Skip to main content Skip to main navigation

Publikation

FACET: A Fragment-Aware Conformer Ensemble Transformer

Ho Minh Duy Nguyen; Trung Nguyen; Ha Thi Hong Le; Mai Thanh Nhat Truong; TrungTin Nguyen; Nhat Ho; Khoa D Doan; Duy Duong-Tran; Li Shen; Daniel Sonntag; James Zou; Mathias Niepert; Hyojin Kim; Jonathan E Allen
In: Proceedings of ICLR 2026. International Conference on Learning Representations (ICLR-2026), ICLR, 2026.

Zusammenfassung

Accurately predicting molecular properties requires effective integration of structural information from both 2D molecular graphs and their corresponding equilibrium conformer ensembles. In this work, we propose FACET, a scalable Structure- Aware Graph Transformer that efficiently aggregates features from multiple 3D conformers while incorporating fragment-level information from 2D graphs. Unlike prior methods that rely on static geometric solvers or rigid fusion strategies, our approach utilizes a differentiable graph transformer to theoretically approximate the computationally expensive Fused Gromov-Wasserstein (FGW), enabling dynamic and scalable fusion of 2D and 3D structural information. We further enhance this mechanism by injecting fragment-specific structural priors into the attention layers, enabling the model to capture fine-grained molecular details. This unified design scales to large datasets, handling up to 75,000 molecules and hundreds of thousands of conformers, and provides over a 6x speedup compared to geometry-aware FGW-based baselines. Our method also achieves state-of-the-art results in molecular property prediction, Boltzmann-weighted ensemble modeling, and reaction-level tasks, and is particularly effective on chemically diverse compounds, including organocatalysts and transition-metal complexes.