A trainable language model with potential to modulate translation rates in non-model organisms by generating upstream untranslated region sequence libraries
Alexander D Duggan, Matthew P Newman, David R McMillen · 2026
Read A trainable language model with potential to modulate translation rates in non-model organisms by generating upstream untranslated region sequence libraries by Alexander D Duggan, Matthew P Newman, David R McMillen (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/plos-pone-0348455.txt.
Description
Alexander D Duggan, Matthew P Newman, and David R McMillen built a tool for tuning protein production, published in PLOS ONE in 2026. The rate at which a gene is translated into protein depends partly on a stretch of sequence before the gene, called the upstream untranslated region. Their language model generates such sequences on demand.
Duggan's team trained the model so users can request sequences that speed up or slow down translation. The tool targets non-model organisms, species that lack the rich toolkits of standard lab organisms. Giving researchers a dial for protein output in neglected species can open work on microbes and crops that current methods barely touch, from biofuels to local food strains.
Catalog record
| CREATOR | Alexander D Duggan, Matthew P Newman, David R McMillen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46237 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |