Prediction of metabolite–protein interactions based on integration of machine learning and constraint-based modeling

Abstract

Abstract Motivation Metabolite–protein interactions play an important role in regulating protein functions and metabolism. Yet, predictions of metabolite–protein interactions using genome-scale metabolic networks are lacking. Here, we fill this gap by presenting a computational framework, termed SARTRE, that employs features corresponding to shadow prices determined in the context of flux variability analysis to predict metabolite–protein interactions using supervised machine learning. Results By using gold standards for metabolite–protein interactomes and well-curated genome-scale metabolic models of Escherichia coli and Saccharomyces cerevisiae, we found that the implementation of SARTRE with random forest classifiers accurately predicts metabolite–protein interactions, supported by an average area under the receiver operating curve of 0.86 and 0.85, respectively. Ranking of features based on their importance for classification demonstrated the key role of shadow prices in predicting metabolite–protein interactions. The quality of predictions is further supported by the excellent agreement of the organism-specific classifiers on unseen interactions shared between the two model organisms. Further, predictions from SARTRE are highly competitive against those obtained from a recent deep-learning approach relying on a variety of protein and metabolite features. Together, these findings show that features extracted from constraint-based analyses of metabolic networks pave the way for understanding the functional roles of the interactions between proteins and small molecules. Availability and implementation https://github.com/fayazsoleymani/SARTRE.