Anthropic Says Claude Discovered a New Enzyme System Resembling CRISPR

Anthropic introduced a new life sciences research group and laboratory on September 23, 2026 and shared early results in which, the company said, its Claude model autonomously discovered a previously uncharacterized enzyme system whose structure resembles the DNA repeats behind CRISPR gene editing.

A New Life Sciences Research Group

Anthropic formed the research group in the spring of 2026 to test whether general AI models can systematize and accelerate biological discovery. The company said it believes that acceleration will come from a new way of doing biology research in which AI agents collaborate with humans at every step, and that developing this approach required building its own laboratory and a single team working on everything from training Claude in biology to running experiments.

The group’s focus is fundamental biology research using Claude: exploring datasets of DNA to identify uncharacterized protein families, generating hypotheses at scale, and testing those hypotheses through experiments in the lab. Its scientists specialize in computational approaches to reading DNA, interpreting its evolution, and picking out biological systems for further characterization. Before joining Anthropic, team members’ research contributed to understanding the evolution and regulation of CRISPR systems, discovering new enzymes for next-generation cell and gene therapies, and building tools to speed the identification of anomalies in DNA such as human pathogenic variants.

The announcement placed the result in a line of past discoveries that began with a scientist noticing something unusual in nature’s molecular machines: restriction enzymes found in bacterial immune systems, Taq polymerase identified in a bacterium in a Yellowstone hotspring and later used as the basis for PCR, and CRISPR itself, first noticed as an unusual repeat sequence in bacterial DNA.

How Claude Found ART

Anthropic gave Claude a prompt to search a massive database of DNA sequences for interesting new examples of reverse transcriptases, or RTs, enzymes that copy RNA into DNA. The company said its scientists’ involvement was limited to the initial prompt and the lab work, while Claude agents combed the database, investigated distinct RT families, and used their own judgment to identify candidates.

Anthropic reported that roughly 950 agents spent 21 hours searching the data and used 210 million tokens before one agent flagged a repeating pattern of DNA sequences occurring next to the gene for an odd-looking RT. Across the campaign, the agents gathered over 200,000 RTs, picked out 3,500 new candidate systems, and narrowed them to the 20 most compelling candidates, which they analyzed into human-readable reports. Anthropic said this type of analysis can take an expert scientist weeks to months.

While reading the raw DNA sequence near the RT, the agent logged: “The DNA next to the RT is spectacular: I can see by eye a tandem repeat array … that’s a CRISPR-like … repeat array?!” The agent then counted the repeats, measured their spacing, compared the layout with known RT systems, and searched the literature for any previous report of the pattern before filing a report for human review. After further analysis and testing in the company’s lab, Anthropic recognized that the pattern marked a previously uncharacterized enzyme system found mainly in bacteriophages, the viruses that infect bacteria, and named it array-associated reverse transcriptases, or ART.

Early Results and What Comes Next

ART consists of three parts: the RT, a partner gene beside it, and a long array of evenly spaced DNA repeat sequences. That layout resembles a CRISPR array, which holds a bank of different RNA sequences that make CRISPR-Cas systems programmable. The underlying RT, found in a jumbo phage, had been identified in previous studies, but Anthropic said Claude appears to be the first to notice the system’s defining features, an associated array of non-coding DNA sequences and an additional accessory protein of unknown function.

Anthropic said the system’s set of characteristics has only ever been found together in a handful of other systems, all of which are programmable and perform operations such as cutting, copying, and pasting DNA. The system’s function is not yet known. The company’s first experiments show the ART array is expressed as a set of distinct short RNAs, and further experiments are underway to determine how ART works. After reviewing the pre-print, Feng Zhang, a pioneer of CRISPR genome editing and a professor at MIT and the Broad Institute, called the work an exciting example of how AI agents can contribute to biological discovery and said the identification of RNA-repeat arrays associated with reverse transcriptases merits further investigation.

The laboratory, located in the Bay Area, works only at the lower biosafety risk levels, BSL-1 and BSL-2, and does not handle pathogens that can infect humans; all lab work is performed by human scientists. The group sits within Anthropic’s life sciences organization alongside teams whose work includes drug discovery and training Claude in biology and chemistry. The team does its work in Claude Science and Claude Code, sometimes with a harness of its own that coordinates many Claude sessions running in parallel. The company said that with hundreds to thousands of candidate reports arriving from a single campaign, the hypotheses themselves have become an object of study, with lessons fed back into the instructions given to Claude.

Anthropic said it is sharing the findings early to demonstrate Claude’s capabilities and to give the broader community insight into its work. The company has released a pre-print and a technical report with more detail on the discovery and invited proposals for research questions from other scientists.