Autonomous AI agents discover reverse transcriptases with tandem repeat arrays
- 1Anthropic, PBC
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.
Related
- Defense-associated reverse transcriptases synthesize DNA in a telomerase-like manner
- Evaluating Autonomous LLM Agents Across Molecular Prediction and Optimization Benchmarks
- Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila
- Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila
- SixPack-AbScan: a web server to discover cross-reactivity of antibodies across species
BibTeX
@misc{yoon2026autonomous,
title = {{Autonomous AI agents discover reverse transcriptases with tandem repeat arrays}},
author = {P. H. Yoon and J. S. Athukoralage and E. Ameisen and E. Kauderer-Abrams and N. T. Perry and M. G. Durrant},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.05.755809},
url = {https://www.biorxiv.org/content/10.64898/2026.10.05.755809v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Autonomous AI agents discover reverse transcriptases with tandem repeat arrays
AU - P. H. Yoon
AU - J. S. Athukoralage
AU - E. Ameisen
AU - E. Kauderer-Abrams
AU - N. T. Perry
AU - M. G. Durrant
PY - 2026
DA - 2026/10/05
PB - bioRxiv
DO - 10.64898/2026.10.05.755809
UR - https://www.biorxiv.org/content/10.64898/2026.10.05.755809v1
AB - 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.
ER -