Prediction of beta-turns in proteins from multiple alignment using neural network.

Kaur, Harpreet and Raghava, G.P.S. (2003) Prediction of beta-turns in proteins from multiple alignment using neural network. Protein science : a publication of the Protein Society, 12 (3). pp. 627-34. ISSN 0961-8368

PDF raghava2002.3.pdf - Published Version Restricted to Registered users only Download (239Kb) | Request a copy

Abstract

A neural network-based method has been developed for the prediction of beta-turns in proteins by using multiple sequence alignment. Two feed-forward back-propagation networks with a single hidden layer are used where the first-sequence structure network is trained with the multiple sequence alignment in the form of PSI-BLAST-generated position-specific scoring matrices. The initial predictions from the first network and PSIPRED-predicted secondary structure are used as input to the second structure-structure network to refine the predictions obtained from the first net. A significant improvement in prediction accuracy has been achieved by using evolutionary information contained in the multiple sequence alignment. The final network yields an overall prediction accuracy of 75.5% when tested by sevenfold cross-validation on a set of 426 nonhomologous protein chains. The corresponding Q(pred), Q(obs), and Matthews correlation coefficient values are 49.8%, 72.3%, and 0.43, respectively, and are the best among all the previously published beta-turn prediction methods. The Web server BetaTPred2 (http://www.imtech.res.in/raghava/betatpred2/) has been developed based on this approach.

Item Type:	Article
Additional Information:	Copyright of this article belongs to Wiley. Supplemental material: See www.proteinscience.org.
Uncontrolled Keywords:	�-Turns; prediction; neural networks; multiple alignment; secondary structure; Web server
Subjects:	Q Science > QR Microbiology
Depositing User:	Dr. K.P.S.Sengar
Date Deposited:	05 Jan 2012 15:05
Last Modified:	05 Jan 2012 15:05
URI:	http://crdd.osdd.net/open/id/eprint/252

Actions (login required)

View Item