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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ni, Yi, Zhu, Liwei, Li, Shuai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908645285953536
author Ni, Yi
Zhu, Liwei
Li, Shuai
author_facet Ni, Yi
Zhu, Liwei
Li, Shuai
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08649
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle 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
Ni, Yi
Zhu, Liwei
Li, Shuai
Quantitative Methods
Artificial Intelligence
68T05, 92C50
I.2.11; I.2.6; J.3
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.
title 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
topic Quantitative Methods
Artificial Intelligence
68T05, 92C50
I.2.11; I.2.6; J.3
url https://arxiv.org/abs/2511.08649