LGBMJul 12, 2024

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

arXiv:2407.09357v35 citationsh-index: 21
Originality Incremental advance
AI Analysis

This work addresses the need for multi-property-conditional molecule generation in drug discovery, representing an incremental improvement over existing methods.

The authors tackled the problem of generating molecules conditional on multiple desired properties by extending a spanning tree-based graph generation method, achieving state-of-the-art performance in conditional generation and reward maximization.

Generating novel molecules is challenging, with most representations 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 SMILES and graph diffusion models for unconditional generation. In the real world, we want to be able to generate molecules conditional on one or multiple desired properties rather than unconditionally. Thus, in this work, 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, and reward maximization.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes