Experts Introduce CRISPR-GPT to Automate Gene Editing Experiments

Researchers from Stanford University School of Medicine, Princeton University, University of California, Berkeley, and Google DeepMind have developed CRISPR-GPT, an artificial intelligence (AI) system designed to automate and enhance CRISPR-based gene editing experiments. The findings of the study are published in Nature Biomedical Engineering.

CRISPR-GPT streamlines the process of selecting CRISPR systems, experiment planning, designing guide RNAs, choosing delivery methods, drafting protocols, designing assays, and analyzing data. This tool leverages the reasoning capabilities of large language models (LLMs), combined with domain expertise, retrieval techniques, and external tools. The platform also integrates safety features to prevent misuse of CRISPR-GPT.

Initial demonstrations show that CRISPR-GPT successfully knocked out four genes using CRISPR-Cas12a in a human lung adenocarcinoma cell line and activated two genes in a human melanoma cell line using CRISPR-dCas9. The scientists highlight CRISPR-GPT as a breakthrough toward AI-guided genome editing, with future applications in robotics and automated laboratory platforms.

For more information, read the study from Nature Biomedical Engineering.