Agent-Guided De Novo Design of Nanobody Binders Against a Novel Cancer Target

Yue Zhao, Melih Yilmaz, Edward Lee, Chuanyui Teh, Lan Guo, Kemal Sonmez, Luca Giancardo, Gordon Trang, Fangda Xu, Madelyn Espinosa-Cotton, Nai-Kong Cheung, Jiwon Kim, Nina Cheng

Keywords: antibody engineering, de novo antibody design, AI for biology, generative biology, agentic AI

TL;DR: We present an AI de novo antibody design pipeline against a new cancer target with experimentally validated nanobody binders.

Abstract: Therapeutic antibody discovery remains slow and resource-intensive, with traditional methods providing limited control over epitope selection. We present an agent-guided workflow for de novo nanobody design against a novel Desmoplastic Small Round Cell Tumor target, encompassing epitope identification via our hotspot recommendation agent, de novo generation using three independent methods (RFantibody, IgGM, mBER) across multiple predicted antigen structures, multi-metric scoring including structural and sequence-based binding affinity metrics, and high-throughput yeast surface display screening followed by surface plasmon resonance (SPR) characterization. From 288,000 designs spanning eight epitope regions and three VHH frameworks, Pareto-based filtering selected 100,000 candidates; of 116 enriched candidates advanced to SPR, 46 (39.7\%) produced reliable kinetic fits ($R_{\max}$ $\geq$ 30 RU) with $K_D$ values from 0.66 nM to 305 nM (median 31.7 nM). These results demonstrate that an agent-guided computational workflow can design nanomolar to sub-nanomolar nanobody binders against a novel target without experimental structure or prior antibody information.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 18