bioRxiv
Virtual-cell verification enables self-auditing AI discovery for immune rejuvenation
Preprint: experiments in human cellsAI & data
434 elderly donors, independent replication
Abstract
Artificial-intelligence agents propose drug-discovery hypotheses faster than experiments can test them, yet their conclusions are rarely verified, against the underlying biology, the predicted perturbation, or the agent's own scoring logic. We close this verification gap with an agentic framework built on three verifiers.
The paper
Walter and Eliza Hall Institute of Medical Research; Guangzhou Laboratory
bioRxiv, 11 Aug 2026, CC BY, Preprint, not peer-reviewed
