Prediction of Calmodulin-Binding Proteins Using Short-Linear Motifs

Abstract

Prediction of Calmodulin-binding (CaM-binding) proteins plays a very important role in the fields of biology and biochemistry, because Calmodulin binds and regulates a multitude of protein targets affecting different cellular processes. Short linear motifs (SLiMs), on the other hand, have been effectively used as features for analyzing protein-protein interactions, though their properties have not been used in the prediction of CaM-binding proteins. In this study, we propose a new method for prediction of CaM-binding proteins based on both the total and average scores of SLiMs in protein sequences using a new scoring method, which we call Sliding Window Scoring (SWS) as features for the prediction. A dataset of 194 manually curated human CaM-binding proteins and 193 Mitochondrial proteins have been obtained and used for testing the proposed model. Multiple EM for Motif Elucidation (MEME) has been used to obtain new motifs from each of the positive and negative datasets individually (the SM approach) and from the combined negative and positive datasets (the CM approach). Moreover, the wrapper criterion with Random Forest for feature selection (FS) has been applied followed by classification using different algorithms such as k-nearest neighbor (k-NN), support vector machine (SVM), and Random Forest (RF), on a 3-fold cross-validation setup. Our proposed method shows promising prediction results and demonstrates how information contained in SLiMs is highly relevant for prediction of CaM-binding proteins.