De Novo KOR Antagonists Datasets

<p>Datasets&nbsp;used as input, generated or analyzed in the manuscript&nbsp;<strong>De Novo Design of&nbsp;</strong><strong>&kappa;</strong><strong>-Opioid Receptor Antagonists Using a Generative Deep Learning Framework</strong>:</p> <p>1. Pre-training Dataset #1 (4.6 million compounds from&nbsp;ZINC 20):&nbsp;zinc20_train.csv (494 MB)<br> 2. Pre-training test set (0.5 million compounds from ZINC 20):&nbsp;zinc20_test.csv (55 MB)<br> 3. Pre-training test scaffolds set (0.5 million compounds from ZINC 20):&nbsp;zinc20_test_scaffolds.csv (57 MB)<br> 4. Pre-training Dataset #2 (2,056 compounds from&nbsp;ChEMBL with IC50 data): &nbsp;chembl30_kor_inhibitors.csv (144 KB)<br> 5. 169 compounds prioritized for chemical synthesis on the basis of their similarity to JDTic&#39;s interactions with KOR:&nbsp;prioritized_169candidates_from1M_by_SIFt_Tc.csv (17 KB)<br> <br> All datasets are in&nbsp;Simplified Molecular Input Line Entry System (SMILES) format.</p>