CA_DEL_database

Introduction This dataset contains molecular docking results and pre-computed CNN features for Carbonic Anhydrase (CAH) targets. The data is organized into four main directories: three dedicated to specific protein targets (CAH12, CAH2, CAH9) and one dedicated to validation/evaluation data. Data Structure O43570_CAH12/: Data for Target CAH12 (UniProt: O43570). P00918_CAH2/: Data for Target CAH2 (UniProt: P00918). Q16790_CAH9/: Data for Target CAH9 (UniProt: Q16790). valid/: Aggregated validation set containing features and evaluation CSVs for all targets. Detailed Tree Structure root/ │ ├── O43570_CAH12/ # Target 1: CAH12 │ ├── output_3p3h.tar.gz # Raw docking output for PDB 3p3h │ ├── output_5doh.tar.gz # Raw docking output for PDB 5doh │ ├── 3p3h.pt # CNN features for PDB 3p3h │ ├── 5doh.pt # CNN features for PDB 5doh │ └── data_cah12and2.csv # Associated data CSV │ ├── P00918_CAH2/ # Target 2: CAH2 │ ├── output_4ht2.tar.gz # Raw docking output for PDB 4ht2 │ ├── output_4kp5.tar.gz # Raw docking output for PDB 4kp5 │ ├── 4ht2.pt # CNN features for PDB 4ht2 │ ├── 4kp5.pt # CNN features for PDB 4kp5 │ └── data_cah12and2.csv # Associated data CSV │ ├── Q16790_CAH9/ # Target 3: CAH9 │ ├── output_2hkf.tar.gz # Raw docking output for PDB 2hkf │ ├── output_5fl4.tar.gz # Raw docking output for PDB 5fl4 │ ├── 2hkf.pt # CNN features for PDB 2hkf │ ├── 5fl4.pt # CNN features for PDB 5fl4 │ ├── data_cah9.csv # Main data CSV for CAH9 │ └── data_cah9_ligand.csv # Ligand specific data for CAH9 │ └── valid/ # Validation Set ├── O43570.tar.gz # Validation docking raw files (CAH12) ├── P00918.tar.gz # Validation docking raw files (CAH2) ├── Q16790.tar.gz # Validation docking raw files (CAH9) ├── cnn_feats_hca_ChEMBL_*.pt # Feature files for validation (2hkf, 3p3h, etc.) ├── df_eval_data_O43570.csv # Evaluation dataset for CAH12 ├── df_eval_data_P00918.csv # Evaluation dataset for CAH2 └── df_eval_data_Q16790.csv # Evaluation dataset for CAH9