De Novo KOR Antagonists Datasets

Datasets used as input, generated or analyzed in the manuscript De Novo Design of κ-Opioid Receptor Antagonists Using a Generative Deep Learning Framework: 1. Pre-training Dataset #1 (4.6 million compounds from ZINC 20): zinc20_train.csv (494 MB) 2. Pre-training test set (0.5 million compounds from ZINC 20): zinc20_test.csv (55 MB) 3. Pre-training test scaffolds set (0.5 million compounds from ZINC 20): zinc20_test_scaffolds.csv (57 MB) 4. Pre-training Dataset #2 (2,056 compounds from ChEMBL with IC50 data): chembl30_kor_inhibitors.csv (144 KB) 5. 169 compounds prioritized for chemical synthesis on the basis of their similarity to JDTic's interactions with KOR: prioritized_169candidates_from1M_by_SIFt_Tc.csv (17 KB) All datasets are in Simplified Molecular Input Line Entry System (SMILES) format.