Zero-shot ecological annotation of microbial genomes with myLLannotator accelerates scientific discovery
A. Leea, Aryan Sharmab, Rohan Maddamsettia b c✉
- aInstitute for Quantitative Biomedicine, Rutgers University, New Brunswick, NJ
- bGraduate Program in Molecular Biosciences, Rutgers University, New Brunswick, NJ
- cDepartment of Biochemistry and Microbiology, Rutgers University, New Brunswick, NJ
- ✉Corresponding author
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
ABSTRACT Large language models (LLMs) are promising scientific assistants, but many models remain inaccessible for resource-constrained scientists. To address this, we present myLLannotator, a python package for metadata annotation built on llama3.2-3B. myLLannotator labels 18,000+ genomes in ~2 hours on a laptop, reproducing a discovery involving substantial manual annotation. We use myLLannotator to discover that duplicated genes are depleted in endosymbiotic bacteria, demonstrating its power to accelerate hypothesis testing and discovery.
TL;DRThis work uses myLLannotator, a python package for metadata annotation built on llama3.2-3B, to discover that duplicated genes are depleted in endosymbiotic bacteria, demonstrating its power to accelerate hypothesis testing and discovery. (Semantic Scholar)