Add threads argument to the _run_hmmsearch function.

src/dbcanlight/__init__.py

@@ -1,4 +1,4 @@
-from .utils import check_db
-from .config import db_path
+from dbcanlight.utils import check_db
+from dbcanlight.config import db_path
 
 check_db(*[x for x in vars(db_path).values()])

src/dbcanlight/dbcanlight.py

@@ -45,10 +45,10 @@ def _load_input(self) -> None:
  if f.is_pressed():
  self._hmms.rewind()
 
- def _run_hmmsearch(self, sequences, evalue, coverage) -> dict[list]:
+ def _run_hmmsearch(self, sequences, evalue, coverage, threads) -> dict[list]:
  results = {}
  logging.debug("Start hmmsearch")
- for hits in pyhmmer.hmmsearch(self._hmms, sequences):
+ for hits in pyhmmer.hmmsearch(self._hmms, sequences, cpus=threads):
  cog = hits.query_name.decode()
  cog_length = self._hmms_length[cog]
  for hit in hits:
@@ -75,9 +75,9 @@ def _run_hmmsearch(self, sequences, evalue, coverage) -> dict[list]:
  logging.info(f"Found {len(results)} genes have hits")
  return results
 
- def run(self, evalue: float, coverage: float) -> dict[list]:
+ def run(self, evalue: float, coverage: float, threads: int) -> dict[list]:
  self._load_input()
- return self._run_hmmsearch(self._sequences, evalue, coverage)
+ return self._run_hmmsearch(self._sequences, evalue, coverage, threads)
 
 
 def cazyme_finder(input: str, output, evalue: float, coverage: float, **kwargs):

src/dbcanlight/utils.py

@@ -8,7 +8,10 @@ def check_db(*dbs: Path) -> None:
  for db in dbs:
  dbmissingList.append(db) if not db.exists() else None
  if dbmissingList:
- print(f"Database file {*dbmissingList,} missing. \nAborted")
+ print(
+ f"Database file {*dbmissingList,} missing. "
+ "Please follow the instructions in https://github.com/chtsai0105/dbcanLight#requirements and download the required database."
+ )
  sys.exit(1)