Phenotype recognition for RNAi screening by random projection forest

High-content screening is important in drug discovery. The use of images of living cells as the basic unit for molecule discovery can aid the identification of small compounds altering cellular phenotypes. As such, efficient computational methods are required for the rate limiting task of cellular phenotype identification. In this paper we first investigate the effectiveness of a feature description approach by combining Haralick texture analysis with Curvelet transform and then propose a new ensemble approach for classification. The ensemble contains a set of base classifiers which are trained using random projection (RP) of original features onto higher-dimensional spaces. With Classification and Regression Tree (CART) as the base classifier, it has been empirically demonstrated that the proposed Random Projection Forest ensemble gives better classification results than those achieved by the Boosting, Bagging and Rotation Forest algorithms, offering a classification rate ∼ 88% with smallest standard deviation, which compares sharply with the published result of 82%.