Abstract
Investigating peptides and antibodies targeting DPP-4 in vitro experiments requires the presence of the native lipid bilayer, as catalytic activity depends on it. We propose a methodology that involves molecular docking, 100-ns molecular dynamics simulations of DPP-4 in a POPC lipid bilayer mimicking nanodisc conditions, a novel dual-channel BiLSTM deep learning model for predicting DPP-4 inhibitor peptides, CDR affinity maturation based on Rosetta, and optimizing the structure of DPP-4 antibodies. For predicting peptides, we developed a novel dual-channel model based on the ESM-2 protein language model and docking data with expected R2 and Spearman correlations of 0.80-0.85 and 0.70-0.80, respectively, based on the same peptide data used in the experiment within the nanodisc system. In optimizing the structure of DPP-4 antibodies, we use IgFold for predicting the structure of DPP-4 antibodies, ClusPro/HADDOCK for mapping binding sites, and virtual saturation mutagenesis for the optimization of CDRs, resulting in a 2-5 times increased binding affinity. A bispecific DPP-4 inhibitor antibody with GLP-1R agonist activity is designed following the principle of knob-into-hole and using AlphaFold-Multimer.
References
[1] Holst JJ, Rosenkilde MM. GIP as a therapeutic target in diabetes and obesity: insight from incretin co-agonists. J Clin Endocrinol Metab. 2020;105(8):e2710-e2716.
[2] Pettersen JM, Yang Y, Robinson AS. Advances in nanodisc platforms for membrane protein purification. Trends Biotechnol. 2023;41(8):1041-1054.
[3] Eberhardt J, Santos-Martins D, Tillack AF, et al. AutoDock Vina 1.2.0: new docking methods, expanded force field, and python bindings. J Chem Inf Model. 2021;61(8):3891-3898.
[4] Páll S, Zhmurov A, Bauer P, et al. Heterogeneous parallelization and acceleration of molecular dynamics simulations in GROMACS. J Chem Phys. 2020;153(13).
[5] Lin Z, Akin H, Rao R, et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science. 2023; 379(6637):1123-1130.
[6] Boorla VS, Chowdhury R, Ramasubramanian R, et al. De novo design and Rosetta-based assessment of high-affinity antibody variable regions (Fv) against the SARS-CoV-2 spike receptor binding domain (RBD). Proteins. 2023;91(2):196-208.
[7] Jumper J, Evans R, Pritzel A, et al. Highly accurate protein structure prediction with AlphaFold. Nature. 2021;596(7873):583-589.
[8] Zhang Y, Zhu Y, Bao X, et al. Mining bovine milk proteins for DPP-4 inhibitory peptides using machine learning and virtual proteolysis. Research. 2024;7:0391.
[9] Wang D, Jin J, Li Z, et al. StructuralDPPIV: a novel deep learning model based on atom structure for predicting dipeptidyl peptidase-IV inhibitory peptides. Bioinformatics. 2024;40(2):btae057.
[10] Zhang M, Zhu L, Wu G, et al. Food-derived dipeptidyl peptidase IV inhibitory peptides: production, identification, structure-activity relationship, and their potential role in glycemic regulation. Crit Rev Food Sci Nutr. 2024;64(8):2053-2075.
[11] Ruffolo JA, Chu LS, Mahajan SP, et al. Fast, accurate antibody structure prediction from deep learning on massive set of natural antibodies. Nat Commun. 2023;14(1):2389.
[12] Vajda S, Yueh C, Beglov D, et al. New additions to the ClusPro server motivated by CAPRI. Proteins. 2017;85(3):435-444.
[13] Evans R, O'Neill M, Pritzel A, et al. Protein complex prediction with AlphaFold-Multimer. bioRxiv. 2021.
doi:10.1101/2021.10.04.463034
How to cite this paper
Computational Intelligence-driven DPP-4 Inhibitory Peptide Prediction and Bispecific Antibody Design: Integrating Deep Learning, Molecular Dynamics, and Nanodisc Validation
How to cite this paper: Taozhi Wang. (2026) Computational Intelligence-driven DPP-4 Inhibitory Peptide Prediction and Bispecific Antibody Design: Integrating Deep Learning, Molecular Dynamics, and Nanodisc Validation. Advance in Biological Research, 7(1), 54-58.
DOI: http://dx.doi.org/10.26855/abr.2026.06.006