Application of AI in the Design of Novel Peptide-based Ingredients for Skincare Products
Abstract
This review provides a systematic review of the current applications and developmental trends of artificial intelligence (AI) in the design of novel peptide-based cosmetic ingredients. With rapid advancements in computational biology and artificial intelligence algorithms, the development paradigm for peptide-based skincare products is undergoing a revolutionary shift—from traditional trial-and-error screening to intelligent, precision-driven design. By leveraging machine learning algorithms, deep learning models, and molecular simulation techniques, artificial intelligence has significantly enhanced the efficiency and success rate of peptide ingredient development while reducing associated costs. The review highlights breakthroughs in artificial intelligence applications for peptide molecular design, stability optimization, transdermal delivery prediction, and efficacy evaluation. It also explores the integration of artificial intelligence with interdisciplinary fields such as synthetic biology and nanotechnology, and offers insights into current challenges and future development directions.
References
Zhai S, Liu T, Lin S, et al., 2025, Artificial Intelligence in Peptide-based Drug Design. Drug Discovery Today, 30(2): 104300. https://doi.org/10.1016/j.drudis.2025.104300
Dong Q, Wang S, Miao Y, et al., 2024, Novel Antimicrobial Peptides Against Cutibacterium Acnes Designed by Deep Learning. Scientific Reports, 14(1): 4529. https://doi.org/10.1038/s41598-024-55205-3
Zhou L, Yuan X, Hu Y, et al., 2024, Blockade of HMGB1 Reduces Inflammation and Pruritus in Atopic Dermatitis by Inhibiting Skin Fibroblasts Activation. International Archives of Allergy and Immunology, 185(2): 170–181. https://doi.org/10.1159/000534568
Yang X, He X, Bi Y, et al., 2025, Accelerating Anti-aging Cyclic Peptide Discovery through Computational Design and Automated Synthesis. Science China Chemistry. 2025: 1–12. https://doi.org/10.1007/S11426-025-2709-7
Gang D, Kim DW, Park HS, 2018, Cyclic Peptides: Promising Scaffolds for Biopharmaceuticals. Genes (Basel), 9(11): 557. https://doi.org/10.3390/genes9110557
Gupta S, Kapoor P, Chaudhary K, et al., 2013, In Silico Approach for Predicting Toxicity of Peptides and Proteins. PLoS One, 8(9): e73957. https://doi.org/10.1371/journal.pone.0073957
Schneider G, Fechner U, 2005, Computer-based de Novo Design of Drug-like Molecules. Nature Reviews Drug Discovery, 4(8): 649–663. https://doi.org/10.1038/nrd1799
