Prediction of Carbohydrate-Binding Proteins from Sequences Using Support Vector Machines

Abstract

Carbohydrate-binding proteins are proteins that can interact with sugar chains but do not modify them. They are involved in many physiological functions, and we have developed a method for predicting them from their amino acid sequences. Our method is based on support vector machines (SVMs). We first clarified the definition of carbohydrate-binding proteins and then constructed positive and negative datasets with which the SVMs were trained. By applying the leave-one-out test to these datasets, our method delivered 0.92 of the area under the receiver operating characteristic (ROC) curve. We also examined two amino acid grouping methods that enable effective learning of sequence patterns and evaluated the performance of these methods. When we applied our method in combination with the homology-based prediction method to the annotated human genome database, H-invDB, we found that the true positive rate of prediction was improved.

De novo prediction of the genomic components and capabilities for microbial plant biomass degradation from (meta-)genomes

“…SVM classification was used by Yosef et al [18] for predicting plasma lipid levels in baboons based on single nucleotide polymorphism data. In Someya et al [19], SVMs were used to predict carbohydrate-binding proteins from amino acid sequences. The SVM [20,21] is a discriminative learning method that infers, in a supervised fashion, the relationship between input features (such as the distribution of conserved gene clusters or single nucleotide polymorphisms across a set of sequence samples) and a target variable, such as a certain phenotype, from labeled training data.…”

Bactericidal activity against meticillin-resistant Staphylococcus aureus of a novel eukaryotic therapeutic recombinant antimicrobial peptide

“…CBDs are domains that can interact with sugar chains but do not modify them [16]. Therefore, it is a potential method for biological activity of AMPs to combine them with a CBD.…”

Protein–RNA and protein–glycan recognitions in light of amino acid codes

“…Currently, we have a number of methods for the biochemical identification of the protein-glycan interactome for defined glycans and for the identification of the protein-glycan interactome for specific proteins [40]. The biochemical and structural properties of identified proteins are effectively processed into informative models for the prediction and mapping of GBPs [43][44][45][46]. The same approach as for protein-RNA recognition is applied for protein-glycan recognition.…”