ML-SyPred – Machine Learning Synergy Predictor: A Tool to Predict Drug Combinations

Abstract Antimicrobial and antiviral resistances are worldwide public health threats, causing treatment failures and increasing morbidity and mortality. Mycobacterium tuberculosis and Plasmodium falciparum, among many others, are examples of multidrug-resistant pathogens requiring combinatorial drug therapy. The use of drug combinations acting in synergy represents an approach to enhance therapy and delay the development of drug resistance. Computational approaches can be used to develop predictive models assessing synergistic drug combinations to reduce the time and cost associated with standard experimental screening. Here, we describe the development of a computational tool (Machine Learning Synergy Predictor - ML-SyPred) that incorporates drug/compound features using machine learning algorithms to predict synergistic drug combinations. Using the ML-SyPred tool, we implemented a synergy predicting method, which includes several Python scriptings to clean and prepare the raw data and convert from the drug's biochemical structure composition to compound fingerprints to use as features. Five Machine Learning algorithms (i.e. Logistic Regression, Random Forest, Support Vector Machine, Ada Boost, and Gradient Boosting) were implemented to build prediction models. Two different biologically validated datasets consisting of 575 antibiotics and 1,054 antimalarials drug combinations were used to test the algorithms implemented. The best prediction models were obtained with the Random Forest algorithm for the antibiotic dataset (0.88 AUC), Logistic Regression for the antimalarial datasets strain Dd2 and HB3 (0.81 and 0.70 AUC, respectively), and Random Forest for the antimalarial datasets strain 3D7 (0.69 AUC). The ML-SyPred tool yielded 45% precision for synergistically predicted antimalarial drug combinations that are annotated and biologically validated, thus confirming the tool’s functionality and applicability. The ML-SyPred tool is available for free use and represents a promising strategy to discover potential drug combinations for further development in novel therapies.