Feature selection in bioinformatics

• Main Author: Wang, Lipo.
• Other Authors: School of Electrical and Electronic Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2013
• Subjects: DRNTU::Engineering::Bioengineering
• Online Access: https://hdl.handle.net/10356/84511; http://hdl.handle.net/10220/10071
• Institution: Nanyang Technological University

In bioinformatics, there are often a large number of input features. For example, there are millions of single nucleotide polymorphisms (SNPs) that are genetic variations which determine the dierence between any two unrelated individuals. In microarrays, thousands of genes can be proled in each test. It is important to nd out which input features (e.g., SNPs or genes) are useful in classication of a certain group of people or diagnosis of a given disease. In this paper, we investigate some powerful feature selection techniques and apply them to problems in bioinformatics. We are able to identify a very small number of input features sucient for tasks at hand and we demonstrate this with some real-world data.