Colander: A Probability-Based Support Vector Machine Algorithm for Automatic Screening for CID Spectra of Phosphopeptides Prior to Database Search

@article{citeulike:2906756, abstract = {Abstract: We developed a probability-based machine-learning program, Colander, to identify tandem mass spectra that are highly likely to represent phosphopeptides prior to database search. We identified statistically significant diagnostic features of phosphopeptide tandem mass spectra based on ion trap CID MS/MS experiments. Statistics for the features are calculated from 376 validated phosphopeptide spectra and 376 nonphosphopeptide spectra. A probability-based support vector machine (SVM) program, Colander, was then trained on five selected features. Data sets were assembled both from LC/LC-MS/MS analyses of large-scale phosphopeptide enrichments from proteolyzed cells, tissues and synthetic phosphopeptides. These data sets were used to evaluate the capability of Colander to select pS/pT-containing phosphopeptide tandem mass spectra. When applied to unknown tandem mass spectra, Colander can routinely remove 80\% of tandem mass spectra while retaining 95\% of phosphopeptide tandem mass spectra. The program significantly reduced computational time spent on database search by 6090\%. Furthermore, prefiltering tandem mass spectra representing phosphopeptides can increase the number of phosphopeptide identifications under a predefined false positive rate.}, address = {Department of Chemical Physiology, SR-11, The Scripps Research Institute, La Jolla, California 92037}, author = {Lu, Bingwen and Ruse, Cristian I. and Yates, John R. }, citeulike-article-id = {2906756}, doi = {http://dx.doi.org/10.1021/pr8001194}, journal = {J. Proteome Res.}, keywords = {bioinformatics, cid, database, machine-learning, mass-spec, phosphopeptides, svm}, month = {June}, posted-at = {2008-06-19 09:10:38}, priority = {2}, title = {Colander: A Probability-Based Support Vector Machine Algorithm for Automatic Screening for CID Spectra of Phosphopeptides Prior to Database Search}, url = {http://dx.doi.org/10.1021/pr8001194}, year = {2008} }

TY - JOUR ID - citeulike:2906756 L3 - citeulike-article-id:2906756 TI - Colander: A Probability-Based Support Vector Machine Algorithm for Automatic Screening for CID Spectra of Phosphopeptides Prior to Database Search JF - J. Proteome Res. AD - Department of Chemical Physiology, SR-11, The Scripps Research Institute, La Jolla, California 92037 N2 - Abstract: We developed a probability-based machine-learning program, Colander, to identify tandem mass spectra that are highly likely to represent phosphopeptides prior to database search. We identified statistically significant diagnostic features of phosphopeptide tandem mass spectra based on ion trap CID MS/MS experiments. Statistics for the features are calculated from 376 validated phosphopeptide spectra and 376 nonphosphopeptide spectra. A probability-based support vector machine (SVM) program, Colander, was then trained on five selected features. Data sets were assembled both from LC/LC-MS/MS analyses of large-scale phosphopeptide enrichments from proteolyzed cells, tissues and synthetic phosphopeptides. These data sets were used to evaluate the capability of Colander to select pS/pT-containing phosphopeptide tandem mass spectra. When applied to unknown tandem mass spectra, Colander can routinely remove 80% of tandem mass spectra while retaining 95% of phosphopeptide tandem mass spectra. The program significantly reduced computational time spent on database search by 6090%. Furthermore, prefiltering tandem mass spectra representing phosphopeptides can increase the number of phosphopeptide identifications under a predefined false positive rate. KW - bioinformatics KW - cid KW - database KW - machine-learning KW - mass-spec KW - phosphopeptides KW - svm AU - Lu, Bingwen AU - Ruse, Cristian AU - Yates, John PY - 2008/06/19/ UR - http://dx.doi.org/10.1021/pr8001194 ER -