LOTUS: A single- and multitask machine learning algorithm for the prediction of cancer driver genes.

Olivier Collier,Jean-Philippe Vert,Véronique Stoven,Teresa M Przytycka

doi:10.1371/journal.pcbi.1007381

Olivier Collier, Jean-Philippe Vert + Show 2 more

Open Access

https://doi.org/10.1371/journal.pcbi.1007381

Copy DOI

Abstract

Cancer driver genes, i.e., oncogenes and tumor suppressor genes, are involved in the acquisition of important functions in tumors, providing a selective growth advantage, allowing uncontrolled proliferation and avoiding apoptosis. It is therefore important to identify these driver genes, both for the fundamental understanding of cancer and to help finding new therapeutic targets or biomarkers. Although the most frequently mutated driver genes have been identified, it is believed that many more remain to be discovered, particularly for driver genes specific to some cancer types. In this paper, we propose a new computational method called LOTUS to predict new driver genes. LOTUS is a machine-learning based approach which allows to integrate various types of data in a versatile manner, including information about gene mutations and protein-protein interactions. In addition, LOTUS can predict cancer driver genes in a pan-cancer setting as well as for specific cancer types, using a multitask learning strategy to share information across cancer types. We empirically show that LOTUS outperforms five other state-of-the-art driver gene prediction methods, both in terms of intrinsic consistency and prediction accuracy, and provide predictions of new cancer genes across many cancer types.

Highlights

In our current understanding of cancer, tumors appear when some cells acquire functionalities that give them a selective growth advantage, allowing uncontrolled proliferation and avoiding apoptosis [1, 2]
Cancer development is driven by mutations and dysfunction of important, so-called cancer driver genes, that could be targeted by specific therapies
We propose a new method for cancer driver gene prediction called Learning Oncogenes and TUmor Suppressors (LOTUS)

Summary

Introduction

In our current understanding of cancer, tumors appear when some cells acquire functionalities that give them a selective growth advantage, allowing uncontrolled proliferation and avoiding apoptosis [1, 2] These malignant characteristics arise from various genomic alterations including point mutations, gene copy number variants (CNVs), translocations, inversions, deletions, or aberrant gene fusions. Many studies have shown that these alterations are not uniformly distributed across the genome [3, 4], and target specific genes associated with a limited number of important cellular functions such as genome maintenance, cell survival, and cell fate [5] Among these so-called driver genes, two classes have been distinguished in the literature: tumor suppressors genes (TSGs) and oncogenes (OGs) [6, Chapter 15]. Trastuzumab [10] is a drug given against breast cancer that targets the protein precisely encoded by ERBB2, which has dramatically improved the prognosis of patients whose tumors overexpress that OG

Methods

Results

Discussion

Conclusion