Conference proceeding
A two-stage machine learning approach for pathway analysis
2010 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp.274-279
12/2010
DOI: 10.1109/BIBM.2010.5706576
Abstract
Analysis of gene expression data has emerged as an important approach to discover active pathways related to biological phenotypes. Previous pathway analysis methods use all genes in a pathway for linking it to a particular phenotype. Using only a subset of informative genes, however, could better classify samples. Here, we propose a two-stage machine learning approach for pathway analysis. During the first stage, informative genes that can represent a pathway are selected using feature selection methods. These "representative genes" are mostly associated with the phenotype of interest. In the second stage, pathways are ranked based on their "representative genes" using classification methods. We applied our two-stage approach on three gene expression datasets. The results indicate our method does outperform methods that consider every gene in a pathway.
Details
- Title: Subtitle
- A two-stage machine learning approach for pathway analysis
- Creators
- Wei Zhang - Dept. of Comput. Sci. & Eng., Univ. of Notre Dame, Notre Dame, IN, USAScott Emrich - Dept. of Comput. Sci. & Eng., Univ. of Notre Dame, Notre Dame, IN, USAErliang Zeng - Dept. of Comput. Sci. & Eng., Univ. of Notre Dame, Notre Dame, IN, USA
- Resource Type
- Conference proceeding
- Publication Details
- 2010 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp.274-279
- DOI
- 10.1109/BIBM.2010.5706576
- Publisher
- IEEE
- Language
- English
- Date published
- 12/2010
- Academic Unit
- Preventive and Community Dentistry; Roy J. Carver Department of Biomedical Engineering; Iowa Neuroscience Institute; Biostatistics; Dental Research
- Record Identifier
- 9984065371202771
Metrics
29 Record Views