Fig. 16
From: Mol-CycleGAN: a generative model for molecular optimization
Results of iterative procedure of the unconstrained optimization. a Distribution of the penalized logP in the starting set and after \(K=1, 5, 10, 30\) iterations. b Distribution of the Tanimoto similarity between the starting molecules X and random molecules from ZINC-250K, as well as those generated after \(K=1, 2, 5, 10\) iterations. c Plot of the mean value, percentiles (75th and 90th), and the maximum value of penalized logP as a function of the number of iterations