linting, add offline setting

SeonghwanSeo · Dec 25, 2024 · e7a7e9a · e7a7e9a
1 parent b8926f2
commit e7a7e9a
Show file tree

Hide file tree

Showing 34 changed files with 512 additions and 271 deletions.
diff --git a/.gitignore b/.gitignore
@@ -1,11 +1,12 @@
 # USER
 .DS_Store
-weights
+weights/
 run.sh
 result/
 examples/library/
 nogit/
 maintain_test/
+uv.lock
 
 
 # Byte-compiled / optimized / DLL files

diff --git a/README.md b/README.md
@@ -1,7 +1,6 @@
-
 # PharmacoNet: Open-source Protein-based Pharmacophore Modeling
-[![DOI](https://zenodo.org/badge/699273873.svg)](https://zenodo.org/doi/10.5281/zenodo.12168474)
 
+[![DOI](https://zenodo.org/badge/699273873.svg)](https://zenodo.org/doi/10.5281/zenodo.12168474)
 
 **Before using PharmacoNet, consider using OpenPharmaco - GUI powered by PharmacoNet.**
 
@@ -32,7 +31,6 @@ If you have any problems or need help with the code, please add an github issue
 - [Pre-trained Docking Proxy](#pretrained-docking-proxy)
 - [Citation](#citation)
 
-
 ## Quick Start
 
 ```bash
@@ -50,6 +48,7 @@ python feature_extraction.py --protein <PROTEIN_PATH> --center <X> <Y> <Z> --out
 ```
 
 ## Installation
+
 - Using `environment.yml`
   For various environment including Linux, MacOS and Window, the script installs **cpu-only version of PyTorch** by default. You can install a cuda-available version by modifying `environment.yml` or installing PyTorch manually.
 
@@ -61,8 +60,9 @@ python feature_extraction.py --protein <PROTEIN_PATH> --center <X> <Y> <Z> --out
   ```
 
 - Manual Installation
+
   ```bash
-  # Required python>=3.9, Best Performance at higher version. (3.9, 3.10, 3.11, 3.12 - best)
+  # Required python>=3.9, Best Performance at higher version. (3.9, 3.10, 3.11, 3.12(best))
   conda create --name openph python=3.10 openbabel=3.1.1 pymol-open-source=3.0.0 numpy=1.26.4
   conda activate pmnet
 
@@ -140,6 +140,15 @@ INFO:root:Save Pharmacophore Model to result/6OIM/6OIM_2.0_-8.0_-1.0_model.pm
 INFO:root:Save Pymol Visualization Session to result/6OIM/6OIM_2.0_-8.0_-1.0_model.pse
 ```
 
+#### Example with custom model weight file (offline)
+
+PharmacoNet's weight file is automatically downloaded during `modeling.py`.
+If your environment is offline, you can download the weight files from [Google Drive](https://drive.google.com/uc?id=1gzjdM7bD3jPm23LBcDXtkSk18nETL04p).
+
+```bash
+> python modeling.py --pdb 6oim --weight_path <WEIGHT_PATH>
+```
+
 ## Virtual Screening
 
 We provide the simple script for screening.
@@ -175,7 +184,7 @@ score = model.scoring_smiles(<SMILES>, <NUM_CONFORMERS>)
 
 ## Pharmacophore Feature Extraction
 
-***See: [`./developer/`](/developer/), [`./src/pmnet_appl/`](/src/pmnet_appl/).***
+**_See: [`./developer/`](/developer/), [`./src/pmnet_appl/`](/src/pmnet_appl/)._**
 
 For deep learning researcher who want to use PharmacoNet as pre-trained model for feature extraction, we provide the python API.
 
@@ -225,19 +234,21 @@ pmnet_attr = (multi_scale_features, hotspot_infos)
 ```
 
 ## Pretrained Docking Proxy
-***See: [`./src/pmnet_appl/`](/src/pmnet_appl/).***
+
+**_See: [`./src/pmnet_appl/`](/src/pmnet_appl/)._**
 
 We provide pre-trained docking proxy models which predict docking score against arbitrary protein using PharmacoNet.
 We hope this implementation prompts the molecule optimization.
 
