Application of Sparse Linear Discriminant Analysis for Prediction of Protein-Protein Interactions

• Autorzy: Katarzyna Stąpor , Piotr Fabian
• Języki publikacji: EN

Abstrakty

EN

Electronics and Computer Science To understand the complex cellular mechanisms involved in a biological system, it is necessary to study protein-protein interactions (PPIs) at the molecular level, in which prediction of PPIs plays a significant role. In this paper we propose a new classification approach based on the sparse discriminant analysis [10] to predict obligate (permanent) and non-obligate (transient) protein-protein interactions. The sparse discriminant analysis [10] circumvents the limitations of the classical discriminant analysis [4, 9] in the high dimensional low sample size settings by incorporating inherently the feature selection into the optimization procedure. To characterize properties of protein interaction, we proposed to use the binding free energies. The performance of our proposed classifier is 75% ± 5%. (original abstract)

Słowa kluczowe

EN

Discriminant analysis

PL

Analiza dyskryminacyjna

• Czasopismo: Information Systems in Management
• Rocznik: 2016
• Tom: 5
• Numer: nr 1
• Strony: 109--118

Twórcy

autor

Katarzyna Stąpor

• Silesian Technical University

autor

Piotr Fabian

• Silesian Technical University

Bibliografia

• [1] Berman H. et al. (2000) The Protein Data Bank. Nucleid Acid Research 28, 235-242.
• [2] Bordner A., Abagyan R. (2005) Statistical analysis and prediction of protein-protein interfaces. Proteins 60 (3), 353-366.
• [3] Camacho C., Zhang C. (2005) FastContact: rapid estimate of contact and binding free energies. Bioinformatics 21 (10), 2534-2536.
• [4] Fukunaga K. (1990) Introduction to statistical pattern recognition. New York: Academic Press.
• [5] Jones S., Thornton J.M. (1996) Principles of protein-protein interactions. Proc. Natl. Acad. Sci. USA 93(1), 13-20.
• [6] Marron J. et al. (2007) Distance-weighted discrimination. Journal of American Statistical Association, 102, 1267-1273.
• [7] Rueda L. et al. (2010) Biological protein-protein interaction prediction using binding free energies and linear dimensionality reduction. In: Dijkstra T., et al. (eds): PRIB 2010, LNBI 6282, 383-394, Springer Berlin.
• [8] Skrabanek L. et al. (2008) Computational prediction of protein-protein interactions. Molecular Biotechnology, 38(1), 1-17.
• [9] Stąpor K. (2011) Classification methods in computer vision. PWN Warszawa (in Polish).
• [10] Qiao Z., Zhou L., Huang J. (2009) Sparse linear discriminant analysis with applications to high dimensional low sample size data. IAENG Int. Journal of Applied Mathematics, 39, 1.
• [11] Zhou H., Shan Y. (2001) Prediction of protein-protein interaction sites from sequence profile and residue neighbor list. Proteins 44(3), 336-343.
• [12] Zhu H., et al. (2006) NoxClass: prediction of protein-protein interaction types. BMC Bioinformatics 7 (27).