Research Article

Prediction of core cancer genes using a hybrid of feature selection and machine learning methods

Published: August 03, 2015
Genet. Mol. Res. 14 (3) : 8871-8882 DOI: https://doi.org/10.4238/2015.August.3.10
Cite this Article:
(2015). Prediction of core cancer genes using a hybrid of feature selection and machine learning methods. Genet. Mol. Res. 14(3): gmr5929. https://doi.org/10.4238/2015.August.3.10
1,483 views

Abstract

Machine learning techniques are of great importance in the analysis of microarray expression data, and provide a systematic and promising way to predict core cancer genes. In this study, a hybrid strategy was introduced based on machine learning techniques to select a small set of informative genes, which will lead to improving classification accuracy. First feature filtering algorithms were applied to select a set of top-ranked genes, and then hierarchical clustering and collapsing dense clusters were used to select core cancer genes. Through empirical study, our approach is capable of selecting relatively few core cancer genes while making high-accuracy predictions. The biological significance of these genes was evaluated using systems biology analysis. Extensive functional pathway and network analyses have confirmed findings in previous studies and can bring new insights into common cancer mechanisms.

Machine learning techniques are of great importance in the analysis of microarray expression data, and provide a systematic and promising way to predict core cancer genes. In this study, a hybrid strategy was introduced based on machine learning techniques to select a small set of informative genes, which will lead to improving classification accuracy. First feature filtering algorithms were applied to select a set of top-ranked genes, and then hierarchical clustering and collapsing dense clusters were used to select core cancer genes. Through empirical study, our approach is capable of selecting relatively few core cancer genes while making high-accuracy predictions. The biological significance of these genes was evaluated using systems biology analysis. Extensive functional pathway and network analyses have confirmed findings in previous studies and can bring new insights into common cancer mechanisms.

About the Authors