Abstract 4772: AI-guided engineering and preclinical development of biparatopic anti-DLL3 antibody-drug conjugates (ADCs)

Abstract Delta-like ligand 3 (DLL3) is often overexpressed in small cell lung cancer (SCLC) and several other neuroendocrine tumors, with no or very low expression in normal issues. An anti-DLL3 x CD3 bispecific T-cell engager, tarlatamab, has demonstrated significant clinical benefits and was recently approved by the US FDA for the treatment of DLL3-expressing SCLC. On the other hand, Rova-T, the first antibody-drug conjugate (ADC) targeting DLL3 entered advanced clinical development, failed in phase III studies due to insufficient efficacy and an unfavorable safety profile. In this study, via AI-guided engineering and optimization, we produced a novel biparatopic anti-DLL3 antibody and generated a number of ADCs utilizing various linkers and cytotoxic payloads. The ADCs demonstrated efficient DLL3-mediated cell binding and rapid internalization at a much higher efficiency than the mono-epitope targeting ADCs. The ADCs showed selective cytotoxicity towards multiple tumor cell lines with varying levels of DLL3 expression in vitro, and potently inhibited the growth of several DLL3-expressing tumor xenografts in animal models. Taken together, our findings underscore the significance of AI-guided antibody engineering and optimization, and provide support for the further development of the biparatopic anti-DLL3 ADCs in patients with DLL3-expressing tumors such as SCLC and other neuroendocrine tumors. Citation Format: Chuan Chen, Yue Wu, Liang Tian, Chenpeng Su, Zhaohui Chen, Jiyuan Tian, Dandan Liu, Yang He, Xiaoqian chen, Yongxin Shang, Jian Peng, Zhenping Zhu. AI-guided engineering and preclinical development of biparatopic anti-DLL3 antibody-drug conjugates (ADCs) [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 4772.