Identifying protein-protein interaction sites using granularity computing of quotient space theory

Authors:
Yanping Zhang;Yongcheng Wang;Jun Ma;Xiaoyan Chen
Affiliations:
Key Lab of Ministry of Education for CI & SP, Anhui University, Hefei, Anhui, China;Key Lab of Ministry of Education for CI & SP, Anhui University, Hefei, Anhui, China;Key Lab of Ministry of Education for CI & SP, Anhui University, Hefei, Anhui, China;Key Lab of Ministry of Education for CI & SP, Anhui University, Hefei, Anhui, China
Venue:
RSKT'10 Proceedings of the 5th international conference on Rough set and knowledge technology
Year:
2010

Citing 4
Cited 0

Theory and Applications of Problem Solving

Theory and Applications of Problem Solving
Improved prediction of protein--protein binding sites using a support vector machines approach

Bioinformatics
The quotient space theory of problem solving

RSFDGrC'03 Proceedings of the 9th international conference on Rough sets, fuzzy sets, data mining, and granular computing
A geometrical representation of McCulloch-Pitts neural model and its applications

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

The function of protein-protein interaction is very important to cell activity. Studying protein-protein interaction can help us understand life activities and pharmaceutical design. In this study, a kernel covering algorithm combined with the theory of granular computing of quotient space for predicting protein-protein interaction sites is proposed, (i.e. KCA-GS Model). This method achieves good performances, and the Sensitivity, Specificity, Accuracy and Correlation coefficient are 52.97%, 53.92%, 70.27%, 24.61%, respectively. It is indicated that our method is effective, potential and promising to identify protein-protein interaction sites.