DigestAI news desk

Cut through the AI noise.

Research1 min read

Anthropic says Claude identified new enzyme system resembling crispr

Anthropic announced that its Claude system autonomously discovered a previously uncharacterized enzyme system similar to CRISPR, named array associated reverse transcriptases (ART). The system combines a reverse transcriptase, a partner gene, and a long array of evenly spaced DNA repeats found mainly in bacteriophages.

1 source

Key points

  • Claude identified a new enzyme system called array associated reverse transcriptases (ART) that resembles CRISPR.
  • Roughly 950 agents spent 21 hours, used about 210 million tokens, and narrowed 200,000+ reverse transcriptases to 20 candidate systems.
  • Early lab tests show the ART repeat array produces distinct short RNAs, but its biological function remains unknown.

Claude received a high‑level prompt to search a large DNA sequence database for unusual reverse transcriptases. Roughly 950 agents spent 21 hours and used about 210 million tokens, collecting more than 200,000 reverse transcriptases, flagging 3,500 candidate systems and narrowing them to 20 for deeper analysis. Anthropic said the same work would take an expert scientist weeks or months.

Early experiments in Anthropic’s Bay Area laboratory found the ART repeat array is expressed as distinct short RNAs, though its biological function remains unknown. The results have been released as a preprint, with further experiments underway. The project stems from a life‑sciences research group Anthropic formed in spring 2026 to test whether general AI can accelerate biological discovery.

Full story from cryptobriefing.com · by Editorial Team · via Search: ClaudeOpen source ↗

Anthropic’s AI Claude discovers new enzyme system akin to CRISPR

cryptobriefing.com · 23 September 2026

Loading the full article…

This text was published by cryptobriefing.com and written by Editorial Team. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Research

All →

Related stories