Q1VarPred is data-derived tool for predicting functional impact of variants (amino acid substitutions) of the KCNQ1 potassium channel. The underlying model of Q1VarPred is a neural network with two predictors and one hidden layer of 3 neurons.
It was designed to predict functional impact at the molecular level and thus was trained on 107 functionally validated (in vitro electrophysiological study) KCNQ1 variants. The output of Q1VarPred is a label and the corresponding probability of the variant being dysfunctional. Please note that Q1VarPred prediction only serves as complementary "computational evidence" for channel functionality at the molecular level.
Instead of using the server, you can also
view or
download all mutations for the full sequence. If you find this server useful in your research, please cite Li, et. al. 2017. Circ Cardiovasc Genet
full text link. Wild type residues are based off the
canonical 676 residue human KCNQ1 sequence.