article · Scientific Reports
Combining multiple cancer therapies can improve efficacy and overcome multidrug resistance, yet predicting whether drug pairings will be synergistic, additive, or antagonistic remains challenging. A computational framework trained on the O'Neil drug interaction dataset uses classification and regression models to predict both the nature of drug interactions and their sensitivity scores. By evaluating drug features alongside mechanisms of action, the framework identifies combination pairs with high likelihoods of synergistic effects against specific cancers. Notable pairings include kinase inhibitors combined with mTOR inhibitors, DNA damage-inducing therapies, or HDAC inhibitors, showing effectiveness across ovarian, melanoma, prostate, lung, and colorectal cancers. Furthermore, specific agents such as Gemcitabine, MK-8776, and AZD1775 frequently exhibit synergistic behaviours across multiple tumour types, providing a structured computational methodology to assist in discovering potent multi-drug cancer treatments.
Cancer treatments often fail when tumours develop resistance to single therapies. Predicting which drug combinations produce enhanced therapeutic effects without increasing harmful antagonism is difficult and costly. Machine learning models offer a rapid way to screen and prioritise existing approved drugs for combination treatments, helping to identify more effective regimens against challenging malignancies such as lung, ovarian, and colorectal cancers.
This computational tool is an early-stage research framework designed to assist pharmaceutical developers and oncology researchers in prioritising drug combinations for laboratory testing. By identifying high-potential pairings of existing drugs, it could streamline preclinical discovery pipelines. However, because the predictions are derived computationally from existing interaction datasets, substantial laboratory and clinical validation is required before any identified regimens can reach clinical practice.
AI-generated from the published abstract. Always read the original work before citing.
Combination therapy is a fundamental strategy in cancer chemotherapy. It involves administering two or more anti-cancer agents to increase efficacy and overcome multidrug resistance compared to monotherapy. However, drug combinations can exhibit synergy, additivity, or antagonism. This study presents a machine learning framework to classify and predict cancer drug combinations. The framework utilizes several key steps including data collection and annotation from the O'Neil drug interaction dataset, data preprocessing, stratified splitting into training and test sets, construction and evaluation of classification models to categorize combinations as synergistic, additive, or antagonistic, application of regression models to predict combination sensitivity scores for enhanced predictions compared to prior work, and the last step is examination of drug features and mechanisms of action to understand synergy behaviors for optimal combinations. The models identified combination pairs most likely to synergize against different cancers. Kinase inhibitors combined with mTOR inhibitors, DNA damage-inducing drugs or HDAC inhibitors showed benefit, particularly for ovarian, melanoma, prostate, lung and colorectal carcinomas. Analysis highlighted Gemcitabine, MK-8776 and AZD1775 as frequently synergizing across cancer types. This machine learning framework provides a valuable approach to uncover more effective multi-drug regimens.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1038/s41598-024-52814-w
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
