{
  "id": 9667141,
  "title": "Claude Discovers a CRISPR-Like Enzyme System Called ART",
  "url": "https://urgent.news/2026/09/25/claude-discovers-a-crispr-like-enzyme-system-called-art",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-25T01:05:30.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/raxxostudios/claude-discovers-a-crispr-like-enzyme-system-called-art-377b"
  },
  "original_language": "en",
  "account": "Anthropic's biology research lab announced the discovery of a novel enzyme system in bacteriophage DNA, named array-associated reverse transcriptases (ART). To identify this system, Claude, a large language model, autonomously processed 210 million tokens over 21 hours from a genomic database. Claude narrowed the candidate reverse transcriptases from 200,000 to 3,500 and then to 20 compelling candidates before flagging a pattern resembling CRISPR arrays that looked programmable for DNA operations. However, Anthropic emphasized that they do not yet know the system's function. The discovery was made through a distributed search, with Claude filtering and flagging the unusual pattern, while subsequent human experiments confirmed the finding. The comparison to CRISPR is notable due to the structural similarity, but the actual function of ART remains unknown.",
  "summary": "Anthropic says Claude autonomously spotted a novel enzyme system in bacteriophage DNA, which its biology lab named array-associated reverse transcriptases, or ART About 950 Claude agents processed 210 million tokens over 21 hours, narrowing 200,000 candidate reverse transcriptases down to 3,500, then to 20 compelling candidates before one flagged the pattern ART resembles CRISPR arrays and looks…",
  "key_points": [
    "Anthropic's biology lab discovered enzyme system ART in bacteriophage DNA.",
    "Claude, a large language model, identified ART from 210 million tokens.",
    "ART's function remains unknown despite structural similarity to CRISPR."
  ],
  "editors_take": "This discovery suggests that large language models like Claude can effectively partner with human researchers to uncover novel biological systems, potentially accelerating the pace of scientific breakthroughs.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}