Comprehensive comparative analysis and identification of RNA-binding protein domains: Multi-class classification and feature selection

► We did a multi-class prediction of RNA-binding protein domains. ► We compared prediction accuracy of three different state-of-the-art predictor methods. ► We discovered dissimilar features using ℓ1/ℓq-regularized logistic regression. ► Our method could be applied to identify novel RNA-binding proteins with unique folds.