Abstract
BACKGROUND: Protein biologics are indispensable in disease prevention, diagnosis, and therapy, yet their development remains largely constrained by reliance on native protein scaffolds, resulting in long development timelines, limited structural and functional tunability, challenges in manufacturing consistency, and high production costs. MAIN BODY: De novo protein design moves beyond the structural and functional constraints inherent to traditional approaches, enabling the direct creation of proteins with tailored structures and functions and offering a new avenue to address these challenges. In this review, we summarize the principal computational strategies underlying de novo protein design and the contribution of deep learning to its recent progress, and highlight prospective applications, major translational barriers, and the current limitations and future challenges of the field. CONCLUSIONS: Despite notable methodological progress in de novo protein design, its path toward clinical application continues to be limited by a range of biological, technical, and translational considerations. Future work will need closer coordination between computational design, experimental validation, engineering optimization, and clinical needs, with clinical feasibility considered early and refined throughout development.