This repository contains the code and data for “Multi-modal Contrastive Drug Synergy Prediction Model Guided by Single Modality”
- python == 3.7
- pandas == 1.3.5
- numpy == 1.21.6
- rdkit == 2023.3.2
- torch == 1.13.1
- pytorch geometric == 2.3.1
- scikit-learn == 1.0.2
- DrugCombDB is a database with the largest number of drug combinations to date.
- Oncology-Screen is an unbiased oncology compound screen datasets.
- Cell-protein Associations is harvested from the Cancer Cell Line Encyclopedia.
- Protein-Protein Interaction Network is a comprehensive human interactome network.
- Drug-protein Associations are based on FDA-approved or clinically investigational drugs.
python main_DrugCombDB.py
python main_OncologyScreen.py| Dataset | CV_mode | patience | alpha | beta | learning_rate |
|---|---|---|---|---|---|
| DrugCombDB | 1 | 40 | 5 | 0.5 | 0.001 |
| DrugCombDB | 2 | 90 | 10 | 0.05 | 0.0001 |
| DrugCombDB | 3 | 40 | 5 | 0.5 | 0.001 |
| Dataset | CV_mode | patience | alpha | beta | learning_rate |
|---|---|---|---|---|---|
| OncologyScreen | 1 | 200 | 5 | 0.1 | 0.001 |
| OncologyScreen | 2 | 300 | 10 | 0.3 | 0.001 |
| OncologyScreen | 3 | 300 | 5 | 0.1 | 0.001 |
Author: Tong Luo Mail: 751980485@qq.com
Corresponding author：Xian-gan Chen Mail: chenxg@mail.scuec.edu.cn
Date: 2025-10-10
School of Biomedical Engineering, South-Central Minzu University, China
Feel free to cite this work if you find it useful to you !
@article{MCDSP,
title = Multi-modal contrastive drug synergy prediction model guided by single modality,
author = {Tong Luo, Zheng Zhang, Xian-gan Chen, Zhi Li},
year = {2025},
volume = {17},
issue = {1},
journal = {Journal of Cheminformatics},
doi = {10.1186/s13321-025-01087-0},
}This code framework is modified based on the HyperGraphSynergy method. https://github.com/liuxuan666/HypergraphSynergy