PU-MLP: A PU-learning based method for polypharmacy side-effects detection based on multi-layer perceptron and feature extraction techniques

Polypharmacy, or the concurrent use of multiple medications, increases the risk of adverse effects due to drug interactions. As polypharmacy becomes more prevalent, forecasting these interactions is essential in the pharmaceutical field. Due to the limitations of clinical trials in detecting rare side effects associated with polypharmacy, computational methods are being developed to model these adverse effects. This study introduces a method named PU-MLP, based on a Multi-Layer Perceptron, to predict side effects from drug combinations. This research utilizes advanced machine learning techniques to explore the connections between medications and their adverse effects. The approach consists of three key stages: first, it creates an optimal representation of each drug using a combination of a random forest classifier, Graph Neural Networks (GNNs), and dimensionality reduction techniques. Second, it employs Positive Unlabeled learning to address data uncertainty. Finally, a Multi-Layer Perceptron model is utilized to predict polypharmacy side effects. Performance evaluation using 5-fold cross-validation shows that the proposed method surpasses other approaches, achieving impressive scores of 0.99, 0.99, and 0.98 in AUPR, AUC, and F1 measures, respectively. • A method based on Multi-Layer Perceptron is introduced to predict drug combination's side effects. • It utilizes sophisticated machine learning methods to explore the connections between medications and their adverse effects. • it uses Graph Neural Networks, Dimensionality reduction techniques, and a multi-Layer perceptron model.