Prediction of kinase-specific phosphorylation sites using Conditional Random Fields. Export

@article{citeulike:3513919, abstract = {MOTIVATION: Phosphorylation is a crucial post-translational protein modification mechanism with important regulatory functions in biological systems. It is catalyzed by a group of enzymes called kinases, each of which recognizes certain target sites in its substrate proteins. Several authors have built computational models trained from sets of experimentally validated phosphorylation sites to predict these target sites for each given kinase. All of these models suffer from certain limitations, such as the fact that they do not take into account the dependencies between amino acid motifs within protein sequences in a global fashion. RESULTS: We propose a novel approach to predict phosphorylation sites from the protein sequence. The method uses a positive data set to train a Conditional Random Field (CRF) model. The negative training data set is used to specify the decision threshold corresponding to a desired false positive rate. Application of the method on experimentally verified benchmark phosphorylation data (Phospho.ELM) shows that it performs well compared to existing methods for most kinases. This is to our knowledge the first report of the use of Conditional Random Fields to predict post-translational modification sites in protein sequences. AVAILABILITY: The source code of the implementation, called CRPhos, is available from http://www.ptools.ua.ac.be/CRPhos/ Contacts: kris.laukens@ua.ac.be Suplementary Information: http://www.ptools.ua.ac.be/CRPhos/}, author = {Dang, Thanh Hai H. and Leemput, Koenraad Van V. and Verschoren, Alain and Laukens, Kris}, citeulike-article-id = {3513919}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btn546}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/24/24/2857?rss=1}, citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/18940828}, citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=18940828}, day = {20}, doi = {10.1093/bioinformatics/btn546}, issn = {1460-2059}, journal = {Bioinformatics (Oxford, England)}, keywords = {conditional, fields, random}, month = {October}, posted-at = {2009-01-10 00:48:29}, priority = {2}, title = {Prediction of kinase-specific phosphorylation sites using Conditional Random Fields.}, url = {http://dx.doi.org/10.1093/bioinformatics/btn546}, year = {2008} }

TY - JOUR ID - citeulike:3513919 L3 - citeulike-article-id:3513919 N2 - MOTIVATION: Phosphorylation is a crucial post-translational protein modification mechanism with important regulatory functions in biological systems. It is catalyzed by a group of enzymes called kinases, each of which recognizes certain target sites in its substrate proteins. Several authors have built computational models trained from sets of experimentally validated phosphorylation sites to predict these target sites for each given kinase. All of these models suffer from certain limitations, such as the fact that they do not take into account the dependencies between amino acid motifs within protein sequences in a global fashion. RESULTS: We propose a novel approach to predict phosphorylation sites from the protein sequence. The method uses a positive data set to train a Conditional Random Field (CRF) model. The negative training data set is used to specify the decision threshold corresponding to a desired false positive rate. Application of the method on experimentally verified benchmark phosphorylation data (Phospho.ELM) shows that it performs well compared to existing methods for most kinases. This is to our knowledge the first report of the use of Conditional Random Fields to predict post-translational modification sites in protein sequences. AVAILABILITY: The source code of the implementation, called CRPhos, is available from http://www.ptools.ua.ac.be/CRPhos/ Contacts: kris.laukens@ua.ac.be Suplementary Information: http://www.ptools.ua.ac.be/CRPhos/ JF - Bioinformatics (Oxford, England) SN - 1460-2059 TI - Prediction of kinase-specific phosphorylation sites using Conditional Random Fields. KW - conditional KW - fields KW - random AU - Dang, Thanh Hai AU - Leemput, Koenraad Van AU - Verschoren, Alain AU - Laukens, Kris PY - 2008/10/20/ UR - http://dx.doi.org/10.1093/bioinformatics/btn546 ER -