Title: A novel approach to knowledge discovery and representation in biological databases

Authors: Jing Lu; Cuiqing Wang; Malcolm Keech

Addresses: Winchester Business School, West Downs Campus, University of Winchester, Winchester SO22 5HT, Hampshire, UK ' Faculty of Computer Science and Technology, Shenyang University of Chemical Technology, Shenyang 110142, Liaoning, China ' Faculty of Creative Arts, Technologies and Science, University of Bedfordshire, Luton LU1 3JU, Bedfordshire, UK

Abstract: Extraction of motifs from biological sequences is among the frontier research issues in bioinformatics, with sequential patterns mining becoming one of the most important computational techniques in this area. A number of applications motivate the search for more structured patterns and concurrent protein motif mining is considered here. This paper builds on the concept of structural relation patterns and applies the concurrent sequential patterns (ConSP) mining approach to biological databases. Specifically, an original method is presented using support vectors as the data structure for the extraction of novel patterns in protein sequences. Data modelling is pursued to represent the more interesting concurrent patterns visually. Experiments with real-world protein datasets from the UniProt and NCBI databases highlight the applicability of the ConSP methodology in protein data mining and modelling. The results show the potential for knowledge discovery in the field of protein structure identification. A pilot experiment extends the methodology to DNA sequences to indicate a future direction.

Keywords: bioinformatics; biological databases; concurrent vector method; data analytics; DNA sequences; graphical modelling; knowledge discovery; protein motif mining; sequential patterns post-processing; structural relations.

DOI: 10.1504/IJBRA.2017.087384

International Journal of Bioinformatics Research and Applications, 2017 Vol.13 No.4, pp.352 - 375

Received: 02 Mar 2016
Accepted: 24 Aug 2016

Published online: 14 Oct 2017 *

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