% This file was created with JabRef 2.3.1. % Encoding: Cp1252 @INBOOK{hauskrecht2006fundamentals, chapter = {Feature Selection and Dimensionality Reduction in Genomics and Proteomics}, title = {Fundamentals of Data Mining in Genomics and Proteomics}, publisher = {Springer}, year = {2006}, editor = {Berrar and Dubitzky and Granzow}, author = {Milos Hauskrecht and Richard Pelikan and Michal Valko and James Lyons--Weiler}, abstract = {Finding reliable, meaningful patterns in data with high numbers of attributes can be extremely difficult. Feature selection helps us to decide what attributes or combination of attributes are most important for finding these patterns. In this chapter, we study feature selection methods for building classification models from high-throughput genomic (microarray) and proteomic (mass spectrometry) data sets. Thousands of feature candidates must be analyzed, compared and combined in such data sets. We describe the basics of four different approaches used for feature selection and illustrate their effects on an MS cancer proteomic data set. The closing discussion provides assistance in performing an analysis in high-dimensional genomic and proteomic data.} }