Bio AI Agent: A Multi-Agent Artificial Intelligence System for Autonomous CAR-T Cell Therapy Development with Integrated Target Discovery, Toxicity Prediction, and Rational Molecular Design

TL;DR

CAR-T development is hampered by long timelines and high attrition due to gaps in target validation, safety prediction, and molecular optimization. The authors propose Bio AI Agent, a six-agent multi-agent AI system that coordinates target discovery, toxicity prediction, molecular design, patent intelligence, clinical translation, and decision orchestration. Retrospective validation shows autonomous identification of high-risk targets such as FcRH5 hepatotoxicity and CD229 off-tumor risk, plus patent risk assessment and strategic roadmapping. By integrating diverse data sources and enabling parallel, domain-specific reasoning, the approach accelerates early-stage decision making and provides holistic regulatory and IP planning to speed translation of next-generation CAR-T therapies.

Abstract

Chimeric antigen receptor T-cell (CAR-T) therapy represents a paradigm shift in cancer treatment, yet development timelines of 8-12 years and clinical attrition rates exceeding 40-60% highlight critical inefficiencies in target selection, safety assessment, and molecular optimization. We present Bio AI Agent, a multi-agent artificial intelligence system powered by large language models that enables autonomous CAR-T development through collaborative specialized agents. The system comprises six autonomous agents: Target Selection Agent for multi-parametric antigen prioritization across >10,000 cancer-associated targets, Toxicity Prediction Agent for comprehensive safety profiling integrating tissue expression atlases and pharmacovigilance databases, Molecular Design Agent for rational CAR engineering, Patent Intelligence Agent for freedom-to-operate analysis, Clinical Translation Agent for regulatory compliance, and Decision Orchestration Agent for multi-agent coordination. Retrospective validation demonstrated autonomous identification of high-risk targets including FcRH5 (hepatotoxicity) and CD229 (off-tumor toxicity), patent infringement risks for CD38+SLAMF7 combinations, and generation of comprehensive development roadmaps. By enabling parallel processing, specialized reasoning, and autonomous decision-making superior to monolithic AI systems, Bio AI Agent addresses critical gaps in precision oncology development and has potential to accelerate translation of next-generation immunotherapies from discovery to clinic.