Meta-predictors make predictions by organizing and processing the predictions produced by several other predictors in a defined problem domain. A proficient meta-predictor not only offers better predicting performance than the individual predictors from which it is constructed, but it also relieves experimentally researchers from making difficult judgments when faced with conflicting results made by multiple prediction programs. We examined meta-predicting strategies for the serine/threonine phosphorylation site prediction problem, and developed a generalized weighted voting meta-predicting strategy with parameters determined by restricted grid search. Meta-predictors constructed with this strategy possess performance exceeding that of all individual predictors in predicting phosphorylation sites of major serine/threonine kinase families – CDK, CK2, PKA, and PKC. We have established this web server with the implementation of these meta-predictors.
Questions and comments please direct to firstname.lastname@example.org.