Generating Cyclic Conformers with Flow Matching in Cremer-Pople Coordinates

TL;DR

PuckerFlow is a novel machine learning model that efficiently generates diverse and accurate conformers of cyclic molecules by leveraging flow matching in Cremer-Pople coordinates, improving over existing methods.

Contribution

The paper introduces PuckerFlow, a flow matching-based generative model for cyclic conformers that operates in Cremer-Pople space, enabling reliable and diverse ring structure generation.

Findings

PuckerFlow outperforms existing conformer generation methods on multiple metrics.

The model effectively generates valid closed ring conformers with high diversity.

Demonstrates potential in drug discovery and catalysis applications.

Abstract

Cyclic molecules are ubiquitous across applications in chemistry and biology. Their restricted conformational flexibility provides structural pre-organization that is key to their function in drug discovery and catalysis. However, reliably sampling the conformer ensembles of ring systems remains challenging. Here, we introduce PuckerFlow, a generative machine learning model that performs flow matching on the Cremer-Pople space, a low-dimensional internal coordinate system capturing the relevant degrees of freedom of rings. Our approach enables generation of valid closed rings by design and demonstrates strong performance in generating conformers that are both diverse and precise. We show that PuckerFlow outperforms other conformer generation methods on nearly all quantitative metrics and illustrate the potential of PuckerFlow for ring systems relevant to chemical applications, particularly in catalysis and drug discovery. This work enables efficient and reliable conformer generation of cyclic structures, paving the way towards modeling structure-property relationships and the property-guided generation of rings across a wide range of applications in chemistry and biology.