Supplementary Material A Additional Results A.1 Molecule Design

Neural Information Processing Systems 

We present more examples of generated molecules by our method and the CNN baseline liGAN. We select 6 molecules with highest binding affinity for each method and each binding site. To summarize, these examples evidence the proposed model's good We randomly selected 5 cases from the testing set. At the first step of molecule generation, there is no placed atoms in the binding site. The proposal distribution is a Gaussian with 0.1Å standard The resolution of the meshgrid is 0.1Å.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found