Cross-attention and language models reveal the interpretability of functional predictions for the human olfactory receptor family
Yifeng Zhang, Zihuai Xu, Chenxi Gao, Suyang Duan, Gang Li, Chang Xu, Hui‐Meng Lu
This study introduces CrossVOI, a framework for VOC-OR interaction prediction using protein language models and cross-attention, showing improved performance and interpretability of attention mechanisms in human olfactory receptors.
bioRxiv · Aug 18, 2026 · PreprintBioinformatics