CycDelta: Multimodal Residue-Graph Learning of Permeability Changes in Cyclic Peptides
Jie Qian, Yu Zhou, Yaning Cui, Zhifeng Gao, Lingyun Wu, Sean Li, Maohua Yang, Dongdong Wang
CycDelta is a multimodal residue-graph model for predicting permeability changes in cyclic peptides by comparing within-source permeability differences, outperforming baselines on out-of-distribution and zero-shot tasks.
bioRxiv · Sep 24, 2026 · PreprintBioinformatics