Cascading classifier application for topology prediction of transmembrane beta-barrel proteins

Kazemian, Hassan and Grimaldi, Cedric Maxime (2020) Cascading classifier application for topology prediction of transmembrane beta-barrel proteins. Journal of bioinformatics and computational biology. ISSN 1757-6334

Full text not available from this repository. (Request a copy)
Official URL: https://doi.org/10.1142/S0219720020500341

Abstract / Description

Membrane proteins are a major focus for new drug discovery. Transmembrane beta-barrel (TMB) proteins play key roles in the translocation machinery, pore formation, membrane anchoring and ion exchange. Given their key roles and the difficulty in membrane protein structure determination, the use of computational modeling is essential. This paper focuses on the topology prediction of TMB proteins. In the field of bioinformatics, many years of research has been spent on the topology prediction of transmembrane alpha-helices. The efforts to TMB proteins topology prediction have been overshadowed and the prediction accuracy could be improved with further research. Various methodologies have been developed in the past for the prediction of TMB protein topology, however, the use of cascading classifier has never been fully explored. This research presents a novel approach to TMB topology prediction with the use of a cascading classifier. The MATLAB computer simulation results show that the proposed methodology predicts TMB proteins topologies with high accuracy for randomly selected proteins. By using the cascading classifier approach, the best overall accuracy is 76.3% with a precision of 0.831 and recall or probability of detection of 0.799 for TMB topology prediction. The accuracy of 76.3% is achieved using a two-layers cascading classifier.

Item Type: Article
Additional Information: ** From PubMed via Jisc Publications Router
Uncontrolled Keywords: Support vector machine, [Formula: see text]-nearest neighbors, beta-barrel, cascading classifier, deep learning, neural networks, topology prediction
Subjects: 500 Natural Sciences and Mathematics > 510 Mathematics
Department: School of Computing and Digital Media
SWORD Depositor: Pub Router
Depositing User: Pub Router
Date Deposited: 13 Nov 2020 13:28
Last Modified: 13 Nov 2020 13:28
URI: http://repository.londonmet.ac.uk/id/eprint/6145

Actions (login required)

View Item View Item