Autonomous biomedical research with an artificial intelligence agent
Science · 20.08.2026 · 393 (6813)
DOI: 10.1126/science.adz4351 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science, erschienen am 20.08.2026. Verfasst von Kexin Huang und 27 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Stanford University School of Engineering, Stanford, CA, USA. Hauptthemen laut MEDLINE: Artificial Intelligence, Biomedical Research, Software. Die Arbeit wurde bisher 65-mal zitiert (Crossref) und nennt 196 Literaturangaben. Gefördert von: National Science Foundation, National Institutes of Health, Genentech.
Abstract (Originalsprache)
Biomedical research is increasingly constrained by repetitive, fragmented workflows that slow discovery. We introduce Biomni, a general-purpose biomedical artificial intelligence agent that autonomously executes diverse research tasks. To map the biomedical action space, Biomni’s action-discovery agent mines tools, databases, and protocols from thousands of publications across 25 domains, building a unified agentic environment. Its general-purpose architecture integrates large language model reasoning with retrieval-augmented planning and code-based execution, dynamically composing workflows without predefined templates. Systematic benchmarking shows strong generalization across heterogeneous tasks—causal gene prioritization, drug repurposing, rare-disease diagnosis, microbiome analysis, and molecular cloning—without task-specific tuning. Real-world case studies demonstrate Biomni interpreting multimodal datasets, optimizing protein stability, orchestrating wet-lab instruments, and generating experimentally testable protocols. Biomni envisions artificial intelligence augmenting human scientists and accelerating discovery.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer Science, Stanford University School of Engineering, Stanford, CA, USA.
- Phylo, Inc., South San Francisco, CA, USA.
- Research and Early Development, Genentech, South San Francisco, CA, USA.
- Department of Pathology, Stanford University School of Medicine, Stanford, CA, USA.
- Cancer Biology Program, Stanford University School of Medicine, Stanford, CA, USA.
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA.
ORCID-Profile: Kexin Huang, Serena Zhang, Hanchen Wang, Yuanhao Qu, Yingzhou Lu, Ryan Li, Yusuf Roohani, Shiyi Cao, Gavin Li, Junze Zhang, Di Yin, Sherry Liu, Tianwei She, Shruti Marwaha, Xin Zhou, Matthew T Wheeler, Jonathan A Bernstein, Peng He, Jingtian Zhou, Michael P Snyder, Le Cong, Jure Leskovec
Förderung
- National Science Foundation
- National Institutes of Health
- Genentech
- GlaxoSmithKline
- SAP America
- Stanford Bio-X
- Stanford Data Applications Initiative
- Wu Tsai Neurosciences Institute, Stanford University
Zitieren
APA
Huang, K., Zhang, S., Wang, H., Qu, Y., Lu, Y., Li, R., Roohani, Y., Qiu, L., Cao, S., Li, G., Zhang, J., Yin, D., Wierenga, R., Kavi, D., Liu, S., She, T., Marwaha, S., Carter, J. N., Zhou, X., …, & Leskovec, J. (2026). Autonomous biomedical research with an artificial intelligence agent. Science, 393(6813). https://doi.org/10.1126/science.adz4351
Vancouver
Huang K, Zhang S, Wang H, Qu Y, Lu Y, Li R, et al. Autonomous biomedical research with an artificial intelligence agent. Science. 2026;393(6813). doi:10.1126/science.adz4351
BibTeX
@article{Huang2026,
author = {Huang, Kexin and Zhang, Serena and Wang, Hanchen and Qu, Yuanhao and Lu, Yingzhou and Li, Ryan and Roohani, Yusuf and Qiu, Lin and Cao, Shiyi and Li, Gavin and Zhang, Junze and Yin, Di and Wierenga, Rick and Kavi, Deniz and Liu, Sherry and She, Tianwei and Marwaha, Shruti and Carter, Jennefer N and Zhou, Xin and Wheeler, Matthew T and Bernstein, Jonathan A and Wang, Mengdi and He, Peng and Zhou, Jingtian and Snyder, Michael P and Cong, Le and Regev, Aviv and Leskovec, Jure},
title = {Autonomous biomedical research with an artificial intelligence agent},
journal = {Science},
year = {2026},
volume = {393},
number = {6813},
doi = {10.1126/science.adz4351}
}
EUVIMED