Robust prediction of drug combination side effects in realistic settings
- 1Escola de Matemática Aplicada, Fundação Getúlio Vargas, Rio de Janeiro, Brazil.
- 2Department of Computer Science, Centre for Systems and Synthetic Biology, Royal Holloway University of London, Egham, United Kingdom.
Abstract
Side effects caused by drug combinations pose a major challenge in healthcare. Knowledge of these side effects is limited because often they are not detected in clinical trials, which typically involve a restricted number of participants and tested drug combinations. We introduce DCSE (Drug Combinations Side Effects), a novel machine learning method for predicting polypharmacy side effects. DCSE learns latent signatures for drugs, drug pairs, and side effects to predict the probability that a side effect occurs in a given drug combination. We first evaluate its performance in the commonly adopted experimental settings in the literature. However, these rely on balanced testing datasets and sampled negative examples, which do not capture the highly imbalanced and structured set of unknown side effects encountered in practice. Therefore, a key contribution of this paper is the introduction of more realistic experimental settings under prospective evaluations. Here, we attempt to predict side effects reported between 2009 and 2014 after training only on data available prior to that period. These evaluations include warm-start scenarios, in which some side effects are already known for a drug pair, and cold-start scenarios, in which the model predicts side effects for previously uncharacterized drug pairs. Our results indicate that DCSE consistently outperforms state-of-the-art methods, demonstrating its robustness and efficacy in real-world applications. Author summary: Understanding the risks of combining medications is a central problem in healthcare. Clinical trials rarely capture the full range of side effects, and many side effects are identified only after drugs reach the market, leaving many possible drug combinations insufficiently tested. Computational approaches can help fill this gap by predicting which combinations are likely to cause specific side effects. Our approach works by learning signatures for both drugs and side effects, which can be thought of as representations that describe how drugs act and what is required to trigger a side effect. A key challenge is how to combine the signatures of two drugs into one representation for the pair. We show that simple linear models fail to capture the complexity of drug interactions, so we use a deep neural network to combine them in a non-linear way. Our tests, which use reports collected at different points in time to mirror how information about drug pairs becomes available, show that our approach is useful for monitoring risks after drugs have been approved and for exploring new uses of pairs of existing drugs.
Related
- An ensemble framework for robust drug response prediction and large-scale sensitivity profiling across cancers
- Regulon-informed cellular representations reveal task-dependent generalization in drug combination prediction
- ProDTI: prior-guided positive-unlabeled learning for robust drug-target interaction prediction.
- Adaptive responses to antifungal selection depend on dose and drug combination in experimentally evolved yeast
- Synergy-informed bilevel optimization reveals joint-specific benefits for realistic exoskeleton torque prediction
BibTeX
@article{jimenez2026robust,
title = {{Robust prediction of drug combination side effects in realistic settings}},
author = {Ruben Jimenez and Alberto Paccanaro},
journal = {PLOS Computational Biology},
year = {2026},
month = oct,
doi = {10.1371/journal.pcbi.1013619},
url = {https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1013619},
note = {CC BY},
}
RIS
TY - JOUR
TI - Robust prediction of drug combination side effects in realistic settings
AU - Ruben Jimenez
AU - Alberto Paccanaro
PY - 2026
DA - 2026/10/05
JO - PLOS Computational Biology
DO - 10.1371/journal.pcbi.1013619
UR - https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1013619
AB - Side effects caused by drug combinations pose a major challenge in healthcare. Knowledge of these side effects is limited because often they are not detected in clinical trials, which typically involve a restricted number of participants and tested drug combinations. We introduce DCSE (Drug Combinations Side Effects), a novel machine learning method for predicting polypharmacy side effects. DCSE learns latent signatures for drugs, drug pairs, and side effects to predict the probability that a side effect occurs in a given drug combination. We first evaluate its performance in the commonly adopted experimental settings in the literature. However, these rely on balanced testing datasets and sampled negative examples, which do not capture the highly imbalanced and structured set of unknown side effects encountered in practice. Therefore, a key contribution of this paper is the introduction of more realistic experimental settings under prospective evaluations. Here, we attempt to predict side effects reported between 2009 and 2014 after training only on data available prior to that period. These evaluations include warm-start scenarios, in which some side effects are already known for a drug pair, and cold-start scenarios, in which the model predicts side effects for previously uncharacterized drug pairs. Our results indicate that DCSE consistently outperforms state-of-the-art methods, demonstrating its robustness and efficacy in real-world applications. Author summary: Understanding the risks of combining medications is a central problem in healthcare. Clinical trials rarely capture the full range of side effects, and many side effects are identified only after drugs reach the market, leaving many possible drug combinations insufficiently tested. Computational approaches can help fill this gap by predicting which combinations are likely to cause specific side effects. Our approach works by learning signatures for both drugs and side effects, which can be thought of as representations that describe how drugs act and what is required to trigger a side effect. A key challenge is how to combine the signatures of two drugs into one representation for the pair. We show that simple linear models fail to capture the complexity of drug interactions, so we use a deep neural network to combine them in a non-linear way. Our tests, which use reports collected at different points in time to mirror how information about drug pairs becomes available, show that our approach is useful for monitoring risks after drugs have been approved and for exploring new uses of pairs of existing drugs.
SN - 1553-7358
SN - 1553-734X
ER -