 If you use this implementation, please cite PharmacoNet with original papers.
 
 Implementation List:
+
 - TacoGFN: Target-conditioned GFlowNet for Structure-based Drug Design [[paper](https://arxiv.org/abs/2310.03223)]
 
 Related Works:
-- RxnFlow: Generative Flows on Synthetic Pathway for Drug Design [paper]
 
+- RxnFlow: Generative Flows on Synthetic Pathway for Drug Design [paper]
 
 ## Citation
 
@@ -252,4 +263,3 @@ Paper on [arxiv](https://arxiv.org/abs/2310.00681)
   url = {https://arxiv.org/abs/2310.00681},
 }
 ```
-
diff --git a/modeling.py b/modeling.py
@@ -24,9 +24,13 @@ def __init__(self):
         cfg_args = self.add_argument_group("config")
         cfg_args.add_argument("--pdb", type=str, help="RCSB PDB code")
         cfg_args.add_argument("-l", "--ligand_id", type=str, help="RCSB ligand code")
-        cfg_args.add_argument("-p", "--protein", type=str, help="custom path of protein pdb file (.pdb)")
+        cfg_args.add_argument(
+            "-p", "--protein", type=str, help="custom path of protein pdb file (.pdb)"
+        )
         cfg_args.add_argument("-c", "--chain", type=str, help="Chain")
-        cfg_args.add_argument("-a", "--all", action="store_true", help="use all binding sites")
+        cfg_args.add_argument(
+            "-a", "--all", action="store_true", help="use all binding sites"
+        )
         cfg_args.add_argument(
             "--out_dir",
             type=str,
@@ -43,8 +47,15 @@ def __init__(self):
 
         # system config
         env_args = self.add_argument_group("environment")
-        env_args.add_argument("--cuda", action="store_true", help="use gpu acceleration with CUDA")
-        env_args.add_argument("--force", action="store_true", help="force to save the pharmacophore model")
+        env_args.add_argument(
+            "--weight_path", type=str, help="(Optional) custom pharmaconet weight path"
+        )
+        env_args.add_argument(
+            "--cuda", action="store_true", help="use gpu acceleration with CUDA"
+        )
+        env_args.add_argument(
+            "--force", action="store_true", help="force to save the pharmacophore model"
+        )
         env_args.add_argument("-v", "--verbose", action="store_true", help="verbose")
 
         # config
@@ -54,12 +65,16 @@ def __init__(self):
             type=str,
             help="path of ligand to define the center of box (.sdf, .pdb, .mol2)",
         )
-        adv_args.add_argument("--center", nargs="+", type=float, help="coordinate of the center")
+        adv_args.add_argument(
+            "--center", nargs="+", type=float, help="coordinate of the center"
+        )
 
 
 def main(args):
     logging.info(pmnet.__description__)
-    assert args.prefix is not None or args.pdb is not None, "MISSING PREFIX: `--prefix` or `--pdb`"
+    assert (
+        args.prefix is not None or args.pdb is not None
+    ), "MISSING PREFIX: `--prefix` or `--pdb`"
     PREFIX = args.prefix if args.prefix else args.pdb
 
     # NOTE: Setting
@@ -70,19 +85,20 @@ def main(args):
     SAVE_DIR.mkdir(exist_ok=True, parents=True)
 
     # NOTE: Load PharmacoNet
-    module = PharmacoNet("cuda" if args.cuda else "cpu")
-    logging.info(f"Load PharmacoNet finish")
+    module = PharmacoNet("cuda" if args.cuda else "cpu", weight_path=args.weight_path)
+    logging.info("Load PharmacoNet finish")
 
     # NOTE: Set Protein
+    protein_path: str
     if isinstance(args.pdb, str):
-        protein_path: str = str(SAVE_DIR / f"{PREFIX}.pdb")
+        protein_path = str(SAVE_DIR / f"{PREFIX}.pdb")
         if not os.path.exists(protein_path):
             logging.info(f"Download {args.pdb} to {protein_path}")
             download_pdb(args.pdb, protein_path)
         else:
             logging.info(f"Load {protein_path}")
     elif isinstance(args.protein, str):
-        protein_path: str = args.protein
+        protein_path = args.protein
         assert os.path.exists(protein_path)
         logging.info(f"Load {protein_path}")
     else:
@@ -96,13 +112,17 @@ def run_pmnet(filename, ligand_path=None, center=None) -> PharmacophoreModel:
             logging.warning(f"Modeling Pass - {model_path} exists")
             pharmacophore_model = PharmacophoreModel.load(str(model_path))
         else:
-            pharmacophore_model = module.run(protein_path, ref_ligand_path=ligand_path, center=center)
+            pharmacophore_model = module.run(
+                protein_path, ref_ligand_path=ligand_path, center=center
+            )
             pharmacophore_model.save(str(model_path))
             logging.info(f"Save Pharmacophore Model to {model_path}")
         if (not args.force) and os.path.exists(pymol_path):
             logging.warning(f"Visualizing Pass - {pymol_path} exists\n")
         else:
-            visualize.visualize_single(pharmacophore_model, protein_path, ligand_path, PREFIX, str(pymol_path))
+            visualize.visualize_single(
+                pharmacophore_model, protein_path, ligand_path, PREFIX, str(pymol_path)
+            )
             logging.info(f"Save Pymol Visualization Session to {pymol_path}\n")
         return pharmacophore_model
 
@@ -173,16 +193,22 @@ def run_pmnet_manual_center():
         if (not args.force) and os.path.exists(pymol_path):
             logging.warning(f"Visualizing Pass - {pymol_path} exists\n")
         else:
-            visualize.visualize_multiple(model_dict, protein_path, PREFIX, str(pymol_path))
+            visualize.visualize_multiple(
+                model_dict, protein_path, PREFIX, str(pymol_path)
+            )
             logging.info(f"Save Pymol Visualization Session to {pymol_path}\n")
         return
 
     inform_list_text = "\n\n".join(str(inform) for inform in inform_list)
-    logging.info(f"A total of {len(inform_list)} ligand(s) are detected!\n{inform_list_text}\n")
+    logging.info(
+        f"A total of {len(inform_list)} ligand(s) are detected!\n{inform_list_text}\n"
+    )
 
     # NOTE: Case 3-3: pattern matching
     if args.ligand_id is not None or args.chain is not None:
-        logging.info(f"Filtering with matching pattern - ligand id: {args.ligand_id}, chain: {args.chain}")
+        logging.info(
+            f"Filtering with matching pattern - ligand id: {args.ligand_id}, chain: {args.chain}"
+        )
         filtered_inform_list = []
         for inform in inform_list:
             if args.ligand_id is not None and args.ligand_id.upper() != inform.id:
@@ -201,7 +227,9 @@ def run_pmnet_manual_center():
             return FAIL
         if len(inform_list) > 1:
             inform_list_text = "\n\n".join(str(inform) for inform in inform_list)
-            logging.info(f"A total of {len(inform_list)} ligands are selected!\n{inform_list_text}\n")
