We present a set of novel algorithms, called CaMELS (CalModulin intEraction Learning System) for predicting both the binding sites and the possibility of interactions of proteins with Calmodulin (CaM) using sequence information alone. The proposed algorithms give state of the art classification results and are available as a cloud based webserver. You can use it to make predictions for proteins of your interest.
If you use CaMELS please cite: Wajid Arshad Abbasi, Amina Asif, Saiqa Andleeb and Fayyaz-ul-Amir Afsar Minhas (2017), "CaMELS: In silico Prediction of Calmodulin Binding Proteins and their Binding Sites", Proteins: Structure, Function, and Bioinformatics, 85(9), 1724-1740. DOI: 10.1002/prot.25330.
(One letter code sequence length>21 required)
The interaction prediction model predicts the chances of a protein to interact with Calmodulin. This model generates a score for the protein which shows the propensity of the protein to interact with Calmodulin. Please not that this score is not the probability value for interaction. Guidelines to interpret the score the interaction prediction model can be taken from the following figure.
The binding site prediction model predicts the most likely region in the protein that is involved in its interaction with Calmodulin. This region can be identified based on the values of the discriminant function for the window centered at the residues of the region. Guidelines to interpret the output of the binding site prediction model can be taken from the following figure.