Image-based classification of protein subcellular location patterns in human reproductive tissue by ensemble learning global and local features

The reproductive system is a specific system of organs working together for the purpose of reproduction. As one of the most significant characteristics of human cell, subcellular localization plays a critical role for understanding specific functions of mammalian proteins. In this study, we developed a novel computational protocol for predicting protein subcellular locations from microscope images of cells in human reproductive tissues. Three major steps are contained in this protocol, i.e., protein object identification, image feature extraction, and classification. We first separated protein and DNA staining in the images with both linear and non-negative matrix factorization separation methods; then we extracted protein multi-view global and local texture features including wavelet Haralick, local binary patterns, local ternary patterns, and the local quinary patterns; finally based on the selected important feature subset, we constructed an ensemble classifier with support vector machines for classifications. Experiments are performed on a benchmark dataset consisting of seven major subcellular classes in human reproductive tissues collected from human protein atlas. Our results show that the local texture pattern features play an important complementary role to global features for enhancing the prediction performance. An overall accuracy of 85% is obtained through current system, and when only confident classifications are considered, the accuracy can reach 99%. It is the first developed image based protein subcellular location predictor specifically for human reproductive tissue. The promising results indicate that the developed protocol can be applied for accurate large-scale protein subcellular localization annotations in human reproductive system.