Any-Property-Conditional Molecule Generation with Self-Criticism Using Spanning Trees

Abstract

Generating novel molecules is challenging, with most representations of molecules leading to generative models producing many invalid molecules. Spanning Tree-based Graph Generation (STGG) is a promising approach to ensure the generation of valid molecules, outperforming state-of-the-art generative models for unconditional generation. In practice, it is desirable to generate molecules conditional on one or multiple target properties rather than unconditionally. Thus, we extend STGG to multi-property conditional generation. Our approach, STGG+, incorporates a modern Transformer architecture, random masking of properties during training (enabling conditioning on any subset of properties and classifier-free guidance), an auxiliary property-prediction loss (allowing the model to self-criticize molecules and select the best ones), and other improvements. We show that STGG+ achieves state-of-the-art performance on in-distribution and out-of-distribution conditional generation, as well as reward maximization.