FragFM: Hierarchical Framework for Efficient Molecule Generation via Fragment-Level Discrete Flow Matching

TL;DR

FragFM is a hierarchical, fragment-level discrete flow matching framework that improves efficiency and property control in molecular graph generation, especially for natural product-like molecules, outperforming existing models.

Contribution

Introduces FragFM, a novel hierarchical fragment-based generative framework with a coarse-to-fine autoencoder and stochastic fragment bag strategy for scalable molecule generation.

Findings

FragFM achieves better property control than atom-based methods.

FragFM demonstrates superior performance on the NPGen benchmark.

The framework enables efficient exploration of chemical space for drug discovery.

Abstract

We introduce FragFM, a novel hierarchical framework via fragment-level discrete flow matching for efficient molecular graph generation. FragFM generates molecules at the fragment level, leveraging a coarse-to-fine autoencoder to reconstruct details at the atom level. Together with a stochastic fragment bag strategy to effectively handle a large fragment space, our framework enables more efficient, scalable molecular generation. We demonstrate that our fragment-based approach achieves better property control than the atom-based method and additional flexibility through conditioning the fragment bag. We also propose a Natural Product Generation benchmark (NPGen) to evaluate the ability of modern molecular graph generative models to generate natural product-like molecules. Since natural products are biologically prevalidated and differ from typical drug-like molecules, our benchmark provides a more challenging yet meaningful evaluation relevant to drug discovery. We conduct a comparative study of FragFM against various models on diverse molecular generation benchmarks, including NPGen, demonstrating superior performance. The 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.