From Target to Drug: Generative Modeling for the Multimodal Structure-Based Ligand Design

TLDR

Chemical space is impractically large, and conventional structure‑based virtual screening cannot simply search it to find effective bioactive molecules. The authors propose a generative adversarial network that generates diverse 3D ligand shapes complementary to a target pocket instead of searching the space. Generated shapes are decoded into SMILES by a shape‑captioning network, and the method is evaluated with docking and QSAR virtual screening. Both docking and QSAR evaluations show enrichment versus random sampling from ZINC drug‑like compounds.

Abstract

Chemical space is impractically large, and conventional structure-based virtual screening techniques cannot be used to simply search through the entire space to discover effective bioactive molecules. To address this shortcoming, we propose a generative adversarial network to generate, rather than search, diverse three-dimensional ligand shapes complementary to the pocket. Furthermore, we show that the generated molecule shapes can be decoded using a shape-captioning network into a sequence of SMILES enabling directly the structure-based de novo drug design. We evaluate the quality of the method by both structure- (docking) and ligand-based [quantitative structure–activity relationship (QSAR)] virtual screening methods. For both evaluation approaches, we observed enrichment compared to random sampling from initial chemical space of ZINC drug-like compounds.