Anthropic: AI agent Claude autonomously discovers novel enzyme system ART in phage DNA

By Zhang Mengran, Science and Technology Daily

According to an official announcement from Anthropic, the company published research findings on March 23 from its Life Sciences Research Group and laboratory. The study demonstrates that Claude, through parallel agent-based analysis of genomic data, autonomously discovered a previously uncharacterized enzyme system in bacteriophages, named Array-associated Reverse Transcriptase (ART).

Key Findings

The ART system consists of three components:

• Reverse transcriptase – synthesizes DNA from an RNA template
• An adjacent companion protein gene – function currently unknown
• A DNA array containing regularly spaced repeat sequences – resembling CRISPR-like structures

While the system may offer new tools for nucleic acid manipulation, its actual biological function remains to be confirmed experimentally.

How the Discovery Was Made

The research began with a single prompt instructing Claude to search for notable novel reverse transcriptases within large-scale DNA sequences. Approximately 950 Claude agents worked in parallel for 21 hours, consuming about 210 million tokens. The process involved:

1. Screening nearly 200,000 reverse transcriptases to identify approximately 3,500 candidate systems
2. Narrowing the focus to 20 key targets
3. One agent, while examining raw sequences adjacent to an unusual reverse transcriptase in a phage, discovered a row of regularly spaced repetitive DNA
4. The agent then compared it against known families, counted repeat units, and searched relevant literature before submitting the system for human review

Laboratory Validation

Human researchers conducted further wet-lab experiments to verify the findings. They confirmed that the repeat array is expressed and produces a set of distinct short RNAs, indicating active transcriptional activity.

Expert Commentary

Dr. Feng Zhang, a professor at the Massachusetts Institute of Technology and a pioneer in the CRISPR field, reviewed the materials and commented that this represents "an exciting example of an AI agent contributing to biological discovery." He noted that such RNA repeat arrays associated with reverse transcriptases warrant further investigation.

Anthropic's Statement

Anthropic emphasized that AI was responsible only for data retrieval, candidate screening, and hypothesis organization, while all wet-lab experiments were conducted by human scientists. The company stated that if this type of genomic mining can be scaled, it could compress analyses that would typically take experts weeks or months into just a few hours.

However, Anthropic also stressed that whether ART can ultimately be developed into a biotechnology tool comparable to CRISPR depends on future experimental validation of short RNA targets, companion protein functions, and overall regulatory mechanisms.

Editor's Note

Many discoveries that have fundamentally transformed biology and medicine began when scientists noticed peculiarities in the diversity of molecular systems in nature. Yet, faced with massive biological datasets, traditional screening methods are often time-consuming, labor-intensive, and costly. With its powerful data processing and pattern recognition capabilities, AI can rapidly extract valuable information from complex data—and, as demonstrated here, identify novel systems worthy of experimental validation. Looking ahead, AI is expected to further enhance experimental prediction, providing directional guidance for biological research, thereby significantly reducing trial-and-error processes and accelerating the pace of scientific discovery and translation.