PON-BTK is a method for classifying variations in the kinase domain of Bruton tyrosine kinase (BTK) related to X-linked agammaglobulinemia (XLA) to disease-causing and harmful. The method is using the semi-supervised classification method 'upclass'. It uses an expectation maximization (EM) algorithm to obtain maximum likelihood estimates of the model parameters and classifications for the unlabeled data. The PON-P probabilities of pathogenicity were obtained directly from PON-P output and the consensus pathogenicity is the proportion of pathogenic predictions of the methods having Matthews correlation coefficient (MCC) > 0.5. The precalculated results (see below) include in addition to the PON-BTK prediction also other information about the variants.
Jouni Väliaho, Imrul Faisal, Csaba Ortutay, C. I. Edvard Smith and Mauno Vihinen, 2015.
Characterization of all possible single nucleotide change-caused amino acid substitutions in the kinase domain of Bruton tyrosine kinase.
Hum Mutat. 2015 Mar 16. doi: 10.1002/humu.22791