Merge pull request #688 from kbase/dev_add_eggnog_container

pass program threads to tools

src/loaders/compute_tools/eggnog/eggnog.py

@@ -12,14 +12,14 @@
 from src.loaders.compute_tools.tool_common import ToolRunner, run_command
 
 INPUT_TYPE = 'proteins'
-THREADS = 8
 
 
 def _run_eggnog_single(
         tool_safe_data_id: str,
         data_id: str,
         source_file: Path,
         output_dir: Path,
+        program_threads: int,
         debug: bool) -> None:
 
     metadata_file = output_dir / EGGNOG_METADATA
@@ -33,7 +33,7 @@ def _run_eggnog_single(
                '-o', output_dir / source_file.name,  # Output prefix.
                                                      # Save result file to collectiondata directory. Expecting 'emapper.annotations', 'emapper.hits' and  'emapper.seed_orthologs' files.
                '--itype', f'{INPUT_TYPE}',
-               '--cpu', f'{THREADS}',
+               '--cpu', f'{program_threads}',
                '--excel',
                '--sensmode', 'fast',
                '--dmnd_iterate', 'no',

src/loaders/compute_tools/eggnog/versions.yaml

@@ -1,4 +1,10 @@
 versions:
   - version: 0.1.0
     date: 2024-03-13
+    reference_db_version: 5.0.2
+
+  - version: 0.1.1
+    date: 2024-03-15
+    notes: |
+      - add ability to specify thread number for execution
     reference_db_version: 5.0.2

src/loaders/compute_tools/mash/mash.py

@@ -16,6 +16,7 @@ def _run_mash_single(
         data_id: str,
         source_file: Path,
         output_dir: Path,
+        program_threads: int,
         debug: bool,
         kmer_size: int = KMER_SIZE,
         sketch_size: int = SKETCH_SIZE) -> None:
@@ -25,6 +26,7 @@ def _run_mash_single(
                                    # Save result file to source file directory. The suffix '.msh' will be appended.
                '-k', f'{kmer_size}',
                '-s', f'{sketch_size}',
+               '-p', f'{program_threads}',
                source_file]
 
     run_command(command, output_dir if debug else None)

src/loaders/compute_tools/mash/versions.yaml

@@ -2,4 +2,8 @@ versions:
   - version: 0.1.0
     date: 2023-07-18
   - version: 0.1.1
-    date: 2023-07-19
+    date: 2023-07-19
+  - version: 0.1.2
+    date: 2024-03-15
+    notes: |
+      - add ability to specify thread number for execution

src/loaders/compute_tools/microtrait/microtrait.py

@@ -186,7 +186,13 @@ def _process_trait_counts(
     return heatmap_row, cells_meta, traits_meta
 
 
-def _run_microtrait(tool_safe_data_id: str, data_id: str, fna_file: Path, genome_dir: Path, debug: bool):
+def _run_microtrait(
+        tool_safe_data_id: str,
+        data_id: str,
+        fna_file: Path,
+        genome_dir: Path,
+        program_threads: int,
+        debug: bool):
     # run microtrait.extract_traits on the genome file
     # https://github.com/ukaraoz/microtrait
 
@@ -198,6 +204,10 @@ def _run_microtrait(tool_safe_data_id: str, data_id: str, fna_file: Path, genome
     #     object returned by the
     #     extract_traits function.
 
+    # programe_threads is not used in this function, but it is kept for consistency with another tools (e.g., eggnog, mash)
+    # since extract_traits function doesn't take the number of threads as an argument
+    # https://github.com/ukaraoz/microtrait/blob/master/R/extract_traits.R#L22-L26
+
     # Load the R script as an R function
     r_script = """
         library(microtrait)

src/loaders/compute_tools/tool_common.py

@@ -246,7 +246,7 @@ def _get_data_ids(self):
             data_ids = all_data_ids
         return list(set(data_ids))
 
-    def parallel_single_execution(self, tool_callable: Callable[[str, str, Path, Path, bool], None], unzip=False):
+    def parallel_single_execution(self, tool_callable: Callable[[str, str, Path, Path, int, bool], None], unzip=False):
         """
         Run a tool by a single data file, storing the results in a single batch directory with
         the individual runs stored in directories by the data ID.
@@ -298,6 +298,7 @@ def parallel_single_execution(self, tool_callable: Callable[[str, str, Path, Pat
                  meta.get(loader_common_names.META_UNCOMPRESSED_FILE,
                           meta[loader_common_names.META_SOURCE_FILE]),
                  output_dir,
+                 self._program_threads,
                  self._debug))
 
         try:
@@ -378,7 +379,7 @@ def _execute(
             self,
             threads: int,
             tool_callable: Callable[..., None],
-            args: List[Tuple[Dict[str, GenomeTuple], Path, int, bool]],
+            args: List[Tuple[Dict[str, GenomeTuple], Path, int, bool]] | List[Tuple[str, str, Path, Path, int, bool]],
             start: datetime.datetime,
             total: bool,
     ):