Protein subcellular localization prediction using multiple kernel learning based support vector machine

2017 ◽  
Vol 13 (4) ◽  
pp. 785-795 ◽  
Author(s):  
Md. Al Mehedi Hasan ◽  
Shamim Ahmad ◽  
Md. Khademul Islam Molla
Keyword(s):  
Support Vector Machine ◽  
Subcellular Localization ◽  
Multiple Kernel Learning ◽  
Kernel Learning ◽  
Support Vector ◽  
Protein Subcellular Localization ◽  
Subcellular Localization Prediction ◽  
Multiple Kernel ◽  
Protein Subcellular Localization Prediction ◽  
Localization Prediction

An efficient multi-label protein subcellular localization prediction system was developed by introducing multiple kernel learning (MKL) based support vector machine (SVM).

Protein Subcellular Localization Prediction based on PSI-BLAST Profile and Principal Component Analysis

2019 ◽  
Vol 16 (5) ◽  
pp. 402-414
Author(s):  
Yuhua Yao ◽  
Manzhi Li ◽  
Huimin Xu ◽  
Shoujiang Yan ◽  
Pingan He ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Subcellular Localization ◽  
Principal Component ◽  
Component Analysis ◽  
Support Vector ◽  
Protein Subcellular Localization ◽  
Subcellular Localization Prediction ◽  
Evolutionary Features ◽  
Protein Subcellular Localization Prediction ◽  
Localization Prediction

Background: Prediction of protein subcellular location is a meaningful task which attracts much attention in recent years. Particularly, the number of new protein sequences yielded by the highthroughput sequencing technology in the post genomic era has increased explosively. Objective: Protein subcellular localization prediction based solely on sequence data remains to be a challenging problem of computational biology. Methods: In this paper, three sets of evolutionary features are derived from the position-specific scoring matrix, which has shown great potential in other bioinformatics problems. A fusion model is built up by the optimal parameters combination. Finally, principal component analysis and support vector machine classifier is applied to predict protein subcellular localization on NNPSL dataset and Cell- PLoc 2.0 dataset. Results: Our experimental results show that the proposed method remarkably improved the prediction accuracy, and the features derived from PSI-BLAST profile only are appropriate for protein subcellular localization prediction.

Sign in / Sign up

Export Citation Format

Share Document