Minerva: genome language models uncover hidden non-coding DNA elements at scale
BrianHie · x · 2026-09-24
Researcher garykbrixi unveiled Minerva, a discovery-guided method powered by genome language models to mine the "dark matter" of genomes. Key points:
- Reveals interactions hidden in non-coding DNA
- Points to hundreds of new putative RNAs and repetitive elements per bacterial genome
- Finds elements invisible to traditional methods at orders of magnitude greater scale
Bio researchers (BaigYasa, BrianHie) amplified the work, noting strong potential for understanding and mining biological datasets beyond biomolecule design.
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