "w") as id_out_handle:
with open(score_file, "w") as score_out_handle:
id_writer = csv.writer(id_out_handle, dialect="excel-tab")
score_writer = csv.writer(score_out_handle, dialect="excel-tab")
header = [""] + org_names
id_writer.writerow(header)
score_writer.writerow(header)
_do_work(db_refs, in_handle, id_writer, score_writer, config)
def main(org_config_file, config_file):
with open(config_file) as in_handle:
config = yaml.load(in_handle)
with open(org_config_file) as in_handle:
org_config = yaml.load(in_handle)
if not os.path.exists(config['work_dir']):
os.makedirs(config['work_dir'])
(_, org_names, db_refs) = blast.get_org_dbs(config['db_dir'],
org_config['target_org'])
id_file, score_file = setup_output_files(org_config['target_org'])
with open(org_config['search_file']) as in_handle:
with open(id_file, "w") as id_out_handle:
with open(score_file, "w") as score_out_handle:
id_writer = csv.writer(id_out_handle, dialect='excel-tab')
score_writer = csv.writer(score_out_handle,
dialect='excel-tab')
header = [""] + org_names
id_writer.writerow(header)
score_writer.writerow(header)
_do_work(db_refs, in_handle, id_writer, score_writer, config)
