{"title":"Cyclic peptide membrane permeability prediction using deep learning model based on molecular attention transformer.","authors":"Dawei Jiang, Zixi Chen, Hongli Du","doi":"10.3389/fbinf.2025.1566174","DOIUrl":null,"url":null,"abstract":"<p><p>Membrane permeability is a critical bottleneck in the development of cyclic peptide drugs. Experimental membrane permeability testing is costly, and precise <i>in silico</i> 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 (<i>R</i> <sup><i>2</i></sup> ) of 0.67 for PAMPA permeability prediction, and <i>R</i> <sup><i>2</i></sup> 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.</p>","PeriodicalId":73066,"journal":{"name":"Frontiers in bioinformatics","volume":"5 ","pages":"1566174"},"PeriodicalIF":2.8000,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11933047/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in bioinformatics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/fbinf.2025.1566174","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"MATHEMATICAL & COMPUTATIONAL BIOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
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.