Harnessing deep learning to accelerate the development of antibodies and aptamers

Pan Tan, Song Li, Jin Huang, Ziyi Zhou, Liang Hong,
Harnessing deep learning to accelerate the development of antibodies and aptamers,
Acta Pharmaceutica Sinica B,
2025,
,
ISSN 2211-3835,
https://doi.org/10.1016/j.apsb.2025.12.017.
(https://www.sciencedirect.com/science/article/pii/S2211383525008251)
Abstract: Artificial intelligence (AI) has revolutionized the design of antibodies and RNA aptamers, driving significant advancements in molecular therapeutics. In antibody design, AI enables accurate structure prediction and optimization of binding affinity, specificity, and stability, thereby accelerating the development of therapies targeting challenging antigens, such as those associated with viral infections and cancer. By integrating sequence and structural data, AI significantly reduces experimental costs and development timelines, streamlining the creation of next-generation antibody-based therapeutics. Similarly, AI has transformed RNA aptamer design, addressing long-standing challenges in structure prediction and binding optimization. AI-driven approaches allow for the rapid generation of aptamers with enhanced specificity, stability, and functional properties, expanding their potential applications in both therapeutics and diagnostics. These advancements offer scalable, cost-effective, and highly customizable solutions for precision medicine. As AI systems continue to evolve and integrate with experimental validation, they hold immense promise for developing more effective treatments for complex diseases, including cancer, autoimmune disorders, and viral infections. This marks the beginning of a new era in therapeutic innovation, where AI plays a pivotal role in addressing the challenges of modern medicine.
Keywords: Antibody; RNA aptamer; Deep learning; Antibody structure prediction; RNA structure prediction; Protein language models; Protein engineering; De novo design