def run(in_file, ref, blastn_config, config):
logger.info("Preparing the reference file for %s." % (ref.get("name")))
ref_file = prepare_ref_file(ref, config)
logger.info("Preparing the blast database for %s." % (ref.get("name")))
blast_db = prepare_blast_db(ref_file, "nucl")
logger.info("Blasting %s against %s." % (in_file, ref.get("name")))
results_dir = build_results_dir(blastn_config, config)
utils.safe_makedir(results_dir)
out_file = os.path.join(results_dir,
replace_suffix(os.path.basename(in_file),
ref.get("name") + "hits.tsv"))
tmp_out = out_file + ".tmp"
blast_results = blast_search(in_file, blast_db, tmp_out)
#logger.info("Filtering results for at least %f percent of the "
# "sequences covered." %(0.5*100))
#filtered_results = filter_results_by_length(blast_results, 0.5)
#logger.info("Filtered output file here: %s" %(filtered_results))
with open(blast_results) as in_handle:
reader = csv.reader(in_handle, delimiter="\t")
with open(out_file, "w") as out_handle:
writer = csv.writer(out_handle, delimiter="\t")
writer.writerow(HEADER_FIELDS.split(" "))
for line in reader:
writer.writerow(line)
return out_file
def _build_output_prefix(input_file, jellyfish_config, config):
out_dir = build_results_dir(jellyfish_config, config)
out_prefix = os.path.join(out_dir, replace_suffix(input_file,
"count"))
#out_prefix = "_".join([jellyfish_config["name"],
# remove_suffix(input_file)])
return out_prefix
def run(in_file, ref, blastn_config, config):
logger.info("Preparing the reference file for %s." % (ref.get("name")))
ref_file = prepare_ref_file(ref, config)
logger.info("Preparing the blast database for %s." % (ref.get("name")))
blast_db = prepare_blast_db(ref_file, "nucl")
logger.info("Blasting %s against %s." % (in_file, ref.get("name")))
results_dir = build_results_dir(blastn_config, config)
utils.safe_makedir(results_dir)
out_file = os.path.join(
results_dir,
replace_suffix(os.path.basename(in_file),
ref.get("name") + "hits.tsv"))
tmp_out = out_file + ".tmp"
blast_results = blast_search(in_file, blast_db, tmp_out)
#logger.info("Filtering results for at least %f percent of the "
# "sequences covered." %(0.5*100))
#filtered_results = filter_results_by_length(blast_results, 0.5)
#logger.info("Filtered output file here: %s" %(filtered_results))
with open(blast_results) as in_handle:
reader = csv.reader(in_handle, delimiter="\t")
with open(out_file, "w") as out_handle:
writer = csv.writer(out_handle, delimiter="\t")
writer.writerow(HEADER_FIELDS.split(" "))
for line in reader:
writer.writerow(line)
return out_file
def _build_output_file(input_file, novoalign_config, config):
outdir = build_results_dir(novoalign_config, config)
safe_makedir(outdir)
return os.path.join(outdir,
os.path.basename(replace_suffix(input_file, "sam")))
def _build_output_prefix(input_file, jellyfish_config, config):
out_dir = build_results_dir(jellyfish_config, config)
out_prefix = os.path.join(out_dir, replace_suffix(input_file, "count"))
#out_prefix = "_".join([jellyfish_config["name"],
# remove_suffix(input_file)])
return out_prefix
def _build_output_file(input_file, novoalign_config, config):
outdir = build_results_dir(novoalign_config, config)
safe_makedir(outdir)
return os.path.join(outdir,
os.path.basename(replace_suffix(input_file, "sam")))