This is the authors' abstract. We don't add key points for this paper.
Specific and effective treatment of solid tumors has long been a challenge in cancer therapy. Antibody–drug conjugates (ADCs) represent a crucial advancement in precision oncology, with expanding applications and growing attention year by year. Traditional ADCs rely on monoclonal antibodies generated through animal immunization, followed by screening, sequencing, and recombinant expression—a process that is experimentally complex, time-consuming, and costly. In this study, we employed deep learning-based computational design methods to de novo design target-binding proteins specific for the tumor-associated antigen NECTIN-4. The designed NECTIN-4 mini-protein binder exhibited great specificity and thermal stability. The binding affinity was optimized from 0.262 μmol/L to 8.74 nmol/L through partial diffusion. Based on this, we further engineered the mini-protein binder by conjugating it with microtubule inhibitor VcMMAE to produce mini-protein drug conjugates (MPDCs) capable of targeted killing of NECTIN-4-positive tumor cells. We conducted a detailed evaluation of the anti-cancer activity of these MPDCs using cancer cells, organoids, and mouse xenograft models. Treatment experiments in xenograft models demonstrated that MPDCs exhibited good biological safety, with tumor growth being completely inhibited at an injection dose of 5 mg/kg. These designed MPDCs offer a new approach for preparing protein–drug conjugates for the precision treatment of solid tumors.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: