Drug sensitivity prediction across cancer types using graph isomorphism networks and biological pathway features: A dual-branch deep learning approach
Shuang Li, Quanzhong Yang, Feifei Shen, Wei Chen, Shuya Zhang, Xinyi Dong, Weikai Zhang · 2026
Read Drug sensitivity prediction across cancer types using graph isomorphism networks and biological pathway features: A dual-branch deep learning approach by Shuang Li, Quanzhong Yang, Feifei Shen, Wei Chen, Shuya Zhang, Xinyi Dong, Weikai Zhang (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-0354669.txt.
Description
Shuang Li and co-authors built a deep learning model that predicts how strongly a cancer cell line will respond to a drug. The response measure halves cell survival, and computing it well could cut costly screening. Older models ignore either the drug's three-dimensional chemistry or the cell's biological state. Their 2026 design feeds both through separate branches.
One branch reads the drug as a molecular graph through a graph isomorphism network. The other reads fifty pathway activity scores computed from the cell line's gene expression. Training used a major public pharmacogenomics collection spanning many cancer types. Li and colleagues argue joining structure with pathway context should generalise better across data sources than either input alone.
Catalog record
| CREATOR | Shuang Li, Quanzhong Yang, Feifei Shen, Wei Chen, Shuya Zhang, Xinyi Dong, Weikai Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52950 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |