Multimodal Bonds Reconstruction Towards Generative Molecular Design

Abstract

Generative models such as diffusion-based approaches have transformed de novo drug design by enabling rapid generation of novel molecular structures in both 2D and 3D formats. However, accurate reconstruction of chemical bonds, especially from distorted geometries produced by generative models, remains a critical challenge. Here, we present YuelBond, a multimodal graph neural network framework for robust bonds reconstruction across three key scenarios: (i) recovery of bonds from accurate 3D atomic coordinates, (ii) reconstruction of chemically valid bonds in crude de novo generated compounds (CDGs) with perturbed geometries, and (iii) reassignment of bond orders in 2D topological graphs. YuelBond outperforms traditional rule-based methods such as RDKit, achieving 98.4% F1-score on standard 3D structures and maintaining strong performance (92.7% F1-score) on distorted CDGs, even when RDKit fails on most cases. Our results demonstrate that YuelBond enables accurate and reliable bond reconstruction from imperfect molecular data, bridging a critical gap in generative drug discovery pipelines.