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.
|State||Published - 2018|
Bibliographical noteFunding Information:
This study was supported by a fund (No. 31401123) from the Natural Science Foundation of China.
© 2018 Tian S et al.
- Core subset
- Feature selection
- Gene set analysis
- Longitudinal microarray data
- Significance analysis of microarray (SAM)
ASJC Scopus subject areas
- Biochemistry, Genetics and Molecular Biology (all)
- Immunology and Microbiology (all)
- Pharmacology, Toxicology and Pharmaceutics (all)