Autonomous AI agents discover reverse transcriptases with tandem repeat arrays

Checked 31 Oct 2026. Open license (CC-BY, CC-BY-SA, CC0, public domain): full text indexed and used in synthesis.

Abstract Metagenomic databases hold vast quantities of unexplored genetic material that can seed tools for biotechnology and medicine, but discovery is limited by our ability to examine sequence data at scale. Here, we show that large language models (LLMs) in an autonomous harness can alleviate this bottleneck and surface novel molecular systems. We deployed Claude Code instances to survey reverse transcriptase (RT) loci across 1.9 billion protein clusters. Among the top candidates were array-associated RTs (ART), a novel family of jumbo-phage RTs coupled with an array of ∼200-nucleotide units and a dedicated partner gene. Session transcripts show that Claude identified the ART family by directly examining its DNA sequences and recognizing the atypical repeats, a behavior attributable to specific Mythos 5 internal signals that respond to repeated DNA. ART arrays are highly expressed and appear as discrete units during Staphylococcus phage infection, suggesting an RT system directed by a repertoire of distinct RNAs. These findings indicate that LLMs can autonomously detect anomalies and drive analyses to initiate biological discoveries.

• AI-initiated biological discovery is now being validated against experimental ground truth that was never in the literature. Penadés et al. 2025 posed a question that took years to resolve experimentally but remained unpublished and found the AI co-scientist's top-ranked hypothesis matched the confirmed mechanism, while Yoon et al. 2026's autonomous Claude Code survey of 1.9 billion protein clusters surfaced a novel reverse-transcriptase family with expression evidence during phage infection. Trace →
• Yoon et al. 2026 redraws rather than breaks the computation-first boundary of autonomous science: the discovery is biological, but it was made by surveying protein-cluster databases—work conducted entirely on the computer, the very condition under which Lu et al. 2026 built their end-to-end system—so the autonomy frontier tracks the digital experimental loop, not the discipline. Trace →
• The full-chain traceability that Zhao et al. 2026 demand as a new evaluation paradigm is already being practiced: Yoon et al. 2026 used session transcripts to attribute their agent's discovery to the model directly examining DNA sequences and recognizing atypical repeats, a behavior they trace to specific internal signals responding to repeated DNA. Trace →

• AI for science and agentic research