A Machine Learning Approach for Predicting Synergism of Mixtures of Compounds in Treating Cancers
- 1Department of Physics, University of Alberta, 11335 Saskatchewan Dr NW, Edmonton, AB T6G 2M9, Canada
- 2Department of Mechanical and Aerospace Engineering, Politecnico di Torino, Corso Duca degli Abruzzi, 24, 10129 Turin, Italy
- 3SinoVeda Canada Inc., 1059 Tory Road NW, Edmonton, AB T6R 3A5, Canada
Abstract
Combination therapy is a common strategy in cancer treatment to improve efficacy, minimize side effects, and overcome drug resistance. However, the vast number of possible drug pairings makes experimental screening both time-consuming and costly. Drug interactions can result in synergy and antagonism, emphasizing the need for efficient predictive models. In this study, we develop a pairwise-compound quantitative structure–activity relationship (pQSAR) framework based on an ensemble stacking machine learning strategy to enhance prediction of empirically defined combination-effect classes using molecular and PK-related descriptors. Our approach leverages molecular descriptors along with key pharmacokinetic properties, the estimated accumulated drug concentration over 24 h (AUC), bioavailability (Fb) and volume of distribution at steady state (Vdss) to train the model on pairwise drug combinations. Building upon this foundation, we develop an ensemble stacking classification model that integrates multiple ML algorithms, providing a more accurate and robust prediction of drug synergy. Using the ALMANAC drug dataset across 8 cell lines from 4 different cancer types, our model achieves an accuracy exceeding 0.88 in predicting the effects of drug pairs. These results indicate that the proposed framework can capture predictive patterns associated with experimentally defined drug-combination effect classes in the evaluated dataset.
Related
- Synergism Between Krameria lappacea (Dombey) Burdet & B.B.Simpson Extracts and Gentamicin Against Gram-Positive Bacteria
- scDRP: disentangled representation learning for predicting single-cell responses to perturbations and estimating individual treatment effects
- Predicting transcriptional burst kinetics from histone modifications with deep learning
- Predicting specificity of TCR-pMHC interactions using machine-learning and biophysical models
- CPRISP: an interpretable deep learning framework predicting circRNA-RBP interactions and guiding therapeutic discovery in neurodegeneration
BibTeX
@article{shamloo2026machine,
title = {{A Machine Learning Approach for Predicting Synergism of Mixtures of Compounds in Treating Cancers}},
author = {Azar Shamloo and Jack Tuszynski and Yun Tam and Chih-Yuan Tseng},
journal = {International Journal of Molecular Sciences},
year = {2026},
month = sep,
doi = {10.3390/ijms27188345},
url = {https://www.mdpi.com/1422-0067/27/18/8345},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A Machine Learning Approach for Predicting Synergism of Mixtures of Compounds in Treating Cancers
AU - Azar Shamloo
AU - Jack Tuszynski
AU - Yun Tam
AU - Chih-Yuan Tseng
PY - 2026
DA - 2026/09/19
JO - International Journal of Molecular Sciences
DO - 10.3390/ijms27188345
UR - https://www.mdpi.com/1422-0067/27/18/8345
AB - Combination therapy is a common strategy in cancer treatment to improve efficacy, minimize side effects, and overcome drug resistance. However, the vast number of possible drug pairings makes experimental screening both time-consuming and costly. Drug interactions can result in synergy and antagonism, emphasizing the need for efficient predictive models. In this study, we develop a pairwise-compound quantitative structure–activity relationship (pQSAR) framework based on an ensemble stacking machine learning strategy to enhance prediction of empirically defined combination-effect classes using molecular and PK-related descriptors. Our approach leverages molecular descriptors along with key pharmacokinetic properties, the estimated accumulated drug concentration over 24 h (AUC), bioavailability (Fb) and volume of distribution at steady state (Vdss) to train the model on pairwise drug combinations. Building upon this foundation, we develop an ensemble stacking classification model that integrates multiple ML algorithms, providing a more accurate and robust prediction of drug synergy. Using the ALMANAC drug dataset across 8 cell lines from 4 different cancer types, our model achieves an accuracy exceeding 0.88 in predicting the effects of drug pairs. These results indicate that the proposed framework can capture predictive patterns associated with experimentally defined drug-combination effect classes in the evaluated dataset.
SN - 1422-0067
ER -