Prediction of human protein kinase substrate specificities

In this paper we propose a new algorithm to predict the phosphorylation site specificities of 478 human protein kinases based on the primary structures of the catalytic domains of these enzymes. Existing methods deduce the specificity of a protein kinase through the alignment of the amino acid sequences of phospho-sites targeted by the kinase to generate a consensus sequence or they use machine learning models for recognition. However, for most protein kinases few if any substrates have been experimentally identified by protein sequencing and mass spectrometry. In this work, we used mutual information from a training set of over 200 protein kinases consensus phospho-site sequences and predicted amino acid interactions between kinases and their substrate phospho-sites to generate position-specific scoring matrices (PSSM). The results demonstrate that using our algorithm, knowledge of the primary amino acid sequence of the catalytic domain of these kinases is sufficient to predict their phosphorylation sites specificities and their PSSM matrices.