Spectral clustering of protein sequences.

@article{citeulike:707221, abstract = {An important problem in genomics is automatically clustering homologous proteins when only sequence information is available. Most methods for clustering proteins are local, and are based on simply thresholding a measure related to sequence distance. We first show how locality limits the performance of such methods by analysing the distribution of distances between protein sequences. We then present a global method based on spectral clustering and provide theoretical justification of why it will have a remarkable improvement over local methods. We extensively tested our method and compared its performance with other local methods on several subsets of the SCOP (Structural Classification of Proteins) database, a gold standard for protein structure classification. We consistently observed that, the number of clusters that we obtain for a given set of proteins is close to the number of superfamilies in that set; there are fewer singletons; and the method correctly groups most remote homologs. In our experiments, the quality of the clusters as quantified by a measure that combines sensitivity and specificity was consistently better [on average, improvements were 84\% over hierarchical clustering, 34\% over Connected Component Analysis (CCA) (similar to GeneRAGE) and 72\% over another global method, TribeMCL].}, address = {Bioinformatics Group, The Genome Centre, Barts and The London School of Medicine, Queen Mary, University of London, Charterhouse Square, London EC1M 6BQ, UK. albertopaccanaro@yale.edu}, author = {Paccanaro, A. and Casbon, J. A. and Saqi, M. A. }, citeulike-article-id = {707221}, issn = {1362-4962}, journal = {Nucleic Acids Res}, keywords = {sequence\_clustering}, number = {5}, pages = {1571--1580}, posted-at = {2008-05-07 19:12:12}, priority = {2}, title = {Spectral clustering of protein sequences.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/16547200}, volume = {34}, year = {2006} }

TY - JOUR ID - citeulike:707221 L3 - citeulike-article-id:707221 TI - Spectral clustering of protein sequences. JF - Nucleic Acids Res VL - 34 IS - 5 SP - 1571 EP - 1580 AD - Bioinformatics Group, The Genome Centre, Barts and The London School of Medicine, Queen Mary, University of London, Charterhouse Square, London EC1M 6BQ, UK. albertopaccanaro@yale.edu SN - 1362-4962 N2 - An important problem in genomics is automatically clustering homologous proteins when only sequence information is available. Most methods for clustering proteins are local, and are based on simply thresholding a measure related to sequence distance. We first show how locality limits the performance of such methods by analysing the distribution of distances between protein sequences. We then present a global method based on spectral clustering and provide theoretical justification of why it will have a remarkable improvement over local methods. We extensively tested our method and compared its performance with other local methods on several subsets of the SCOP (Structural Classification of Proteins) database, a gold standard for protein structure classification. We consistently observed that, the number of clusters that we obtain for a given set of proteins is close to the number of superfamilies in that set; there are fewer singletons; and the method correctly groups most remote homologs. In our experiments, the quality of the clusters as quantified by a measure that combines sensitivity and specificity was consistently better [on average, improvements were 84% over hierarchical clustering, 34% over Connected Component Analysis (CCA) (similar to GeneRAGE) and 72% over another global method, TribeMCL]. KW - sequence_clustering AU - Paccanaro, A AU - Casbon, JA AU - Saqi, MA PY - 2006/// UR - http://view.ncbi.nlm.nih.gov/pubmed/16547200 ER -