Fusing Sequence and Structural Knowledge by Heterogeneous Models to Accurately and Interpretively Predict Drug–Target Affinity
Xin Zeng, Kai-Yang Zhong, Bei Jiang, Yi Li, Wim Buijs · 2023
Read Fusing Sequence and Structural Knowledge by Heterogeneous Models to Accurately and Interpretively Predict Drug–Target Affinity by Xin Zeng, Kai-Yang Zhong, Bei Jiang, Yi Li, Wim Buijs (2023) 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-10745601.txt.
Description
Xin Zeng and co-authors predict how tightly drugs bind their targets in a 2023 paper. Binding strength guides drug discovery, but many predictors miss the fine structure of the contact. Their model, S2DTA, reads both the letter sequences of the drug, target, and binding pocket, and graph versions of their structures, then fuses the two views.
Extra feature complexity alone added little, the experiments showed, but joining the two model families did lift accuracy. Against three leading rivals, the fused model cut average error by about a quarter. Attention maps, which show what the model looks at, supported that it focuses on sensible contact regions. The authors offer the tool for screening candidate drugs before lab work.
Catalog record
| CREATOR | Xin Zeng, Kai-Yang Zhong, Bei Jiang, Yi Li, Wim Buijs |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |