Help! Try using the key arrows in your keyboard or the buttons below to switch among the tips below.
Kinact is a novel computational method for predicting activating mutations in kinases. It is a machine learning approach that relies on structural and sequence data of proteins, such as environment residue, stability changes predictions, atomic interactions, graph-based signatures and residue conservation.
Such a predictive model is not only of great relevance for antibody engineering and development, but would also allow the prediction of biologically relevant mutations when investigating diseases, such as cancer.
To run a prediction:
The results for a single mutation will be displayed once computations are completed.
For this analysis one have to click on the "Interatomic Interactions of Wild-Type Residue" bar to open the panel with the interactive 3D viewer.
For this analysis one have to click on the "Conservation within Homologue Group of Kinases" bar to open the panel with the interactive 3D viewer.
For this analysis one have to click on the "Multiple Sequence Alignment within Homologue Group of Kinases" bar to open the panel with the Multiple Sequence Alignment.
Your results for a list of mutations will be displayed in a table format with the following information:
In case you experience any trouble using Kinact or have any suggestions or comments, please do not hesitate in contacting us either via e-mail (1) or through the online form (2) .