A comprehensive analysis of classification algorithms for cancer prediction from gene expression

Raehoon Jeong, Ameet Soni

Abstract: With the advent of inexpensive microarray technology, biologists have become increasingly reliant on gene expression analysis for detecting disease states, including diagnosis of cancerous tissue [12]. While random forests and SVMs have proven to be popular methods for expression analysis, little work has been done to compare these methods with AdaBoost, a popular ensemble learning algorithm, across a wide array of cancer prediction tasks. Our work shows AdaBoost outperforms other approaches on binary predictions while random forests and SVMs are the best choice in multi-class predictions.