Prediction of antimicrobial activity of peptides using relational machine learning

We apply relational machine learning techniques to predict antimicrobial activity of peptides. We follow our successful strategy (Szabóová et al., MLSB 2010) to prediction of DNA-binding propensity of proteins from structural features. We exploit structure prediction methods to obtain peptides' spatial structures, then we construct the structural relational features. We use these relational features as attributes in a regression model. We apply this methodology to antimicrobial activity prediction of peptides achieving better predictive accuracies than a state-of-the-art approach.