Predicting Protein Interaction Sites Based on a New Integrated Radial Basis Functional Neural Network

Abstract:

Interactions among proteins are the basis of various life events. So, it is important to recognize and research protein interaction sites. A control set that contains 149 protein molecules were used here. Then 10 features were extracted and 4 sample sets that contained 9 sliding windows were made according to features. These 4 sample sets were calculated by Radial Basis Functional neutral networks which were optimized by Particle Swarm Optimization respectively. Then 4 groups of results were obtained. Finally, these 4 groups of results were integrated by Genetic Algorithm based Selected Ensemble (GASEN) and better accuracy was got. So, the integrated method was proved to be effective.

• Periodical: Advanced Materials Research (Volumes 183-185)
• Pages: 387-391
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.183-185.387
• Online since: January 2011
• Authors: Xiao Li Shen, Yue Hui Chen
• Keywords: Feature, Genetic Algorithm Based Selected Ensemble, Integration, Protein Interaction Sites, Radial Basis Functional Neutral Network

References

[1] W. Xiangyu, C. Shouliang and G. Mingde: General Biology ( Higher Education Press, Beijing 2005).

[2] Y. Changhui, H. Vasant and D. Drena in: Predicting Protein-Protein Interaction Sites From Ami- no Acid Sequence. Technical report, Iowa State University (2002).

[3] S. Mile, T. Sanja and V. Kristian: Prediction of Protein-Protein Interaction Sites in Sequences and 3D Structures by Random Forests. PloS. Comput. Biol. Forum Vol. 5 (2009), pp.1-9.

DOI: 10.1371/journal.pcbi.1000278

[4] L. Man, L. T. Chew and S. Jian: Feature generation and representations for protein-protein intera- ction classification. J. Biomed. Inform. Forum Vol. 42 (2009), pp.866-872.

[5] P. B. John and R. B. Lauren: Sensitivity of RBF interpolation on an otherwise uniform grid with a point omitted or slightly shifted. Appl. Numer. Math. Forum Vol. 60 (2010), pp.659-672.

DOI: 10.1016/j.apnum.2009.08.009

[6] Z. Zhihua, W. Jianxin and T. Wei: Ensembling neural networks: Many could be better than all. Artif. Intell. Forum Vol. 137 (2002), pp.239-263.

DOI: 10.1016/s0004-3702(02)00190-x

[7] E. Iakes, B. Lisa, F. Piero, C. Rita, V. Alfonso and L. T. Michael: Progress and challenges in pre- dicting protein-protein interaction sites. Brief. Bioinform. Forum Vol. 10 (2009), pp.233-246.

[8] L. Yang, T. Zhengquan and W. Yifei in: SVM-based protein interaction sites prediction. Techni- cal report, Shanghai University (2006).

[9] Information on ftp: /ftp. ebi. ac. uk/pub/databases/hssp.

[10] L. Chun and Q. Weiyi: Mathematical description of biological macromolecules and its applicat- ion. (Dalian University of Technology Press, Liaoning 2009).

[11] J. Mihel, M. Sikic, S. Tomic, B. Jeren and K. Vlahovicek: PSAIA-Protein Structure and Interact- ion Analyzer. BMC. Struct. Biol. Forum Vol. 8 (2008), p.21.

DOI: 10.1186/1472-6807-8-21

[12] M. Wei,W. Feifei and P. Xinjun: Prediction of Protein-Protein Interaction Sites Using Support Vector Machine. J. App. Scie. Forum Vol. 26 (2008), pp.403-408.

[13] Z. Huanxiang and S. Yibing: Prediction of Protein Interaction Sites From Sequence Profile and Residue Neighbor List. Proteins. Forum Vol. 44 (2001), pp.336-343.

DOI: 10.1002/prot.1099

[14] E. Mohammed and S. K. Mohamed: PSO Bounds: A New Hybridization Technique of PSO and EDAs. Stud. Comp. Intell. Forum Vol. 203 (2009), pp.509-526.