Discovery of spatially cohesive itemsets in three-dimensional protein structuresDiscovery of spatially cohesive itemsets in three-dimensional protein structures
Faculty of Sciences. Mathematics and Computer Science
Advanced Database Research and Modeling (ADReM)
Department of Mathematics - Computer Sciences
2014New York, N.Y., 2014
IEEE/ACM transactions on computational biology and bioinformatics / Institute of Electrical and Electronics Engineers [New York, N.Y.] - New York, N.Y.
11(2014):5, p. 814-825
University of Antwerp
In this paper we present a cohesive structural itemset miner aiming to discover interesting patterns in a set of data objects within a multidimensional spatial structure by combining the cohesion and the support of the pattern. We propose two ways to build the itemset miner, VertexOne and VertexAll, in an attempt to find a balance between accuracy and run-times. The experiments show that VertexOne performs better, and finds almost the same itemsets as VertexAll in a much shorter time. The usefulness of the method is demonstrated by applying it to find interesting patterns of amino acids in spatial proximity within a set of proteins based on their atomic coordinates in the protein molecular structure. Several patterns found by the cohesive structural itemset miner contain amino acids that frequently co-occur in the spatial structure, even if they are distant in the primary protein sequence and only brought together by protein folding. Further various indications were found that some of the discovered patterns seem to represent common underlying support structures within the proteins.