Tevogen.AI announced a 20‑fold improvement in the robustness of its PredicTcell™ model, the core engine that predicts immunologically active peptides for drug discovery. The updated model is now trained on 1.8 million data points and is supported by three production AI agents that enable continuous learning between predictions and biological validation.
The upgrade expands Tevogen’s proprietary AI infrastructure and strengthens its ability to accelerate target identification for both virology and oncology programs. By improving predictive accuracy, the company aims to reduce the time and cost required to bring new therapies into clinical trials, addressing a key bottleneck in drug development.
"Our goal is to reduce trial‑and‑error in immunotherapy design and ultimately predict the proteome for any given combination of protein and HLA type. As our prediction quality improves, we believe we can meaningfully increase success rates while lowering development risk. That combination has the potential to create significant long‑term value," said Mittul Mehta, CIO and Head of Tevogen.AI.
Tevogen’s AI focus is supported by collaborations with Microsoft and Databricks, and the PredicTcell model is part of the broader ExacTcell platform that underpins the company’s virology, oncology, and neurology pipelines. The model’s enhanced performance positions Tevogen to pursue future partnerships and potentially generate new revenue streams while solidifying its competitive edge in the biotech AI space.
The advancement signals a strategic shift toward data‑driven drug discovery, reinforcing Tevogen’s commitment to leveraging AI to streamline the development of immunotherapies and other therapeutics.
The content on EveryTicker is for informational purposes only and should not be construed as financial or investment advice. We are not financial advisors. Consult with a qualified professional before making any investment decisions. Any actions you take based on information from this site are solely at your own risk.