Using maximum entropy model to predict protein secondary structure with single sequence

Ding, Y.-S., Zhang, T.-L., Gu, Q. , Zhao, P.-Y. and Chou, K.-C. (2009) Using maximum entropy model to predict protein secondary structure with single sequence. Protein and Peptide Letters, 16(5), pp. 552-560. (doi: 10.2174/092986609788167833) (PMID:19442235)

Full text not currently available from Enlighten.

Abstract

Prediction of protein secondary structure is somewhat reminiscent of the efforts by many previous investigators but yet still worthy of revisiting it owing to its importance in protein science. Several studies indicate that the knowledge of protein structural classes can provide useful information towards the determination of protein secondary structure. Particularly, the performance of prediction algorithms developed recently have been improved rapidly by incorporating homologous multiple sequences alignment information. Unfortunately, this kind of information is not available for a significant amount of proteins. In view of this, it is necessary to develop the method based on the query protein sequence alone, the so-called single-sequence method. Here, we propose a novel single-sequence approach which is featured by that various kinds of contextual information are taken into account, and that a maximum entropy model classifier is used as the prediction engine. As a demonstration, cross-validation tests have been performed by the new method on datasets containing proteins from different structural classes, and the results thus obtained are quite promising, indicating that the new method may become an useful tool in protein science or at least play a complementary role to the existing protein secondary structure prediction methods.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Gu, Dr Quan
Authors: Ding, Y.-S., Zhang, T.-L., Gu, Q., Zhao, P.-Y., and Chou, K.-C.
Subjects:Q Science > QH Natural history > QH301 Biology
College/School:College of Medical Veterinary and Life Sciences > School of Infection & Immunity
College of Medical Veterinary and Life Sciences > School of Infection & Immunity > Centre for Virus Research
Journal Name:Protein and Peptide Letters
Publisher:Bentham Science Publishers
ISSN:0929-8665
ISSN (Online):1875-5305

University Staff: Request a correction | Enlighten Editors: Update this record