Work

To select relevant features for longitudinal gene expression data by extending a pathway analysis method

Year: 2018

Type: article

Abstract: The emerging field of pathway-based feature selection that incorporates biological information conveyed by gene sets/pathways to guide the selection of relevant genes has become increasingly popular and widespread. In this study, we adapt a gene set analysis method - the significance analysis of microarray gene set reduction (SAMGSR) algorithm to carry out feature selection for longitudinal microarray data, and propose a pathway-based feature selection algorithm - the two-level SAMGSR method. By using simulated data and a real-world application, we demonstrate that a gene's expression profiles over time can be considered as a gene set. Thus a suitable gene set analysis method can be utilized or modified to execute the selection of relevant genes for longitudinal omics data. We believe this work paves the way for more research to bridge feature selection and gene set analysis with the development of novel pathway-based feature selection algorithms.

Source: F1000Research

DOI: 10.12688/f1000research.15357.1

Authors: Suyan Tian, Chi Wang, Howard H. Chang

Institutions: First Hospital of Jilin University, University of Kentucky, Emory University

Language: English

Topic: Gene expression and cancer classification

Subfield: Molecular Biology

Field: Biochemistry, Genetics and Molecular Biology

Domain: Life Sciences

Open Access status: gold

Estimated APC paid: $1,350

Funders: National Natural Science Foundation of China, National Cancer Institute