Minerva uses genome language models to uncover diverse ncRNA arrays in UG27 reverse transcriptase systems
BrianHie · x · 2026-09-23
David Li and Garyk Brixi introduce Minerva, an approach leveraging genome language models for biological discovery. Using learned co-evolutionary relationships, they show that UG27 reverse transcriptase systems encode variable arrays of diverse ncRNAs sharing a common structure, each templating a short DNA hairpin — a demonstration of how learned sequence representations can surface new biology.
More from Research
- MIT's Tegmark coins 'formal-washing': Signal protocol proof is far from complete — tegmark · 2026-11-12
- Signal formal verification hits 80%, Tegmark says Wired overstated completion — tegmark · 2026-11-12
- When does matter compute? Wave memory and a categorical closure criterion — neurovium · 2026-11-12
- Category-theoretic framework asks: when does a physical system actually compute? — neurovium · 2026-11-12
- Radical Numerics brings genome language model Omnii-1 to the edge for biodefense — exnx · 2026-11-12
- Against 'verifiable vs. fuzzy': the real axis is how expensive tasks are to grade — dfrsrchtwts · 2026-11-12