Title: Automated image-based protein subcellular location prediction in human reproductive tissue based on ensemble learning global and local patterns
Authors: Fan Yang
Addresses: Key Laboratory of Optic-Electronic and Communication, Jiangxi Science & Technology Normal University, Nanchang, China
Abstract: Human reproductive system is a unique organ system owing to which humans are capable of reproducing and bearing live offsprings. From a microscopic point of view, this system process requires protein appearing on the right subcellular location at the right time. In this paper, we developed a novel protocol for protein subcellular localisation prediction from human reproductive normal tissues. According to experimental results, three conclusions can be summarised. First, the completed local binary pattern is more discriminative for describing immunohistochemistry images. Second, the proposed ensemble classifier based on support vector machine learning models has a significant improvement. Third, through three different statistical voting approaches, two proteins for male and two proteins for female were identified as the biomarkers in reproductive tissue. These promising results indicate that the developed protocol can be applied not only for accurate large-scale image-based protein subcellular localisation annotations but also for biomarker identification of human reproductive tissue.
Keywords: protein subcellular localisation; local binary patterns; feature selection; ensemble classifiers; biomarker identification; biomarkers; immunohistochemistry images; location prediction; human reproductive tissue; support vector machines; SVM.
International Journal of Wireless and Mobile Computing, 2015 Vol.8 No.4, pp.367 - 376
Available online: 27 Jul 2015 *Full-text access for editors Access for subscribers Purchase this article Comment on this article