Predicting Enzyme Class From Protein Structure Without Alignments Export

@article{Dobson2005, abstract = {Methods for predicting protein function from structure are becoming more important as the rate at which structures are solved increases more rapidly than experimental knowledge. As a result, protein structures now frequently lack functional annotations. The majority of methods for predicting protein function are reliant upon identifying a similar protein and transferring its annotations to the query protein. This method fails when a similar protein cannot be identified, or when any similar proteins identified also lack reliable annotations. Here, we describe a method that can assign function from structure without the use of algorithms reliant upon alignments. Using simple attributes that can be calculated from any crystal structure, such as secondary structure content, amino acid propensities, surface properties and ligands, we describe each enzyme in a non-redundant set. The set is split according to Enzyme Classification (EC) number. We combine the predictions of one-class versus one-class support vector machine models to make overall assignments of EC number to an accuracy of 35\% with the top-ranked prediction, rising to 60\% accuracy with the top two ranks. In doing so we demonstrate the utility of simple structural attributes in protein function prediction and shed light on the link between structure and function. We apply our methods to predict the function of every currently unclassified protein in the Protein Data Bank.}, address = {Department of Biomolecular Sciences, UMIST, P.O. Box 88, Manchester M60 1QD, UK.}, author = {Dobson, Paul D. and Doig, Andrew J.}, citeulike-article-id = {308879}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.jmb.2004.10.024}, citeulike-linkout-1 = {http://linkinghub.elsevier.com/retrieve/pii/S0022283604013166}, citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/15567421}, citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=15567421}, citeulike-linkout-4 = {http://www.sciencedirect.com/science/article/B6WK7-4DM22TY-1/1/f40ea9b82a93cec11832284ea0e3f6f3}, day = {07}, doi = {10.1016/j.jmb.2004.10.024}, issn = {00222836}, journal = {Journal of Molecular Biology}, keywords = {protein-function, protein-structure}, month = {January}, number = {1}, pages = {187--199}, posted-at = {2009-11-02 19:02:05}, priority = {4}, title = {Predicting Enzyme Class From Protein Structure Without Alignments}, url = {http://dx.doi.org/10.1016/j.jmb.2004.10.024}, volume = {345}, year = {2005} }

TY - JOUR ID - Dobson2005 L3 - citeulike-article-id:308879 N2 - Methods for predicting protein function from structure are becoming more important as the rate at which structures are solved increases more rapidly than experimental knowledge. As a result, protein structures now frequently lack functional annotations. The majority of methods for predicting protein function are reliant upon identifying a similar protein and transferring its annotations to the query protein. This method fails when a similar protein cannot be identified, or when any similar proteins identified also lack reliable annotations. Here, we describe a method that can assign function from structure without the use of algorithms reliant upon alignments. Using simple attributes that can be calculated from any crystal structure, such as secondary structure content, amino acid propensities, surface properties and ligands, we describe each enzyme in a non-redundant set. The set is split according to Enzyme Classification (EC) number. We combine the predictions of one-class versus one-class support vector machine models to make overall assignments of EC number to an accuracy of 35% with the top-ranked prediction, rising to 60% accuracy with the top two ranks. In doing so we demonstrate the utility of simple structural attributes in protein function prediction and shed light on the link between structure and function. We apply our methods to predict the function of every currently unclassified protein in the Protein Data Bank. IS - 1 JF - Journal of Molecular Biology SN - 00222836 AD - Department of Biomolecular Sciences, UMIST, P.O. Box 88, Manchester M60 1QD, UK. EP - 199 TI - Predicting Enzyme Class From Protein Structure Without Alignments VL - 345 SP - 187 KW - protein-function KW - protein-structure AU - Dobson, Paul AU - Doig, Andrew PY - 2005/01/07/ UR - http://dx.doi.org/10.1016/j.jmb.2004.10.024 ER -