Title: Improved protein fold assignment using support vector machines
Authors: Robert E. Langlois, Alice Diec, Ognjen Perisic, Yang Dai, Hui Lu
Addresses: Department of Bioengineering, University of Illinois at Chicago, IL 60607, USA. ' Department of Bioengineering, University of Illinois at Chicago, IL 60607, USA. ' Department of Bioengineering, University of Illinois at Chicago, IL 60607, USA. ' Department of Bioengineering, University of Illinois at Chicago, IL 60607, USA. ' Department of Bioengineering, University of Illinois at Chicago, IL 60607, USA
Abstract: Because of the relatively large gap of knowledge between number of protein sequences and protein structures, the ability to construct a computational model predicting structure from sequence information has become an important area of research. The knowledge of a protein|s structure is crucial in understanding its biological role. In this work, we present a support vector machine based method for recognising a protein|s fold from sequence information alone, where this sequence has less similarity with sequences of known structures. We have focused on improving multi-class classification, parameter tuning, descriptor design, and feature selection. The current implementation demonstrates better prediction accuracy than previous similar approaches, and has similar performance when compared with straightforward threading.
Keywords: fold recognition; support vector machines; machine learning; proteomics; structure prediction; bioinformatics; protein fold assignment; protein sequences; protein structures.
DOI: 10.1504/IJBRA.2005.007909
International Journal of Bioinformatics Research and Applications, 2005 Vol.1 No.3, pp.319 - 334
Published online: 30 Sep 2005 *
Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article