CRISPR-GPT for agentic automation of gene-editing experiments

Yuanhao Qu^#¹, Kaixuan Huang^#², Ming Yin², Kanghong Zhan³, Dyllan Liu⁴, Di Yin¹, Henry C Cousins^{5

6}, William A Johnson¹, Xiaotong Wang¹, Mihir Shah⁵, Russ B Altman^{4

7}, Denny Zhou⁸, Mengdi Wang⁹, Le Cong¹⁰

Affiliations

¹ Department of Pathology, Department of Genetics, Cancer Biology Program, Stanford University School of Medicine, Stanford, CA, USA.
² Center for Statistics and Machine Learning, Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA.
³ Department of Computing, Data Science, and Society, University of California, Berkeley, Berkeley, CA, USA.
⁴ Department of Computer Science, University of California, Berkeley, Berkeley, CA, USA.
⁵ Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA.
⁶ Medical Scientist Training Program, Stanford University School of Medicine, Stanford, CA, USA.
⁷ Department of Bioengineering, Department of Genetics, Stanford University, Stanford, CA, USA.
⁸ Google DeepMind, Mountain View, CA, USA.
⁹ Center for Statistics and Machine Learning, Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA. mengdiw@princeton.edu.
¹⁰ Department of Pathology, Department of Genetics, Cancer Biology Program, Stanford University School of Medicine, Stanford, CA, USA. congle@stanford.edu.

^# Contributed equally.

PMID: 40738974
DOI: 10.1038/s41551-025-01463-z

CRISPR-GPT for agentic automation of gene-editing experiments

Yuanhao Qu et al. Nat Biomed Eng. 2025.

. 2025 Jul 30.

doi: 10.1038/s41551-025-01463-z. Online ahead of print.

Authors

Affiliations

¹ Department of Pathology, Department of Genetics, Cancer Biology Program, Stanford University School of Medicine, Stanford, CA, USA.
² Center for Statistics and Machine Learning, Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA.
³ Department of Computing, Data Science, and Society, University of California, Berkeley, Berkeley, CA, USA.
⁴ Department of Computer Science, University of California, Berkeley, Berkeley, CA, USA.
⁵ Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA.
⁶ Medical Scientist Training Program, Stanford University School of Medicine, Stanford, CA, USA.
⁷ Department of Bioengineering, Department of Genetics, Stanford University, Stanford, CA, USA.
⁸ Google DeepMind, Mountain View, CA, USA.
⁹ Center for Statistics and Machine Learning, Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA. mengdiw@princeton.edu.
¹⁰ Department of Pathology, Department of Genetics, Cancer Biology Program, Stanford University School of Medicine, Stanford, CA, USA. congle@stanford.edu.

^# Contributed equally.

PMID: 40738974
DOI: 10.1038/s41551-025-01463-z

Abstract

Performing effective gene-editing experiments requires a deep understanding of both the CRISPR technology and the biological system involved. Meanwhile, despite their versatility and promise, large language models (LLMs) often lack domain-specific knowledge and struggle to accurately solve biological design problems. We present CRISPR-GPT, an LLM agent system to automate and enhance CRISPR-based gene-editing design and data analysis. CRISPR-GPT leverages the reasoning capabilities of LLMs for complex task decomposition, decision-making and interactive human-artificial intelligence (AI) collaboration. This system incorporates domain expertise, retrieval techniques, external tools and a specialized LLM fine tuned with open-forum discussions among scientists. CRISPR-GPT assists users in selecting CRISPR systems, experiment planning, designing guide RNAs, choosing delivery methods, drafting protocols, designing assays and analysing data. We showcase the potential of CRISPR-GPT by knocking out four genes with CRISPR-Cas12a in a human lung adenocarcinoma cell line and epigenetically activating two genes using CRISPR-dCas9 in a human melanoma cell line. CRISPR-GPT enables fully AI-guided gene-editing experiment design and analysis across different modalities, validating its effectiveness as an AI co-pilot in genome engineering.

PubMed Disclaimer

Conflict of interest statement

Competing interests: Princeton University and Stanford University have filed patent applications (#19/093,928, Princeton and Stanford, 2025) based on this work, where L.C., M.W., Y.Q. and K.H. are listed as inventors. L.C. is a member of the scientific advisory board of Arbor Biotechnologies. L.C. has equity interest in Auto Bio, Rootpath Genomics, and Acrobat Genomics. D.Z. is an employee of Google DeepMind. The remaining authors declare no competing interests.

Update of

CRISPR-GPT for Agentic Automation of Gene Editing Experiments.
Qu Y, Huang K, Yin M, Zhan K, Liu D, Yin D, Cousins HC, Johnson WA, Wang X, Shah M, Altman RB, Zhou D, Wang M, Cong L. Qu Y, et al. bioRxiv [Preprint]. 2025 Jul 26:2024.04.25.591003. doi: 10.1101/2024.04.25.591003. bioRxiv. 2025. Update in: Nat Biomed Eng. 2025 Jul 30. doi: 10.1038/s41551-025-01463-z. PMID: 39463961 Free PMC article. Updated. Preprint.

References

1. Chowdhery, A. et al. PaLM: scaling language modeling with pathways. J. Mach. Learn. Res. 24, 240 (2023).
1. Hoffmann, J. et al. An empirical analysis of compute-optimal large language model training. In Advances in Neural Information Processing Systems (eds Koyejo, S. et al.) Vol. 35, 30016–30030 (Curran Associates, Inc., 2022).
1. OpenAI et al. GPT-4 technical report. Preprint at https://doi.org/10.48550/arXiv.2303.08774 (2024).
1. The Claude 3 Model Family: Opus, Sonnet, Haiku (Anthropic, 2024).
1. Anil, R. et al. PaLM 2 technical report. Preprint at https://doi.org/10.48550/arXiv.2305.10403 (2023).

Grants and funding

LinkOut - more resources

Full Text Sources
- Nature Publishing Group

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

CRISPR-GPT for agentic automation of gene-editing experiments

Affiliations

CRISPR-GPT for agentic automation of gene-editing experiments

Authors

Affiliations

Abstract

Conflict of interest statement

Update of

References

Grants and funding

LinkOut - more resources

Full Text Sources