Minerva uses genome language models to uncover novel ncRNA systems in microbial genomes
BrianHie · x · 2026-09-24
Researchers unveil Minerva, an approach leveraging genome language models for biological discovery. The study finds that UG27 reverse transcriptase systems encode variable arrays of diverse ncRNAs sharing a common structure, each templating a short DNA hairpin. The work highlights how language models can decode poorly understood systems hidden in microbial genomes.
More from Research
- Open-source sys1 ships a Rust System 1 API for decision models at ~14ms on RTX PRO 6000 — IgorCarron · 2026-09-24
- AI's 'stunningly simple' proof of Erdős–Sós conjecture signals humans becoming interpreters of AI discoveries — alejandroll10 · 2026-09-24
- Max Planck's ERC-funded BrainAlign project opens two postdoc slots on brain-aligned LLMs — mtoneva1 · 2026-09-24
- Economist maps the order AI will automate economics: theory first, experiments last — soumitrashukla9 · 2026-09-24
- The rise of the solo researcher: single-author papers gain ground on arXiv — luismbat · 2026-09-24
- Science covers LLM 'functional pain vectors' study: can AI feel pain? — anilkseth · 2026-09-24