Decision tree based information integration for automated protein classification.

@article{citeulike:1058646, abstract = {We propose a novel technique for automatically generating the SCOP classification of a protein structure with high accuracy. We achieve accurate classification by combining the decisions of multiple methods using the consensus of a committee (or an ensemble) classifier. Our technique, based on decision trees, is rooted in machine learning which shows that by judicially employing component classifiers, an ensemble classifier can be constructed to outperform its components. We use two sequence- and three structure-comparison tools as component classifiers. Given a protein structure and using the joint hypothesis, we first determine if the protein belongs to an existing category (family, superfamily, fold) in the SCOP hierarchy. For the proteins that are predicted as members of the existing categories, we compute their family-, superfamily-, and fold-level classifications using the consensus classifier. We show that we can significantly improve the classification accuracy compared to the individual component classifiers. In particular, we achieve error rates that are 3-12 times less than the individual classifiers' error rates at the family level, 1.5-4.5 times less at the superfamily level, and 1.1-2.4 times less at the fold level.}, address = {Department of Computer Science, University of California at Santa Barbara, Santa Barbara, CA 93106, USA. orhan@cs.ucsb.edu}, author = {Camo\u{g}lu, O. and Can, T. and Singh, A. K. and Wang, Y. F. }, citeulike-article-id = {1058646}, issn = {0219-7200}, journal = {J Bioinform Comput Biol}, keywords = {decision\_tree}, month = {June}, number = {3}, pages = {717--742}, posted-at = {2007-01-22 06:52:39}, priority = {2}, title = {Decision tree based information integration for automated protein classification.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/16108091}, volume = {3}, year = {2005} }

TY - JOUR ID - citeulike:1058646 L3 - citeulike-article-id:1058646 TI - Decision tree based information integration for automated protein classification. JF - J Bioinform Comput Biol VL - 3 IS - 3 SP - 717 EP - 742 AD - Department of Computer Science, University of California at Santa Barbara, Santa Barbara, CA 93106, USA. orhan@cs.ucsb.edu SN - 0219-7200 N2 - We propose a novel technique for automatically generating the SCOP classification of a protein structure with high accuracy. We achieve accurate classification by combining the decisions of multiple methods using the consensus of a committee (or an ensemble) classifier. Our technique, based on decision trees, is rooted in machine learning which shows that by judicially employing component classifiers, an ensemble classifier can be constructed to outperform its components. We use two sequence- and three structure-comparison tools as component classifiers. Given a protein structure and using the joint hypothesis, we first determine if the protein belongs to an existing category (family, superfamily, fold) in the SCOP hierarchy. For the proteins that are predicted as members of the existing categories, we compute their family-, superfamily-, and fold-level classifications using the consensus classifier. We show that we can significantly improve the classification accuracy compared to the individual component classifiers. In particular, we achieve error rates that are 3-12 times less than the individual classifiers' error rates at the family level, 1.5-4.5 times less at the superfamily level, and 1.1-2.4 times less at the fold level. KW - decision_tree AU - Camoğlu, O AU - Can, T AU - Singh, AK AU - Wang, YF PY - 2005/06// UR - http://view.ncbi.nlm.nih.gov/pubmed/16108091 ER -