An exploration strategy improves the diversity of de novo ligands using deep reinforcement learning: a case for the adenosine A2A receptor

Table 2 Comparison of the percentage of important substructures contained in the molecules generated by the different methods and the molecules in the ZINC and A2AR sets

These methods contained DrugEx with pre-trained and fine-tuned model as different G_φ (in the parentheses), REINVENT, ORGANIC, Pre-trained model, and Fine-tuned model

ISSN: 1758-2946