Prediction of phosphorylation sites using SVMs.

@article{Kim2004, abstract = {MOTIVATION: Phosphorylation is involved in diverse signal transduction pathways. By predicting phosphorylation sites and their kinases from primary protein sequences, we can obtain much valuable information that can form the basis for further research. Using support vector machines, we attempted to predict phosphorylation sites and the type of kinase that acts at each site. RESULTS: Our prediction system was limited to phosphorylation sites catalyzed by four protein kinase families and four protein kinase groups. The accuracy of the predictions ranged from 83 to 95\% at the kinase family level, and 76-91\% at the kinase group level. The prediction system used-PredPhospho-can be applied to the functional study of proteins, and can help predict the changes in phosphorylation sites caused by amino acid variations at intra- and interspecies levels.}, author = {Kim, Jong H. and Lee, Juyoung and Oh, Bermseok and Kimm, Kuchan and Koh, Insong }, citeulike-article-id = {2054436}, doi = {10.1093/bioinformatics/bth382}, journal = {Bioinformatics}, keywords = {algorithms, alignment, analysis, article-predikin, artificial, binding, chemical, computer, intelligence, models, molecular, phosphorylation, phosphotransferases, protein, proteins, relationship, sequence, simulation, sites, structure-activity}, month = {Nov}, number = {17}, pages = {3179--3184}, posted-at = {2007-12-04 03:22:13}, priority = {2}, title = {Prediction of phosphorylation sites using SVMs.}, url = {http://dx.doi.org/10.1093/bioinformatics/bth382}, volume = {20}, year = {2004} }

TY - JOUR ID - Kim2004 L3 - citeulike-article-id:2054436 TI - Prediction of phosphorylation sites using SVMs. JF - Bioinformatics VL - 20 IS - 17 SP - 3179 EP - 3184 N2 - MOTIVATION: Phosphorylation is involved in diverse signal transduction pathways. By predicting phosphorylation sites and their kinases from primary protein sequences, we can obtain much valuable information that can form the basis for further research. Using support vector machines, we attempted to predict phosphorylation sites and the type of kinase that acts at each site. RESULTS: Our prediction system was limited to phosphorylation sites catalyzed by four protein kinase families and four protein kinase groups. The accuracy of the predictions ranged from 83 to 95\% at the kinase family level, and 76-91\% at the kinase group level. The prediction system used-PredPhospho-can be applied to the functional study of proteins, and can help predict the changes in phosphorylation sites caused by amino acid variations at intra- and interspecies levels. KW - algorithms KW - alignment KW - analysis KW - article-predikin KW - artificial KW - binding KW - chemical KW - computer KW - intelligence KW - models KW - molecular KW - phosphorylation KW - phosphotransferases KW - protein KW - proteins KW - relationship KW - sequence KW - simulation KW - sites KW - structure-activity AU - Kim, Jong AU - Lee, Juyoung AU - Oh, Bermseok AU - Kimm, Kuchan AU - Koh, Insong PY - 2004/Nov// UR - http://dx.doi.org/10.1093/bioinformatics/bth382 ER -