TPepPro: a deep learning model for predicting peptide–protein interactions
Xiaohong Jin, Zimeng Chen, Dan Yu, Qianhui Jiang, Zhuobin Chen, Bin Yan, Jing Qin, Yong Liu, Junwen Wang · 2025
Read TPepPro: a deep learning model for predicting peptide–protein interactions by Xiaohong Jin, Zimeng Chen, Dan Yu, Qianhui Jiang, Zhuobin Chen, Bin Yan, Jing Qin, Yong Liu, Junwen Wang (2025) 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-11681936.txt.
Description
Xiaohong Jin and co-authors present a deep learning model, described in the head as a 2024 paper, to predict how small protein chains bind larger proteins. Such pairs matter since chain-based drugs are on the rise, with more approvals each year. Lab tests of these pairs are slow and costly, and classic sim methods eat compute with modest accuracy.
Their model rests on a transformer design, the frame behind many recent AI gains. It trained on 19,187 pairs with both sequence and shape data, mixing local sequence features with global shape features. A rebuilt shape network in a lean order cut the compute the task needs. The model hit 0.855 accuracy, which beat the next best model by a wide margin. Some of its fresh picks match past lab proof, which backs its use in drug hunts.
Catalog record
| CREATOR | Xiaohong Jin, Zimeng Chen, Dan Yu, Qianhui Jiang, Zhuobin Chen, Bin Yan, Jing Qin, Yong Liu, Junwen Wang |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 41 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |