pepe-cli 1.3.0__tar.gz → 1.4.0__tar.gz

{pepe_cli-1.3.0 → pepe_cli-1.4.0}/MANIFEST.in

@@ -3,6 +3,7 @@ include LICENSE
 include requirements.txt
 include pyproject.toml
 recursive-include src *.py
+include src/pepe/py.typed
 recursive-include examples *
 recursive-exclude * __pycache__
 recursive-exclude * *.py[co]

{pepe_cli-1.3.0/src/pepe_cli.egg-info → pepe_cli-1.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pepe-cli
-Version: 1.3.0
+Version: 1.4.0
 Summary: Pipeline for Easy Protein Embedding - Extract embeddings and attention matrices from protein sequences
 Home-page: https://github.com/csi-greifflab/pepe-cli
 Author: Jahn Zhong

{pepe_cli-1.3.0 → pepe_cli-1.4.0}/pyproject.toml

@@ -52,5 +52,29 @@ package-dir = {"" = "src"}
 [tool.setuptools.packages.find]
 where = ["src"]
 
+[tool.setuptools.package-data]
+pepe = ["py.typed"]
+
 [tool.setuptools.dynamic]
 version = {attr = "pepe.__version__"}
+
+[tool.mypy]
+python_version = "3.10"
+warn_return_any = false
+warn_unused_ignores = true
+ignore_missing_imports = true
+check_untyped_defs = false
+disallow_untyped_defs = false
+
+[[tool.mypy.overrides]]
+module = [
+    "pepe.api",
+    "pepe.model_selecter",
+    "pepe.model_errors",
+    "pepe.embedders.base_embedder",
+    "pepe.embedders.huggingface_embedder",
+    "pepe.embedders.custom_embedder",
+    "pepe.embedders.esm_embedder",
+    "pepe.utils",
+]
+check_untyped_defs = true

{pepe_cli-1.3.0 → pepe_cli-1.4.0}/src/pepe/__init__.py

@@ -7,7 +7,7 @@ except ImportError:
     pass
 
 # Package metadata - single source of truth
-__version__ = "1.3.0"
+__version__ = "1.4.0"
 __package_name__ = "pepe-cli"
 __module_name__ = "pepe"
 __author__ = "Jahn Zhong"
@@ -16,7 +16,7 @@ __description__ = "Pipeline for Easy Protein Embedding - Extract embeddings and
 __homepage__ = "https://github.com/csi-greifflab/pepe-cli"
 
 
-# Configure logging for the embedairr package
+# Configure logging for the pepe package
 def setup_logging(level=logging.INFO):
     """Set up logging configuration for the PEPE package."""
     # Create formatter
@@ -30,7 +30,7 @@ def setup_logging(level=logging.INFO):
     console_handler.setFormatter(formatter)
 
     # Get root logger for the package
-    logger = logging.getLogger("src")
+    logger = logging.getLogger("pepe")
     logger.setLevel(level)
 
     # Remove existing handlers to avoid duplication

pepe_cli-1.4.0/src/pepe/__main__.py

@@ -0,0 +1,48 @@
+import logging
+import sys
+from pepe.parse_arguments import parse_arguments
+
+logger = logging.getLogger("pepe.__main__")
+
+
+def main():
+    args = parse_arguments()
+
+    if args.check_model:
+        from pepe.model_selecter import report_model
+
+        report_model(args.check_model, trust_remote_code=args.trust_remote_code)
+        return
+
+    missing = []
+    if not args.model_name:
+        missing.append("--model_name")
+    if not args.fasta_path:
+        missing.append("--fasta_path")
+    if not args.output_path:
+        missing.append("--output_path")
+    if missing:
+        print(
+            f"Error: the following arguments are required: {', '.join(missing)}",
+            file=sys.stderr,
+        )
+        sys.exit(2)
+
+    # Lazy import to avoid loading heavy dependencies during --help
+    from pepe.model_selecter import select_model
+
+    selected_model = select_model(
+        args.model_name, trust_remote_code=args.trust_remote_code
+    )
+
+    embedder = selected_model(args)
+
+    logger.info("Embedder initialized")
+
+    embedder.run()
+
+    logger.info("All outputs saved.")
+
+
+if __name__ == "__main__":
+    main()

{pepe_cli-1.3.0 → pepe_cli-1.4.0}/src/pepe/api.py

@@ -90,15 +90,19 @@ def embed(
         "split_long_sequences": kwargs.get("split_long_sequences", False),
         "split_overlap": kwargs.get("split_overlap", 0),
         "force_split_length": kwargs.get("force_split_length"),
+        "trust_remote_code": kwargs.get("trust_remote_code", False),
         "num_workers": kwargs.get("num_workers", 8),
         "disable_special_tokens": kwargs.get("disable_special_tokens", False),
         "flatten": kwargs.get("flatten", False),
         "flush_batches_after": kwargs.get("flush_batches_after", 128),
+        "verbose": kwargs.get("verbose", False),
     }
     
     args = SimpleNamespace(**args_dict)
     
-    selected_model_class = select_model(model_name)
+    selected_model_class = select_model(
+        model_name, trust_remote_code=args.trust_remote_code
+    )
     embedder = selected_model_class(args)
     embedder.run()