DeepDRP: Dose-response predictions of drug pairs using deep learning based on data-driven feature representation and dose-response curve characteristics
Mohammadamin Moragheb, Alireza Dehghan, Parvin Razzaghi, Sajjad Gharaghani · 2026
Read DeepDRP: Dose-response predictions of drug pairs using deep learning based on data-driven feature representation and dose-response curve characteristics by Mohammadamin Moragheb, Alireza Dehghan, Parvin Razzaghi, Sajjad Gharaghani (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/pmc-13155681.txt.
Description
Drug pairs can work better than single drugs, but the right dose of each partner matters as much as the pairing itself, and testing every dose grid in the lab is impractical. Mohammadamin Moragheb and co-authors built DeepDRP, a deep learning system that predicts how a pair will perform across doses. It reads features of the two drugs, their doses, and the cell line being treated, then estimates the pair's synergy.
The system pairs two models. A global model trains on every available combination, while a local model focuses on past cases similar to the query at hand, arranged as a graph. Their joined predictions beat rival methods on two standard cancer drug datasets. The authors offer the tool as a way to narrow dose searches before costly experiments.
Catalog record
| CREATOR | Mohammadamin Moragheb, Alireza Dehghan, Parvin Razzaghi, Sajjad Gharaghani |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 42 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |