FlexiFlow: decomposable flow matching for generation of flexible molecular ensemble

TL;DR

FlexiFlow is a novel generative model that efficiently produces diverse molecular conformations and ensembles, improving over existing methods by capturing conformational diversity and enabling faster inference for drug discovery.

Contribution

We introduce FlexiFlow, a flow-matching architecture that jointly samples molecules and multiple conformations, preserving equivariance and permutation invariance, advancing 3D molecular generation techniques.

Findings

Achieves state-of-the-art results on QM9 and GEOM Drugs datasets.

Generates valid, unique, and diverse molecules with high fidelity.

Provides conformational ensembles comparable to physics-based methods at lower inference cost.

Abstract

Sampling useful three-dimensional molecular structures along with their most favorable conformations is a key challenge in drug discovery. Current state-of-the-art 3D de-novo design flow matching or diffusion-based models are limited to generating a single conformation. However, the conformational landscape of a molecule determines its observable properties and how tightly it is able to bind to a given protein target. By generating a representative set of low-energy conformers, we can more directly assess these properties and potentially improve the ability to generate molecules with desired thermodynamic observables. Towards this aim, we propose FlexiFlow, a novel architecture that extends flow-matching models, allowing for the joint sampling of molecules along with multiple conformations while preserving both equivariance and permutation invariance. We demonstrate the effectiveness of our approach on the QM9 and GEOM Drugs datasets, achieving state-of-the-art results in molecular generation tasks. Our results show that FlexiFlow can generate valid, unstrained, unique, and novel molecules with high fidelity to the training data distribution, while also capturing the conformational diversity of molecules. Moreover, we show that our model can generate conformational ensembles that provide similar coverage to state-of-the-art physics-based methods at a fraction of the inference time. Finally, FlexiFlow can be successfully transferred to the protein-conditioned ligand generation task, even when the dataset contains only static pockets without accompanying conformations.