A novel approach to knowledge discovery and representation in biological databases

Jing Lu
,
Cuiqing Wang
,
Malcolm Keech

University of Winchester
,
Shenyang Institute of Chemical Technology

Research Output: Contribution to journal Article Peer-review

Open access

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.

Publication Information

Output type

Research Output: Contribution to journal Article Peer-review

Original language

English

Pages from-to (Number of pages)

Pages 352-375

Journal (Volume, Issue Number)

International Journal of Bioinformatics Research and Applications (Volume 13, Issue 4)

Publication milestones

Published - 25/09/2017

Publication status

Published - 25/09/2017

ISSN

1744-5485

External Publication IDs

handle.net: 10547/624500
Scopus: 85047054684

Access to documents

10.1504/IJBRA.2017.087384

296Lu_ANovelApproachToKnowledge..._item_296_original_deposit.pdf

Accepted author manuscript, 501.62 KB

License:CC BY-NC-ND