Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2025 Jul 30:16:1632775.
doi: 10.3389/fphar.2025.1632775. eCollection 2025.

Machine learning-based drug-drug interaction prediction: a critical review of models, limitations, and data challenges

Flaviu-Ioan Gheorghita  1 , Vlad-Ioan Bocanet  2 , Laszlo Barna Iantovics  3
Affiliations
Review

Machine learning-based drug-drug interaction prediction: a critical review of models, limitations, and data challenges

Flaviu-Ioan Gheorghita et al. Front Pharmacol. .

Abstract

Background/objectives: New computational methods, based on statistical, machine learning, and deep learning techniques using drug-related entities (e.g., genes, protein bindings, etc.), help reduce the costs of in-vitro experiments through drug-drug interaction prediction (DDIp). This review examines recent advances in DDIp. It presents an in-depth review of the state-of-the-art studies relating to semi-supervised, supervised, self-supervised learning, and other techniques such as graph-based learning and matrix factorization methods for predicting DDIs. All possible interactions between drugs are not known, and accurately predicting interactions is even more difficult due to the complex nature of drug-drug interactions (DDI).

Methods: Of the 49 papers published in Web of Science in the last 6 years, 24 papers were considered relevant based on information presented in their titles and abstracts. The included articles focus specifically on predicting DDIs using a type of machine learning algorithm. Excluded articles focused on drug discovery, drug repurposing, molecular representation, or the extraction of biomedical interactions. The methodology, results limitations, and future research directions were studied for each paper. Common challenges, limitations, and future research directions were analyzed.

Results and conclusion: The main limitations are class imbalance, poor performance on new drugs, limited explainability, and the need for additional data sources.

Keywords: adverse drug reactions; drug-drug interaction; graph-based learning; healthcare; machine learning techniques; semi-supervised learning; supervised learning.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

FIGURE 1
FIGURE 1
Overview of article selection and classification strategy used in this review.
FIGURE 2
FIGURE 2
The resulting papers grouped by publication year.
FIGURE 3
FIGURE 3
The resulting papers grouped by publisher.
FIGURE 4
FIGURE 4
The country of origin of the authors of the publications as per WoS.
FIGURE 5
FIGURE 5
Universal pipeline for DDI prediction showing the typical workflow from input data to clinical application. This framework reflects common steps used across all 24 reviewed models, with some variation in preprocessing and modeling components.
FIGURE 6
FIGURE 6
Performance versus computational complexity of the 24 reviewed DDI prediction models. Performance metrics from Table 6 plotted against estimated complexity scores, color-coded by learning paradigm.
FIGURE 7
FIGURE 7
Taxonomy of the 24 reviewed DDI prediction models, grouped by learning paradigm (supervised, semi-supervised, self-supervised, structured) and showing their core methodological components.
FIGURE 8
FIGURE 8
Decision guide for selecting appropriate DDI prediction approaches based on data characteristics and computational or interpretability constraints.
See this image and copyright information in PMC

References

    1. Cao J., Lin X., Guo S., Liu L., Liu T., Wang B. (2021). “Bipartite graph embedding via mutual information maximization,” in Proceedings of the 14th ACM international conference on web search and data mining (New York, NY, USA: Association for Computing Machinery; ), 635–643. 10.1145/3437963.3441783 - DOI
    1. Chandra Umakantham O., Srinivasan S., Pathak V. (2024). Detecting side effects of adverse drug reactions through drug-drug interactions using graph neural networks and self-supervised learning. IEEE Access 12, 93823–93840. 10.1109/ACCESS.2024.3407877 - DOI
    1. Chen T., Guestrin C. (2016). “XGBoost: a scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (New York, NY, USA: Association for Computing Machinery; ), 785–794. 10.1145/2939672.2939785 - DOI
    1. Cheng F., Zhao Z. (2014). Machine learning-based prediction of drug–drug interactions by integrating drug phenotypic, therapeutic, chemical, and genomic properties. J. Am. Med. Inf. Assoc. 21, e278–e286. 10.1136/amiajnl-2013-002512 - DOI - PMC - PubMed
    1. Chu X., Lin Y., Wang Y., Wang L., Wang J., Gao J. (2019). MLRDA: a multi-task semi-supervised learning framework for drug-drug interaction prediction, 4518–4524.