FragFM: Efficient Fragment-Based Molecular Generation via Discrete Flow Matching

Joongwon Lee, Seonghwan Kim, Woo Youn Kim

Track: Machine learning: computational method and/or computational results

Nature Biotechnology: Yes

Keywords: Molecular generative model, Molecular graph, Discrete flow mathcing, Graph generative model, Fragment-based drug discovery

TL;DR: We introduce FragFM, a fragment-based discrete flow matching framework that improves scalability, property control, and sampling efficiency in molecular generation.

Abstract: We introduce FragFM, a novel fragment-based discrete flow matching framework for molecular graph generation. FragFM generates molecules at the fragment level, leveraging a coarse-to-fine autoencoding mechanism to reconstruct atom-level details. This approach reduces computational complexity while maintaining high chemical validity, enabling more efficient and scalable molecular generation. We benchmark FragFM against state-of-the-art diffusion- and flow-based models on standard molecular generation benchmarks and natural product datasets, demonstrating superior performance in validity, property control, and sampling efficiency. Notably, FragFM achieves over 99\% validity with significantly fewer sampling steps, improving scalability while preserving molecular diversity. These results highlight the potential of fragment-based generative modeling for large-scale, property-aware molecular design, paving the way for more efficient exploration of chemical space.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Presenter: ~Joongwon_Lee2

Format: Yes, the presenting author will definitely attend in person because they attending ICLR for other complementary reasons.

Funding: No, the presenting author of this submission does *not* fall under ICLR’s funding aims, or has sufficient alternate funding.

Submission Number: 67