Cyclic Peptide Membrane Permeability Prediction Using Deep Learning Model Based on Molecular Attention Transformer

Dawei Jiang ¹ Zixi Chen ^2,3 Hongli Du ^1*

• ¹ South China University of Technology, Guangzhou, China
• ² Shenzhen Longhua District Central Hospital, Shenzhen, China
• ³ Anhui University of Science and Technology, Huainan, Anhui, China

Membrane permeability is a critical bottleneck in the development of cyclic peptide drugs. Experimental membrane permeability testing is costly, and precise in silico prediction tools are scarce. In this study, we developed CPMP (https://github.com/panda1103/CPMP), a cyclic peptide membrane permeability prediction model based on the Molecular Attention Transformer (MAT) frame. The model demonstrated robust predictive performance, achieving determination coefficients (R² ) of 0.67 for PAMPA permeability prediction, and R² values of 0.75, 0.62, and 0.73 for Caco-2, RRCK, and MDCK cell permeability predictions, respectively. Its performance outperforms traditional machine learning methods and graph-based neural network models. In ablation experiments, we validated the effectiveness of each component in the MAT architecture. Additionally, we analyzed the impact of data pre-training and cyclic peptide conformation optimization on model performance.