Skip to main content


Fig. 10 | Journal of Cheminformatics

Fig. 10

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

Fig. 10

Comparison of the chemical space of active ligands in the A2AR set and generated molecules by DrugEx (fine-tuned, ac), DrugEx (pre-trained, df), REINVENT (gi), and ORGANIC (jl). Chemical Space was represented by logP ~ MW (a, d, g, j), the first two components in PCA on PhysChem descriptors (b, e, h, k), and t-SNE on ECFP6 fingerprints (c, f, i, l)

Back to article page