GENIUS-LLM: An evidence-traceable, gene-centered multi-omics inference framework for plant gene function analysis
Beizhuo Li, Jiaqi You, Jie Zheng, Xianda Zheng, Xianlong Zhang, Maojun Wang, Zeyu Zhang · 2026
Read GENIUS-LLM: An evidence-traceable, gene-centered multi-omics inference framework for plant gene function analysis by Beizhuo Li, Jiaqi You, Jie Zheng, Xianda Zheng, Xianlong Zhang, Maojun Wang, Zeyu Zhang (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-13589542.txt.
Description
Beizhuo Li and colleagues built GENIUS-LLM, a framework that turns plant multi-omics data into traceable gene-function hypotheses. Gene-function analysis guides crop breeding, but integrating scattered omics datasets is labour-intensive, deep-learning predictions are opaque, and database queries demand exact identifiers. Their 2026 letter describes a language-model workflow that organises seven categories of gene-centred evidence across cotton, rice, and Arabidopsis into auditable reports.
For each queried gene, the system retrieves records, rewrites them as standardised natural-language blocks, and reasons through a fixed scaffold in GPT-4o, weighting direct functional cues above expression and co-expression evidence. The authors present traceable reasoning, not just prediction, as the advance, lowering the barrier to usable biological insight for breeders and researchers.
Catalog record
| CREATOR | Beizhuo Li, Jiaqi You, Jie Zheng, Xianda Zheng, Xianlong Zhang, Maojun Wang, Zeyu Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 13 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |