An AI model has found a new ‘CRISPR-like’ biological system. Here’s what it means for science
After coding, mathematics and chatbots, AI companies are setting their sights on the messy world of biology.
Anthropic, a company known for its artificial intelligence (AI) systems, has unveiled a new 'CRISPR-like' biological system discovered by its Claude AI model. This development marks a significant milestone in the integration of AI in scientific research, as the AI system demonstrated a level of autonomy in its discovery process.
The newly found system is called array-associated reverse transcriptases (ART), which comprises an enzyme, a partner gene, and a long array of repeating DNA sequences. Although the reverse transcriptase enzyme is not novel, the discovery of the ART array and its potential role within a larger biological system is groundbreaking.
The ART system shares a similar architecture to CRISPR, a well-known bacterial defence system that has been repurposed as a powerful gene-editing tool. However, unlike CRISPR, it is currently unknown whether ART is capable of targeting and editing specific DNA sequences.
Claude's discovery of ART was driven by the AI’s ability to autonomously search through over 200,000 reverse transcriptases, identify 3,500 candidate systems, and select 20 for further analysis. During this process, an AI agent noticed the repeat array pattern, compared it with known systems, and identified ART as a potentially interesting result. The team then provided this finding to human researchers for validation.
The study demonstrates that AI can play a more significant role in scientific research by autonomously deciding which analyses to perform and which leads to follow, as well as identifying interesting results for experimental validation. While the ART system's impact on the scientific community remains uncertain, this work indicates that AI could become a valuable tool in managing existing biological datasets and exploring novel biological phenomena.
As AI systems like Claude continue to advance, they may become crucial in shaping the future of biological research, enabling researchers to prioritize testing of candidates and generate hypotheses. However, the ultimate potential of AI in science remains to be seen, as well as the necessary safeguards to ensure its safe and responsible use.
Written by urgent.news from The Conversation AU's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
