Impact Factor 4.151
2017 JCR, Clarivate Analytics 2018

Frontiers journals are at the top of citation and impact metrics

Original Research ARTICLE Provisionally accepted The full-text will be published soon. Notify me

Front. Genet. | doi: 10.3389/fgene.2019.00256

A machine learning approach for identifying gene biomarkers guiding the treatment of breast cancer

 Ashraf Abou Tabl1*,  Abedalrhman Alkhateeb1*, Waguih ElMaraghy1,  Luis Rueda1 and Alioune Ngom1
  • 1University of Windsor, Canada

Studying breast cancer survivability among different patients who received various treatment therapies may help us understand the relationship between the survivability and treatment of patients based on genetic expression. In this work, we present a classification system that predicts whether a given breast cancer patient who underwent through hormone therapy, radiotherapy, or surgery will survive beyond five years after treatment. Our classifier is a tree-based hierarchical approach that groups breast cancer patients based on survivability classes. Each node in the tree is associated with a treatment therapy and a subset of genes that can best predict whether a given patient will survive for more than 5 years after that particular treatment. We applied our tree-based method to a gene expression dataset about 347 treated breast cancer patients and identified potential subsets of biomarkers that can predict survivability with high accuracy levels, ranging from 80.9% to 100%. We investigated the roles of many biomarkers through a literature review and found that certain biomarkers are strongly related to breast cancer survivability.

Keywords: breast cancer, Classification, Feature Selection, gene biomarkers, machine learning, Survivability, Treatment therapy

Received: 25 Oct 2018; Accepted: 08 Mar 2019.

Edited by:

Quan Zou, University of Electronic Science and Technology of China, China

Reviewed by:

Yang Dai, University of Illinois at Chicago, United States
Leyi Wei, Tianjin University, China  

Copyright: © 2019 Abou Tabl, Alkhateeb, ElMaraghy, Rueda and Ngom. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence:
Mr. Ashraf Abou Tabl, University of Windsor, Windsor, Canada, aboutaba@uwindsor.ca
Dr. Abedalrhman Alkhateeb, University of Windsor, Windsor, Canada, alkhate@uwindsor.ca