Title: Dimensional reduction in the protein secondary structure prediction: non-linear method improvements

Authors: Gisele M. Simas, Silvia S.C. Botelho, Rafael G. Colares, Renan R. Almeida

Addresses: Fundacao Universidade Federal do Rio Grande do Sul (FURG), Av. Italia Km 8 – 96.200-090 – Rio Grande – RS – Brazil. ' Fundacao Universidade Federal do Rio Grande do Sul (FURG), Av. Italia Km 8 – 96.200-090 – Rio Grande – RS – Brazil. ' Fundacao Universidade Federal do Rio Grande do Sul (FURG), Av. Italia Km 8 – 96.200-090 – Rio Grande – RS – Brazil. ' Fundacao Universidade Federal do Rio Grande do Sul (FURG), Av. Italia Km 8 – 96.200-090 – Rio Grande – RS – Brazil

Abstract: This paper investigates the use of a dimensional reduction method, called cascaded non-linear components analysis (C-NLPCA), in the protein secondary structure prediction problem. C-NLPCA treats dimensional reductions considering the non-linearity of the data. In order to prove the effectiveness of the C-NLPCA, a set of tests are presented, comparing our approach with other existing predictors. The C-NLPCA is revealed to be efficient, propelling a new field of research.

Keywords: cascaded nonlinear component analysis; C-NLPCA; nonlinear dimensional reduction; protein secondary structure prediction; neural networks; ANNs; bioinformatics.

DOI: 10.1504/IJCIBSB.2010.038219

International Journal of Computational Intelligence in Bioinformatics and Systems Biology, 2010 Vol.1 No.4, pp.383 - 401

Published online: 23 Jan 2011 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article