+            logging.info(
+                f"A total of {len(inform_list)} ligands are selected!\n{inform_list_text}\n"
+            )
 
     if len(inform_list) == 1:
         run_pmnet_inform(inform_list[0])

diff --git a/pyproject.toml b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pharmaconet"
-version = "2.1.0"
+version = "2.1.1"
 description = "PharmacoNet: Open-Source Software for Protein-based Pharmacophore Modeling and Virtual Screening"
 license = { text = "MIT" }
 authors = [{ name = "Seonghwan Seo", email = "shwan0106@kaist.ac.kr" }]
@@ -31,7 +31,8 @@ dependencies = [
   "omegaconf>=2.3.0",
   "molvoxel>=0.1.3",
   "gdown>=5.1.0",
-  "biopython>=1.83"
+  "biopython>=1.83",
+  "ruff>=0.8.4",
 ]
 
 [project.optional-dependencies]
@@ -68,19 +69,22 @@ line-length = 120
 select = ["E", "F", "B", "UP", "T203",]
 ignore = ["E501"]
 
-[tool.ruff.per-file-ignores]
+[tool.ruff.lint.per-file-ignores]
 "__init__.py" = [
     "F401", # imported but unused
     "E402", # Module level import not at top of file
 ]
 
-[tool.pyright]
+[tool.basedpyright]
 pythonVersion = "3.10"
 typeCheckingMode = "standard"
 diagnosticMode = "openFilesOnly"
 reportImplicitStringConcatenation = false
+useLibraryCodeForTypes = true
 reportGeneralTypeIssues = "warning"
 reportDeprecated = "warning"
 reportUnusedVariable = false
 reportUnusedImport = false
-
+venvPath = '.'
+venv = '.venv'
+exclude = [".venv/"]
diff --git a/src/pmnet/__init__.py b/src/pmnet/__init__.py
@@ -1,11 +1,7 @@
 from .pharmacophore_model import PharmacophoreModel
 
-__version__ = "2.1.0"
-__citation_information__ = (
-    "Seo, S., & Kim, W. Y. (2023, December). "
-    "PharmacoNet: Accelerating Large-Scale Virtual Screening by Deep Pharmacophore Modeling. "
-    "In NeurIPS 2023 Workshop on New Frontiers of AI for Drug Discovery and Development."
-)
+__version__ = "2.1.1"
+__citation_information__ = "Seo, S., & Kim, W. Y. (2024). PharmacoNet: deep learning-guided pharmacophore modeling for ultra-large-scale virtual screening. Chemical Science, 15(46), 19473-19487."
 __maintainer__ = "https://github.com/SeonghwanSeo/PharmacoNet"
 
 __description__ = (

diff --git a/src/pmnet/data/constant.py b/src/pmnet/data/constant.py
@@ -1,4 +1,4 @@
-from typing import Sequence, Set
+from collections.abc import Sequence
 
 INTERACTION_LIST: Sequence[str] = (
     "Hydrophobic",
@@ -40,7 +40,7 @@
     XBOND: 4.5,  # 4.0 + 0.5
 }
 
-LONG_INTERACTION: Set[int] = {
+LONG_INTERACTION: set[int] = {
     PISTACKING_P,
     PISTACKING_T,
     PICATION_PRING,
@@ -49,7 +49,7 @@
     SALTBRIDGE_PNEG,
 }
 
-SHORT_INTERACTION: Set[int] = {
+SHORT_INTERACTION: set[int] = {
     HYDROPHOBIC,
     HBOND_LDON,
     HBOND_PDON,

diff --git a/src/pmnet/data/extract_pocket.py b/src/pmnet/data/extract_pocket.py
@@ -5,7 +5,6 @@
 from Bio.PDB import PDBParser, PDBIO
 from Bio.PDB.PDBIO import Select
 
-from typing import Union
 from numpy.typing import ArrayLike
 from pathlib import Path
 
@@ -87,7 +86,7 @@ def accept_residue(self, residue):
 
 
 def extract_pocket(
-    protein_pdb_path: Union[str, Path], out_pocket_pdb_path: str, center: ArrayLike, cutoff: float = DEFAULT_CUTOFF
+    protein_pdb_path: str | Path, out_pocket_pdb_path: str, center: ArrayLike, cutoff: float = DEFAULT_CUTOFF
 ):
     parser = PDBParser()
     structure = parser.get_structure("protein", str(protein_pdb_path))