Ensemble feature selection for stable biomarker identification and cancer classification from microarray expression data. (March 2022)

• Record Type: Journal Article
• Authors: Wang, Aiguo; Liu, Huancheng; Yang, Jing; Chen, Guilin
• Is Part Of: Computers in biology and medicine. Volume 142(2022)
• Publication Date: 2022-03
• Subjects: Feature selection -- Gene expression profiles -- Stability -- Ensemble learning; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2021.105208
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Microarray technology facilitates the simultaneous measurement of expression of tens of thousands of genes and enables us to study cancers and tumors at the molecular level. Because microarray data are typically characterized by small sample size and high dimensionality, accurate and stable feature selection is thus of fundamental importance to the diagnostic accuracy and deep understanding of disease mechanism. Hence, we in this study present an ensemble feature selection framework to improve the discrimination and stability of finally selected features. Specifically, we utilize sampling techniques to obtain multiple sampled datasets, from each of which we use a base feature selector to select a subset of features. Afterwards, we develop two aggregation strategies to combine multiple feature subsets into one set. Finally, comparative experiments are conducted on four publicly available microarray datasets covering both binary and multi-class cases in terms of classification accuracy and three stability metrics. Results show that the proposed method obtains better stability scores and achieves comparable to and even better classification performance than its competitors. Highlights: An ensemble feature selection framework towards stable gene selection is proposed. We present two aggregation strategies to combine multiple feature subsets into one. Experimental results show its effectiveness in terms of stability and accuracy. We conducted time complexity analysis of the proposed model.