Jul 2026
PeptideSGCL: Structure-Enhanced Graph-Transformer Encoding and Dual-Level Contrastive Learning for Peptide Property Prediction.
A multimodal dual-contrastive learning framework for peptide property prediction is proposed, which improves both the structural encoder and the contrastive learning strategy to enhance the quality of joint sequence-structure representations.
Jiajie Cai, Shuwen Xiong, Yuntao Yang et al.
· ACS Synthetic Biology · 0 citations