Deep learning and attention mechanisms to identify key genes and their implications for the origin of insect wings
Fangrong Liu, Yong Cao, Songping Qian, Xingyu Tong, Junhui Liu, Jiawei Mao, Si Li, Shiyu Li, Youjie Zhao · 2026
Read Deep learning and attention mechanisms to identify key genes and their implications for the origin of insect wings by Fangrong Liu, Yong Cao, Songping Qian, Xingyu Tong, Junhui Liu, Jiawei Mao, Si Li, Shiyu Li, Youjie Zhao (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-13197475.txt.
Description
Fangrong Liu and co-authors present a computational biology paper, published in 2026, using deep learning to find genes behind the origin of insect wings. Wings were a key invention in animal history, yet the gene changes behind them remain partly hidden. Crustaceans, as cousins of the first winged insects, hold clues, and the team trained a model on protein sequences from more than one hundred species.
Their model mixes a two way memory network with an attention mechanism that highlights the sequence parts driving each call. It picked out several hundred candidate wing genes with high test accuracy. Those genes and their counterparts showed similar activity in wings and in crustacean gills, supporting the idea that wings evolved from gill like structures.
Catalog record
| CREATOR | Fangrong Liu, Yong Cao, Songping Qian, Xingyu Tong, Junhui Liu, Jiawei Mao, Si Li, Shiyu Li, Youjie Zhao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 59 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |