mt

src/pynteny/preprocessing.py

@@ -557,7 +557,7 @@ def annotate(
             utils.parallelize_over_input_files(
                 wrappers.run_prodigal,
                 input_list=list(contigs_dir.iterdir()),
-                n_processes=processes,
+                processes=processes,
                 output_dir=prodigal_dir,
                 output_format="fasta",
                 metagenome=metagenome,
@@ -634,6 +634,7 @@ def build(
         seq_prefix: str = None,
         prepend_file_name: bool = False,
         output_file: Path = None,
+        processes: int = None,
     ) -> LabelledFASTA:
         """Build database from data files.
 
@@ -643,6 +644,7 @@ def build(
             prepend_file_name (bool, optional): whether to add file name as genome ID to
                 each record in the result merged fasta file.
             output_file (Path, optional): path to output file. Defaults to None.
+            processes (int, optional): maximum number of threads. Defaults to all minus one.
 
         Returns:
             LabelledFASTA: object containing the labelled peptide database.
@@ -663,7 +665,8 @@ def build(
                     assembly_fasta = FASTA(self._data)
                 logger.info("Translating and annotating assembly data.")
                 labelled_database = GeneAnnotator(assembly_fasta).annotate(
-                    output_file=output_file
+                    output_file=output_file,
+                    processes=processes,
                 )
         elif self.is_gbk(self._data_files[0]):
             logger.info("Parsing GenBank data.")

src/pynteny/subcommands.py

@@ -181,6 +181,7 @@ def build_database(args: Union[CommandArgs, ArgumentParser]) -> None:
     database.build(
         output_file=args.outfile,
         prepend_file_name=prepend_file_name,
+        processes=args.processes,
     )
     logger.info("Database built successfully!")
     logging.shutdown()

src/pynteny/utils.py

@@ -172,7 +172,7 @@ def terminal_execute(
 
 
 def parallelize_over_input_files(
-    callable, input_list: list, n_processes: int = None, **callable_kwargs
+    callable, input_list: list, processes: int = None, **callable_kwargs
 ) -> None:
     """Parallelize callable over a set of input objects using a pool
     of workers. Inputs in input list are passed to the first argument
@@ -184,9 +184,9 @@ def parallelize_over_input_files(
         n_processes (int, optional): maximum number of threads.
             Defaults to all minus one.
     """
-    if n_processes is None:
-        n_processes = os.cpu_count - 1
-    p = Pool(processes=n_processes)
+    if processes is None:
+        processes = os.cpu_count - 1
+    p = Pool(processes=processes)
     p.map(partial(callable, **callable_kwargs), input_list)
     p.close()
     p.join()