Abstract 2917: Utilizing artificial intelligence for the discovery of a novel CNS-penetrating ATR inhibitor

Abstract Introduction: Ataxia telangiectasia and Rad3-related protein serine/threonine kinase (ATR) plays a crucial role in regulating DNA damage repair. ATR inhibitors have shown promise against solid tumors, not only as monotherapies, but also in combination with chemotherapy, radiotherapy, and immunotherapy with several clinical trials ongoing. The ATR inhibitors currently in clinical development have low CNS-penetration and are therefore sub-optimal for the treatment of brain tumors and brain metastases. It has been proposed that ATR inhibitors could be used as a monotherapy or could be used to potentiate the cytotoxicity of radiotherapy, one of the mainstay treatments for brain tumors. Development of novel, potent, CNS-penetrating ATR inhibitors could provide a new treatment alternative for patients with few options. Traditional drug discovery methods are time-consuming and costly, necessitating innovative approaches. Here, we describe the application of the Enki™ platform, an artificial intelligence approach, in the discovery of a novel ATR inhibitor for use against brain tumors. Methods: The Enki™ platform utilizes generative AI and deep machine learning to search a broad chemical space to identify hits. It uses variational autoencoders to optimize many properties simultaneously within the search space, including maximal potency against the primary target, selectivity, ADMET, and physicochemical properties. This platform was used to generate de novo molecules with optimized properties to penetrate the blood-brain barrier and specifically target ATR. Results: We will present preliminary results from the de novo molecule generation by the Enki™ platform. Validation of in vitro data, including ATR inhibition and selectivity, BBB permeability and metabolic stability, will be described. Conclusion: The Enki™ platform is being leveraged for the development of a CNS-penetrant ATR inhibitor, significantly accelerating the drug discovery and development process. Use of this system enables a broader exploration of the vast chemical space and refinement of drug properties, both shortening the drug development process and increasing specificity and efficacy of potential therapeutics. Citation Format: Sarah Truong, Beibei Zhai, Louise Ramos, Mona Marzban, Fariba Ghaidi, Peter Guzzo, Mehran Khodabandeh, Ahmad Issa, Seyed A. Saberali, Jason Rolfe, Sarah Omar, Marshall Drew-Brook, John Langlands, Dennis Brown, Jeffrey Bacha, Mads Daugaard. Utilizing artificial intelligence for the discovery of a novel CNS-penetrating ATR inhibitor [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 2917.