The structure-preserving spectral graph neural network for dual kinase inhibitors and synergy scoring in gastric cancer

Yang Zhang, Chunhong Yuan, Longgang Wang, Yujia Chen, Yanpeng Xing, Yuanlin Sun · 2025

Read The structure-preserving spectral graph neural network for dual kinase inhibitors and synergy scoring in gastric cancer by Yang Zhang, Chunhong Yuan, Longgang Wang, Yujia Chen, Yanpeng Xing, Yuanlin Sun (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-12764931.txt.

Description

Blocking two growth kinases with one drug could outflank gastric cancer, but designing such dual blockers is guesswork without good prediction. Yang Zhang and five co-authors build DuoKinaseNet, a graph neural network that learns from a large biomedical knowledge graph. Its key module feeds global graph structure into the model through spectral coordinates and diffusion-based attention, so predictions respect the network's overall shape.

Trained on DrugBank data, the model scored about 0.90 area under the curve for two prized targets, HER2 and FGFR2b, even on proteins it had never seen. It beat a wide field of baselines, including 3D-aware methods. The authors credit the dual-task setup and the structure-preserving module working together. The study appears in 2025.

Catalog record

CREATORYang Zhang, Chunhong Yuan, Longgang Wang, Yujia Chen, Yanpeng Xing, Yuanlin Sun
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE92 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12764931

Browse the full library · About the Tower of Babel