Sporadic cancer develops from the accrual of somatic mutations. Out of all small-scale somatic aberrations in coding regions, 95% are base substitutions, with 90% being missense mutations. While multiple studies focused on the importance of this mutation type, a machine learning method based on the number of protein-protein interactions (PPIs) has not been fully explored. This study aims to develop an improved computational method for driver identification, validation and evaluation (DRIVE), which is compared to other methods for assessing its performance. DRIVE aims at distinguishing between driver and passenger mutations using a feature-based learning approach comprising two levels of biological classification for a pan-cancer assessment of somatic mutations. Gene-level features include the maximum number of protein-protein interactions, the biological process and the type of post-translational modifications (PTMs) while mutation-level features are based on pathogenicity scores. Multiple supervised classification algorithms were trained on Genomics Evidence Neoplasia Information Exchange (GENIE) project data and then tested on an independent dataset from The Cancer Genome Atlas (TCGA) study. Finally, the most powerful classifier using DRIVE was evaluated on a benchmark dataset, which showed a better overall performance compared to other state-of-the-art methodologies, however, considerable care must be taken due to the reduced size of the dataset. DRIVE outlines the outstanding potential that multiple levels of a feature-based learning model will play in the future of oncology-based precision medicine.
Keywords: classification; decision tree; driver mutation; extreme gradient boosting; k-nearest neighbours; logistic regression; multilayer perceptron; pan-cancer; random forest; support vector machines.