By Milliam Murigi
International researchers have developed an artificial intelligence (AI) system dubbed CRISPR-GPT, designed to automate and enhance CRISPR-based gene-editing experiments.
Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR) is a gene-editing technology that allows scientists to make precise changes to DNA in living organisms.
The team decided to develop CRISPR-GPT because performing effective gene-editing experiments requires a deep understanding of both CRISPR technology and the biological system involved.
CRISPR has become one of the most commonly used lab techniques. The technology has been used to produce the first permanent cure for sickle cell disease and β-thalassemia. It is also being used to engineer plants for more sustainable agriculture.
This technology is accompanied by numerous software tools and protocols designed for specific gene-editing tasks. However, a complete end-to-end solution from choosing the CRISPR-Cas system and designing guide RNAs to evaluating off-target effects, planning delivery, and analyzing data remains complex, especially for newcomers.
“This is why we introduce CRISPR-GPT, a solution that combines the strengths of large language models (LLMs) with domain-specific knowledge, chain-of-thought reasoning, instruction fine-tuning, retrieval techniques and tools,” the study, published in Nature Biomedical Engineering, states.
According to the team that includes experts from Stanford University School of Medicine, Princeton University, the University of California, Berkeley, and Google DeepMind, CRISPR-GPT is centred around LLM-powered planning and execution agents. This system leverages the reasoning abilities of general-purpose LLMs and multi-agent collaboration for task decomposition, constructing state machines and automated decision-making.
It draws upon expert knowledge from leading practitioners and peer-reviewed published literature in gene editing for retrieval-augmented generation (RAG). It assists users in selecting CRISPR systems, experiment planning, designing guide RNAs, choosing delivery methods, drafting protocols, designing assays and analyzing data.
“CRISPR-GPT is designed to assist researchers at every stage of gene-editing experiments. From experiment planning, designing guide RNAs, choosing delivery methods, drafting protocols, designing assays to analysing data,” the study states.
It offers tunable levels of automation via three modes: Meta, Auto and Q&A. The ‘Meta mode’ is designed for beginner researchers, guiding them through a sequence of essential tasks from selection of CRISPR systems, delivery methods, to designing gRNA, assessing off-target efficiency, generating experiment protocols and data analysis. Throughout this decision-making process, CRISPR-GPT interacts with users at every step, provides instructions and seeks clarifications when needed.
The ‘Auto mode’ caters to advanced researchers and does not adhere to a predefined task order. Users submit a freestyle request, and the LLM Planner decomposes this into tasks, manages their interdependence, builds a customized workflow and executes them automatically. It fills in missing information on the basis of the initial inputs and explains its decisions and thought process, allowing users to monitor and adjust the process. The ‘Q&A mode’ supports users with on-demand scientific inquiries about gene editing.
Initial demonstrations show that CRISPR-GPT successfully knocked 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, validating its effectiveness as an AI co-pilot in genome engineering.
“All these wet-lab experiments were carried out by junior researchers not familiar with gene editing. They both succeeded on the first attempt, confirmed by not only editing efficiencies, but also biologically relevant phenotypes and protein-level validation, highlighting the potential of LLM-guided biological research.”
The developers stress that safeguards have been built into the system to prevent misuse, ensuring the technology supports responsible scientific progress.
“AI-assisted tools can simplify gene-editing experiment design and data analysis, making the technology more accessible and accelerating scientific and therapeutic discoveries,” reads part of the study findings.
