ProtoMol: Enhancing Molecular Property Prediction via Prototype-Guided Multimodal Learning
* Equal contribution
Published in Briefings in Bioinformatics, 2025
We propose ProtoMol, a prototype-guided multimodal framework that hierarchically aligns molecular graphs and textual descriptions via layer-wise cross-modal attention and a shared prototype space, consistently outperforming prior methods on molecular property prediction while improving interpretability.
Authors: Yingxu Wang*, Kunyu Zhang*, Jiaxin Huang, Nan Yin, Siwei Liu, Eran Segal
* Equal contribution