Abstract The development of personalized cancer immunotherapies is critically hampered by the inability to rapidly interpret the functional consequences of genetic variants, particularly non-coding variants and variants of uncertain significance (VUS). This interpretation bottleneck creates significant delays in designing effective, patient-specific treatments. To address this catastrophic failure, we have developed an agentic platform that automates the end-to-end in silico workflow from variant discovery to therapeutic design and validation. Our platform, CrisPRO.ai integrates a powerful intelligence engine and a generative therapeutic forge, orchestrated by a central command agent. The intelligence engine leverages a state-of-the-art biological foundation model (Evo2) to provide zero-shot, quantitative predictions of variant pathogenicity across the entire genome. This allows for the rapid annihilation of VUS in critical immune-regulating genes and pathways, such as JAK/STAT and PD-L1, by providing a definitive functional score. Furthermore, the engine can perform in silico gene knockouts to identify novel synthetic lethal targets in the tumor microenvironment. The intelligence gathered is then passed to the therapeutic forge, which is commanded to generate novel biologics. Leveraging the model's generative capabilities, the forge can design high-efficacy CRISPR guide RNAs for gene knockout or correction, and even design custom regulatory elements like promoters and enhancers to ensure precise, context-specific expression of therapeutic payloads. Crucially, CrisPRO.ai closes the loop by performing fully computational therapeutic validation. After a pathogenic variant is identified and a corrective therapeutic is designed, the resulting "repaired" sequence is fed back into the intelligence engine. By comparing the pathogenicity scores before and after the intervention, we conduct a complete in silico trial, generating high-tier evidence of therapeutic efficacy. This agentic, closed-loop system represents a paradigm shift, collapsing the timeline for designing and validating personalized cancer immunotherapies from years to hours. Citation Format: Fahad Kiani, Rahima Nayeem. An agentic platform for designing cancer immunotherapies: From automated variant interpretation to in silico therapeutic validation abstract. In: Proceedings of the AACR Special Conference in Cancer Research: Mechanisms of Cancer Immunity and Cancer-related Autoimmunity; 2025 Sep 24-27; Montreal, QC, Canada. Philadelphia (PA): AACR; Cancer Immunol Res 2025;13(9 Suppl):Abstract nr B025.
Kiani et al. (Wed,) studied this question.