T-pGNN4DTI: Towards better drug-target interactions prediction using Global Self-attentive Pooled Graph Convolutional Networks and protein pre-training Models
Yanmei Lin, Boqi Yang, Jianping Liao, Chenjie Du, Hongguo Cai, Yijia Wu, Yuzhong Peng · 2026
Read T-pGNN4DTI: Towards better drug-target interactions prediction using Global Self-attentive Pooled Graph Convolutional Networks and protein pre-training Models by Yanmei Lin, Boqi Yang, Jianping Liao, Chenjie Du, Hongguo Cai, Yijia Wu, Yuzhong Peng (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/plos-pone-0352250.txt.
Description
Lin and colleagues built a computer method to predict which drugs will bind which body proteins in a 2026 study. Lab testing of every drug and protein pair is slow and costly, so good predictions narrow the search. Their method reads drug shapes with a graph network that weighs the most telling parts, and reads proteins with a pre-trained language-style model.
Tests on three standard data sets beat older prediction methods, the authors report. Fuller reading of both drug structure and protein sequence drove the gain. Better shortlists mean chemists spend lab time on pairs most likely to work. The approach adds a fresh route for early drug discovery work.
Catalog record
| CREATOR | Yanmei Lin, Boqi Yang, Jianping Liao, Chenjie Du, Hongguo Cai, Yijia Wu, Yuzhong Peng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 51695 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |