Identifying Cancer Drivers Using DRIVE: A Feature-Based Machine Learning Model for a Pan-Cancer Assessment of Somatic Missense Mutations

Abstract

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.

Introducing AI to the molecular tumor board: one direction toward the establishment of precision medicine using large-scale cancer clinical and biological information

“…A Schematic diagram showing an overview of DRIVE, a feature-based machine learning platform for pan-cancer assessment of somatic missense mutations, modified from Ref. [ 142 ]. This approach uses a total of 51 features spanning the gene and mutation levels.…”

“…Therefore, Dragomir et al developed and reported a new method (DRIVE) that utilizes machine learning techniques to identify driver and passenger mutations (Fig. 3 A) [ 142 ]. Mutation-level characteristics are based on pathogenicity scores, while gene-level characteristics include the maximum number of protein-protein interactions, biological processes, and types of post-translational modifications.…”

“…To validate the ability of the proposed method, it was evaluated on a benchmark dataset, which showed that both gene- and mutation-level features were representative of driver mutations, and the proposed method was > 80% accurate in finding the true mutation type. The results suggest that machine learning methods can be used to gain knowledge from mutation data to achieve more targeted cancer treatments [ 142 ].…”

Identification and Segregation of Genes with Improved Recurrent Neural Network Trained with Optimal Gene Level and Mutation Level Features

“…The results acquired with the projected model are manifested in Table II Bi-GRU, SVM, DRIVE [28] and EARN [5], respectively. I-RNN model has recorded the highest accuracy as 95.5%, which is better than the existing models.…”

Effects of Multi-Omics Characteristics on Identification of Driver Genes Using Machine Learning Algorithms

“…For example, H3 lysine 4 (H3K4me3) and 5 -C-phosphate-G-3 (CpG) methylation alteration are related to transcription elongation, enhancer activity, and repression of tumor suppressors [14]. Genomic features include the maximum number of protein-protein interactions, biological principle types of cells, and post-translational modification (PTM) [15].…”