Abstract A026: GenAI and Physics Assisted Methods for the Design and Development of USP1 Inhibitors

Abstract GenAI enables the exploration of vast chemical spaces that would be impractical through traditional methods. Its ability to learn from complex datasets and generate novel compound structures makes it a game-changer in early-stage drug discovery. Generative Artificial Intelligence (GenAI) is transforming drug discovery, USP1 (ubiquitin-specific protease 1) plays a key role in DNA damage repair, making it an attractive target for cancer therapies. At VeGen, AI-driven platforms have been instrumental in designing next-generation USP1 inhibitors. By leveraging generative and predictive models, we accelerate the discovery process—rapidly designing and optimizing molecules with high potency, selectivity, and drug-like properties. An early promising hit with strong chemical diversity has been identified, demonstrating potent USP1 inhibition and favorable selectivity. To further refine selectivity, AlphaFold-based structural modelling has been integrated into the workflow, allowing detailed predictions of target-ligand interactions and off-target risk assessment alongside AI-driven design. This effort employs a closed-loop system—Bridging Computational Predictions with Experimental Validation—which not only streamlines the workflow but also minimizes experimental risk by prioritizing the most promising candidates. These innovations underscore the power of AI to reduce development timelines, lower costs, and enhance therapeutic potential, particularly in overcoming resistance to PARP inhibitors—a significant challenge in cancer treatment. Citation Format: Appaji Baburao. Mandhare, Prashant Bhavar, Uday Surampudi, Rupesh Chikale. GenAI and Physics Assisted Methods for the Design and Development of USP1 Inhibitors [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Artificial Intelligence and Machine Learning; 2025 Jul 10-12; Montreal, QC, Canada. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(13_Suppl):Abstract nr A026.