Learning protein multi-view features in complex space

Dong-Jun Yu, Jun Hu, Xiao-Wei Wu, Hong-Bin Shen, Jun Chen, Zhen-Min Tang, Jian Yang, Jing-Yu Yang
2013 Amino Acids  
Your article is protected by copyright and all rights are held exclusively by Springer-Verlag Wien. This e-offprint is for personal use only and shall not be self-archived in electronic repositories. If you wish to selfarchive your work, please use the accepted author's version for posting to your own website or your institution's repository. You may further deposit the accepted author's version on a funder's repository at a funder's request, provided it is not made publicly available until 12
more » ... onths after publication. Abstract Protein attribute prediction from primary sequences is an important task and how to extract discriminative features is one of the most crucial aspects. Because single-view feature cannot reflect all the information of a protein, fusing multi-view features is considered as a promising route to improve prediction accuracy. In this paper, we propose a novel framework for protein multi-view feature fusion: first, features from different views are parallely combined to form complex feature vectors; Then, we extend the classic principal component analysis to the generalized principle component analysis for further feature extraction from the parallely combined complex features, which lie in a complex space. Finally, the extracted features are used for prediction. Experimental results on different benchmark datasets and machine learning algorithms demonstrate that parallel strategy outperforms the traditional serial approach and is particularly helpful for extracting the core information buried among multi-view feature sets. A web server for protein structural class prediction based on the proposed method (COMSPA) is freely available for academic use at: http://www.csbio. sjtu.edu.cn/bioinf/COMSPA/.
doi:10.1007/s00726-013-1472-6 pmid:23456487 fatcat:mozm24gjvvctdd2zxkb2yyfu6y