Server Introduction Code and Data Contact
Introduction page

Service description:

The localization information of RNAs in cell can provide important insights into biological functions. There is a great deal of research that subcellular localization has been demonstrated to be a fundamental regulation mode in cells. Considering expensive and inconvenient biological experiments, automatic computational tools are highly desired to speed up RNA-related subcellular localization studies. However, most existing RNA subcellular localization classifiers only solve the problem of single-label classification. In fact, a single RNAs sequence often surrounds multiple proteins. Therefore, it is of great practical significance to expand into the multi-label classification problem. In this study, we extract different types of RNA-associated subcellular localization multi-label datasets on four RNA categories, and construct RNA subcellular localization datasets. In order to study subcellular localization for Homo sapiens, we establish human RNA subcellular localization datasets. Furthermore, we utilize different nucleotide property composition models to extract effective features to adequately represent the important information of nucleotide sequences. In the most critical part, we achieve a major challenge is to fuse the multivariate information through multiple kernel learning based on Hilbert-Schmidt independence criterion, and put the optimal combined kernel into an integration support vector machine model for training a multi-label RNA subcellular localization classifier. To be specific, our novel method outperforms outstanding rather than other tools in most respects on our novel benchmark datasets. The flowchart is shown in the figure 1.

This web server develops for RNAs subcelluar prediction. The predictor covers the following 4 types of RNAs: (1) mRNA, (2) lncRNA, (3) miRNA, (4) snoRNA.

flow

Fig.1.Flowchart of the whole prediction process.