Abstract
Motivation: Calmodulin (CaM) is a ubiquitously conserved protein that acts as a calcium sensor, and interacts with a large number of proteins. Detection of CaM binding proteins and their interaction sites experimentally requires a significant effort, so accurate methods for their prediction are important.Results: We present a novel algorithm (MI-1 SVM) for binding site prediction and evaluate its performance on a set of CaM-binding proteins extracted from the Calmodulin Target Database. Our approach directly models the problem of binding site prediction as a large-margin classification problem, and is able to take into account uncertainty in binding site location. We show that the proposed algorithm performs better than the standard SVM formulation, and illustrate its ability to recover known CaM binding motifs. A highly accurate cascaded classification approach using the proposed binding site prediction method to predict CaM binding proteins in Arabidopsis thaliana is also presented.Availability: Matlab code for training MI-1 SVM and the cascaded classification approach is available on request.Contact: fayyazafsar@gmail.com or asa@cs.colostate.edu
Highlights
Calmodulin (CaM) is an intracellular calcium sensor protein that interacts with a large number of proteins to regulate their biological functions and exhibits sequence conservation across all eukaryotes (Bouche et al, 2005)
It can be noted that the accuracy of MI-1 Support Vector Machine (SVM) is noticeably better than multiple instance learning SVM (mi-SVM)
The improvement resulting from switching to a positiondependent feature representation is larger for MI-1 SVM than that observed in the case of mi-SVM
Summary
Calmodulin (CaM) is an intracellular calcium sensor protein that interacts with a large number of proteins to regulate their biological functions and exhibits sequence conservation across all eukaryotes (Bouche et al, 2005). This article presents a highly accurate computational approach that can identify the location of a CaM binding site in a protein solely on the basis of its amino acid sequence, helping avoid the significant effort of performing such experiments in the lab (Reddy et al, 2011). CaM binding sites are known to be contiguous in sequence, often occurring through an amphiphilic alpha helix (O’Neil and DeGrado, 1990). This makes CaM binding site prediction amenable to a sliding-window classification approach, as applied in recent work (Radivojac et al, 2006; Hamilton et al, 2011).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have