MolGAN: An implicit generative model for small molecular graphs

TLDR

Deep generative models for graph-structured data enable chemical synthesis by directly generating molecular graphs, avoiding costly discrete search procedures. The paper introduces MolGAN, an implicit, likelihood‑free generative model for small molecular graphs that bypasses expensive graph matching and node ordering. MolGAN adapts GANs to graph data and incorporates a reinforcement‑learning objective to bias generation toward desired chemical properties. On the QM9 dataset, MolGAN generates nearly 100 % valid molecules and outperforms recent SMILES‑based and likelihood‑based graph generators, though it can suffer from mode collapse. Code is available at https://github.com/nicola-decao/MolGAN.

Abstract

Deep generative models for graph-structured data offer a new angle on the problem of chemical synthesis: by optimizing differentiable models that directly generate molecular graphs, it is possible to side-step expensive search procedures in the discrete and vast space of chemical structures. We introduce MolGAN, an implicit, likelihood-free generative model for small molecular graphs that circumvents the need for expensive graph matching procedures or node ordering heuristics of previous likelihood-based methods. Our method adapts generative adversarial networks (GANs) to operate directly on graph-structured data. We combine our approach with a reinforcement learning objective to encourage the generation of molecules with specific desired chemical properties. In experiments on the QM9 chemical database, we demonstrate that our model is capable of generating close to 100% valid compounds. MolGAN compares favorably both to recent proposals that use string-based (SMILES) representations of molecules and to a likelihood-based method that directly generates graphs, albeit being susceptible to mode collapse. Code at https://github.com/nicola-decao/MolGAN