Random Forest for Bioinformatics

Modern biology has experienced an increasing use of machine learning techniques for large scale and complex biological data analysis. In the area of Bioinformatics, the Random Forest (RF) [6] technique, which includes an ensemble of decision trees and incorporates feature selection and interactions naturally in the learning process, is a popular choice. It is nonparametric, interpretable, efficient, and has a high prediction accuracy for many types of data. Recent work in computational biology has shown an increased use of random forest, owing to its unique advantages in dealing with small sample size, high-dimensional feature space, and complex data structures. The aim of this chapter is two-fold. First, to provide a review of notable extensions of random forest in bioinformatics, whereby promising direction such as RF based feature selection is discussed. Second, to briefly introduce the applications of random forest and its extensions. RF has been applied in a broad spectrum of biological tasks, including, for example; classifying different types of samples using gene expression of microarrays data, identifying disease associated genes from genome wide association studies, recognizing the important elements in protein sequences, or identifying protein-protein interactions.