Poster
in
Workshop: 2nd Generative AI for Biology Workshop
From Fragments to Geometry: A Unified Graph Transformer for Molecular Representation from Conformer Ensembles
Duy Nguyen · Trung Nguyen · Ha Le · Mai Thanh Nhat Truong · TrungTin Nguyen · Nhat Ho · Khoa Doan · Duy Duong-Tran · Li Shen · Daniel Sonntag · James Zou · Mathias Niepert · Hyojin Kim · Jonathan Allen
Keywords: [ graph transformer ] [ molecule representation learning ] [ small molecule design ] [ fragment molecule ] [ optimal transport ]
Designing and understanding molecules for biological applications requires models that can integrate rich structural information from both 2D molecular graphs and diverse 3D conformer ensembles. We introduce a fragment-aware, structure-guided graph transformer that enables scalable and expressive molecular modeling by aggregating multiple 3D conformers while incorporating fragment-level inductive biases from the 2D topology. Our approach employs a trainable attention-based fusion mechanism within a graph transformer to dynamically combine 2D and 3D representations, moving beyond static solvers and rigid fusion heuristics. This architecture enables fine-grained reasoning over chemically diverse molecules, including organocatalysts and transition-metal complexes. While originally developed for molecular property prediction, the method’s structure-aware and fragment-level modeling is readily applicable to generative molecular design, enabling downstream applications in drug discovery, reaction modeling, and AI-driven biological research. The model scales to large datasets and achieves state-of-the-art results across molecular property benchmarks, demonstrating its potential as a foundational component for generative AI in molecular science.