GLM-Prior: a genomic language model for transferable sequence-derived priors in gene regulatory network inference
Claudia Skok Gibbs, Angelica Chen, Richard Bonneau, Kyunghyun Cho · 2026
Read GLM-Prior: a genomic language model for transferable sequence-derived priors in gene regulatory network inference by Claudia Skok Gibbs, Angelica Chen, Richard Bonneau, Kyunghyun Cho (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13614953.txt.
Description
Claudia Skok Gibbs and co-authors build a gene-language model in 2026 that reads DNA text to guess gene links. Maps of which genes switch which others rest on prior lore, which is rich for a few beasts and thin for the rest. Their model learns the lore straight from letter strings.
Paired with a second stage that adds single-cell data, the priors feed full gene maps. Across six cell lines, the model beat chance where lore is rich, and its skill grew with more known links. It also carried across kinds of beasts in tests. Gene teams gain priors that can travel where hand-built lore runs out.
Catalog record
| CREATOR | Claudia Skok Gibbs, Angelica Chen, Richard Bonneau, Kyunghyun Cho |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 96 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |