TY - JOUR
T1 - Hidden Markov models for cancer classification using gene expression profiles
AU - Nguyen, Thanh
AU - Khosravi, Abbas
AU - Creighton, Douglas
AU - Nahavandi, Saeid
N1 - Funding Information:
This research is supported by the Australian Research Council (Discovery Grant DP120102112 ) and the Centre for Intelligent Systems Research (CISR) at Deakin University.
Publisher Copyright:
© 2015 Elsevier Inc. All rights reserved.
PY - 2015/9/20
Y1 - 2015/9/20
N2 - This paper introduces an approach to cancer classification through gene expression profiles by designing supervised learning hidden Markov models (HMMs). Gene expression of each tumor type is modelled by an HMM, which maximizes the likelihood of the data. Prominent discriminant genes are selected by a novel method based on a modification of the analytic hierarchy process (AHP). Unlike conventional AHP, the modified AHP allows to process quantitative factors that are ranking outcomes of individual gene selection methods including t-test, entropy, receiver operating characteristic curve, Wilcoxon test and signal to noise ratio. The modified AHP aggregates ranking results of individual gene selection methods to form stable and robust gene subsets. Experimental results demonstrate the performance dominance of the HMM approach against six comparable classifiers. Results also show that gene subsets generated by modified AHP lead to greater accuracy and stability compared to competing gene selection methods, i.e. information gain, symmetrical uncertainty, Bhattacharyya distance, and ReliefF. The modified AHP improves the classification performance not only of the HMM but also of all other classifiers. Accordingly, the proposed combination between the modified AHP and HMM is a powerful tool for cancer classification and useful as a real clinical decision support system for medical practitioners.
AB - This paper introduces an approach to cancer classification through gene expression profiles by designing supervised learning hidden Markov models (HMMs). Gene expression of each tumor type is modelled by an HMM, which maximizes the likelihood of the data. Prominent discriminant genes are selected by a novel method based on a modification of the analytic hierarchy process (AHP). Unlike conventional AHP, the modified AHP allows to process quantitative factors that are ranking outcomes of individual gene selection methods including t-test, entropy, receiver operating characteristic curve, Wilcoxon test and signal to noise ratio. The modified AHP aggregates ranking results of individual gene selection methods to form stable and robust gene subsets. Experimental results demonstrate the performance dominance of the HMM approach against six comparable classifiers. Results also show that gene subsets generated by modified AHP lead to greater accuracy and stability compared to competing gene selection methods, i.e. information gain, symmetrical uncertainty, Bhattacharyya distance, and ReliefF. The modified AHP improves the classification performance not only of the HMM but also of all other classifiers. Accordingly, the proposed combination between the modified AHP and HMM is a powerful tool for cancer classification and useful as a real clinical decision support system for medical practitioners.
KW - Analytic hierarchy process
KW - Cancer classification
KW - DNA microarray
KW - Gene expression profile
KW - Gene selection
KW - Hidden Markov model
UR - http://www.scopus.com/inward/record.url?scp=84930065248&partnerID=8YFLogxK
U2 - 10.1016/j.ins.2015.04.012
DO - 10.1016/j.ins.2015.04.012
M3 - Article
AN - SCOPUS:84930065248
SN - 0020-0255
VL - 316
SP - 293
EP - 307
JO - Information Sciences
JF - Information Sciences
ER -