FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generation

TL;DR

FlowMol3 is a novel flow matching model for 3D small-molecule generation that significantly improves validity, accuracy, and efficiency using architecture-agnostic techniques, advancing chemical discovery.

Contribution

The paper introduces FlowMol3, a new flow matching model with three simple techniques that enhance performance without changing the core architecture.

Findings

Achieves nearly 100% validity for drug-like molecules with explicit hydrogens.

Reproduces functional group composition and geometry more accurately.

Uses fewer parameters than comparable methods.

Abstract

A generative model capable of sampling realistic molecules with desired properties could accelerate chemical discovery across a wide range of applications. Toward this goal, significant effort has focused on developing models that jointly sample molecular topology and 3D structure. We present FlowMol3, an open-source, multi-modal flow matching model that advances the state of the art for all-atom, small-molecule generation. Its substantial performance gains over previous FlowMol versions are achieved without changes to the graph neural network architecture or the underlying flow matching formulation. Instead, FlowMol3's improvements arise from three architecture-agnostic techniques that incur negligible computational cost: self-conditioning, fake atoms, and train-time geometry distortion. FlowMol3 achieves nearly 100% molecular validity for drug-like molecules with explicit hydrogens, more accurately reproduces the functional group composition and geometry of its training data, and does so with an order of magnitude fewer learnable parameters than comparable methods. We hypothesize that these techniques mitigate a general pathology affecting transport-based generative models, enabling detection and correction of distribution drift during inference. Our results highlight simple, transferable strategies for improving the stability and quality of diffusion- and flow-based molecular generative models.