DeepIR-Pred: identification of insulin receptors using metaheuristic optimization of biologically informed multi-view features with deep recurrent learning
Matee Ullah, Zhen Li, Yixiao Zhai, Changwei Lv, Kashif Ahmad Khan, Quan Zou, Xu Tan · 2026
Read DeepIR-Pred: identification of insulin receptors using metaheuristic optimization of biologically informed multi-view features with deep recurrent learning by Matee Ullah, Zhen Li, Yixiao Zhai, Changwei Lv, Kashif Ahmad Khan, Quan Zou, Xu Tan (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-13617576.txt.
Description
The insulin receptor is a gatekeeper of growth and metabolism, and finding its look-alikes in protein sequences aids drug research. Matee Ullah and co-authors built a predictor that combines several views of a protein: evolutionary patterns, classic sequence features, and embeddings from protein language models. A whale-inspired search algorithm then picked the most telling features.
A recurrent neural network read the selected features in both directions to make the final call. On two carefully cleaned datasets, the system proved robust under cross-validation and on unseen proteins. Maps of its decisions showed clean separation between receptor and non-receptor proteins. The authors release the code and data for other researchers.
Catalog record
| CREATOR | Matee Ullah, Zhen Li, Yixiao Zhai, Changwei Lv, Kashif Ahmad Khan, Quan Zou, Xu Tan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 58 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |