MolGuidance: Advanced Guidance Strategies for Conditional Molecular Generation with Flow Matching
This work addresses the problem of generating molecules with specific properties for drug discovery and materials science, representing an incremental improvement by adapting existing guidance methods to a molecular context.
The paper tackled conditional molecular generation by integrating advanced guidance strategies into a flow matching framework, achieving new state-of-the-art performance in property alignment on QM9 and QMe14S datasets while ensuring high structural validity.
Key objectives in conditional molecular generation include ensuring chemical validity, aligning generated molecules with target properties, promoting structural diversity, and enabling efficient sampling for discovery. Recent advances in computer vision introduced a range of new guidance strategies for generative models, many of which can be adapted to support these goals. In this work, we integrate state-of-the-art guidance methods -- including classifier-free guidance, autoguidance, and model guidance -- in a leading molecule generation framework built on an SE(3)-equivariant flow matching process. We propose a hybrid guidance strategy that separately guides continuous and discrete molecular modalities -- operating on velocity fields and predicted logits, respectively -- while jointly optimizing their guidance scales via Bayesian optimization. Our implementation, benchmarked on the QM9 and QMe14S datasets, achieves new state-of-the-art performance in property alignment for de novo molecular generation. The generated molecules also exhibit high structural validity. Furthermore, we systematically compare the strengths and limitations of various guidance methods, offering insights into their broader applicability.