BCL::KinasePred Server
Discovery of selective inhibitors of biological target proteins is the primary goal of many drug discovery campaigns. However, this goal has proven elusive, especially for inhibitors targeting the well-conserved orthosteric ATP binding pocket of kinase enzymes. The human kinome is large and it is rather difficult to profile early lead compounds against around 500 targets to gain an upfront knowledge on selectivity. Further, selectivity can change drastically during derivatization of an initial lead compound. Here we have introduce a computational model to support the profiling of compounds early in the drug discovery pipeline. Based on the extensive profiled activity of 70 kinase inhibitors against 379 kinases including 81 tyrosine kinases, we developed a quantitative structure activity relation model using artificial neural networks to predict the activity of these kinase inhibitors against the panel of 379 kinases. The model performance in predicting activity against ranges from area under the curve of the receiver operating characteristics of 0.6 to 0.8 depending on the kinase. The work highlights room for improving prediction accuracy of kinase selectivity.
Files are limited to 4MB in size; if you are a Meiler-Lab member, please login to upload files up to 16MB
* tooltip
Input the molecule in sdf format here
Javascript-enabled users can draw molecules instead of uploading sdfs

Or browse for a file with one of these extensions: .sdf or .mdl
tooltip