Tomato classification using mass spectrometry-machine learning technique: A food safety-enhancing platform

•This research proposes the development of a platform for tomato quality monitoring.•Decision tree algorithm was used to analyze raw spectral data and propose biomarkers.•Features were composed of paired biomarkers to provide robustness to the method.•Metrics were 92% accuracy, 94% sensitivity, 90% specificity and 91% precision.•Biomarkers proposed evidenced use of agrochemicals and presence of organic compounds.