Issue No.10 - Oct. (2013 vol.25)
David K.Y. Chiu , University of Guelph, Guelph
Thomas W.H. Lui , University of Guelph, Guelph
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TKDE.2012.151
In this research, we introduce a novel, complex associative pattern that is found to be very useful because it identifies the core associative structure from the data. We refer to it as nested high-order pattern. The pattern is more specific than associative patterns represented as multiple variables. It also generalizes sequential patterns, as the outcomes need not be contiguous. This paper outlines two search algorithms, the $(r)$-Tree and Best-$(k)$ algorithm in its detection. It was then applied to an analysis of biomolecule using the aligned sequence family of the molecule. In the SH3 protein, a model for protein-protein interaction mediator, we identify functional groups (core and binding sites) in the three-dimensional structure as well as amino acid patterns dominating certain species.
Algorithm design and analysis, Tin, Statistical analysis, Mutual information, Proteins, Educational institutions, Compounds, pattern analysis, Algorithm design and analysis, Tin, Statistical analysis, Mutual information, Proteins, Educational institutions, Compounds, bioinformatics, Classifier design and evaluation, data mining, granular computing
David K.Y. Chiu, Thomas W.H. Lui, "NHOP: A Nested Associative Pattern for Analysis of Consensus Sequence Ensembles", IEEE Transactions on Knowledge & Data Engineering, vol.25, no. 10, pp. 2314-2324, Oct. 2013, doi:10.1109/TKDE.2012.151