KAUST DepartmentComputational Bioscience Research Center (CBRC)
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
KAUST Grant NumberURF/1/1976-04
Permanent link to this recordhttp://hdl.handle.net/10754/622304
MetadataShow full item record
AbstractThe protein structure classification problem, which is to assign a protein structure to a cluster of similar proteins, is one of the most fundamental problems in the construction and application of the protein structure space. Early manually curated protein structure classifications (e.g., SCOP and CATH) are very successful, but recently suffer the slow updating problem because of the increased throughput of newly solved protein structures. Thus, fully automatic methods to cluster proteins in the protein structure space have been designed and developed. In this study, we observed that the SCOP superfamilies are highly consistent with clustering trees representing hierarchical clustering procedures, but the tree cutting is very challenging and becomes the bottleneck of clustering accuracy. To overcome this challenge, we proposed a novel density-based K-nearest uphill clustering method that effectively eliminates noisy pairwise protein structure similarities and identifies density peaks as cluster centers. Specifically, the density peaks are identified based on K-nearest uphills (i.e., proteins with higher densities) and K-nearest neighbors. To our knowledge, this is the first attempt to apply and develop density-based clustering methods in the protein structure space. Our results show that our density-based clustering method outperforms the state-of-the-art clustering methods previously applied to the problem. Moreover, we observed that computational methods and human experts could produce highly similar clusters at high precision values, while computational methods also suggest to split some large superfamilies into smaller clusters. © 2016 Elsevier B.V.
CitationCui X, Gao X (2017) K-nearest uphill clustering in the protein structure space. Neurocomputing 220: 52–59. Available: http://dx.doi.org/10.1016/j.neucom.2016.04.065.
SponsorsThis publication is based upon work supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No URF/1/1976-04. This research made use of the resources of the computer clusters at King Abdullah University of Science and Technology (KAUST).