Towards the Improved Discovery and Design of Functional Peptides: Common Features of Diverse Classes Permit Generalized Prediction of Bioactivity

Catherine Mooney,Niall J Haslam,Denis C Shields,Gianluca Pollastri,Lukasz Kurgan

doi:10.1371/journal.pone.0045012

Abstract

The conventional wisdom is that certain classes of bioactive peptides have specific structural features that endow their particular functions. Accordingly, predictions of bioactivity have focused on particular subgroups, such as antimicrobial peptides. We hypothesized that bioactive peptides may share more general features, and assessed this by contrasting the predictive power of existing antimicrobial predictors as well as a novel general predictor, PeptideRanker, across different classes of peptides.We observed that existing antimicrobial predictors had reasonable predictive power to identify peptides of certain other classes i.e. toxin and venom peptides. We trained two general predictors of peptide bioactivity, one focused on short peptides (4–20 amino acids) and one focused on long peptides ( amino acids). These general predictors had performance that was typically as good as, or better than, that of specific predictors. We noted some striking differences in the features of short peptide and long peptide predictions, in particular, high scoring short peptides favour phenylalanine. This is consistent with the hypothesis that short and long peptides have different functional constraints, perhaps reflecting the difficulty for typical short peptides in supporting independent tertiary structure.We conclude that there are general shared features of bioactive peptides across different functional classes, indicating that computational prediction may accelerate the discovery of novel bioactive peptides and aid in the improved design of existing peptides, across many functional classes. An implementation of the predictive method, PeptideRanker, may be used to identify among a set of peptides those that may be more likely to be bioactive.

Highlights

Active, or bioactive, peptides encompass a wide range of activities across all kingdoms of life, and the available proteomes of many organisms represent a rich resource for the computational prediction of potential function of peptides encoded within them
Training a general predictor of peptide bioactivity In training PeptideRanker to predict bioactive peptides we reduced over-fitting by training and testing using five-fold crossvalidation with redundancy reduced datasets and by assessing the performance on two independent datasets
Our study identifies that bioactivity may be computationally predicted across diverse functional classes of bioactive peptides, and that long peptides are best treated as a separate class, compared to short peptides

Summary

Introduction

Active, or bioactive, peptides encompass a wide range of activities across all kingdoms of life, and the available proteomes of many organisms represent a rich resource for the computational prediction of potential function of peptides encoded within them. New antibiotic drugs are needed urgently to address the problem of bacterial resistance [1] and bioactive peptides may provide an answer [2,3]. They may serve as leads for drug design, or in certain circumstances be themselves used as therapeutics. The identification of food, especially milk, derived bioactive peptides is a growing research area. With bioactive peptides showing such potential as new therapeutics, nutraceuticals and functional food ingredients, the discovery and prediction of new bioactive peptides is an increasingly valuable research area

Methods

Results

Conclusion