Optimal selection of molecular descriptors for antimicrobial peptides classification: an evolutionary feature weighting approach.

BACKGROUND: Antimicrobial peptides are a promising alternative for combating pathogens resistant to conventional antibiotics. Computer-assisted peptide discovery strategies are necessary to automatically assess a significant amount of data by generating models that efficiently classify what an antimicrobial peptide is, before its evaluation in the wet lab. Model's performance depends on the selection of molecular descriptors for which an efficient and effective approach has recently been proposed. Unfortunately, how to adapt this method to the selection of molecular descriptors for the classification of antimicrobial peptides and the performance it can achieve, have only preliminary been explored. RESULTS: We propose an adaptation of this successful feature selection approach for the weighting of molecular descriptors and assess its performance. The evaluation is conducted on six high-quality benchmark datasets that have previously been used for the empirical evaluation of state-of-art antimicrobial prediction tools in an unbiased manner. The results indicate that our approach substantially reduces the number of required molecular descriptors, improving, at the same time, the performance of classification with respect to using all molecular descriptors. Our models also outperform state-of-art prediction tools for the classification of antimicrobial and antibacterial peptides. CONCLUSIONS: The proposed methodology is an efficient approach for the development of models to classify antimicrobial peptides. Particularly in the generation of models for discrimination against a specific antimicrobial activity, such as antibacterial. One of our future directions is aimed at using the obtained classifier to search for antimicrobial peptides in various transcriptomes.

Towards an experimental classification system for membrane active peptides.

Mature proteins can act as potential sources of encrypted bioactive peptides that, once released from their parent proteins, might interact with diverse biomolecular targets. In recent work we introduced a systematic methodology to uncover encrypted intragenic antimicrobial peptides (IAPs) within large protein sequence libraries. Given that such peptides may interact with membranes in different ways, resulting in distinct observable outcomes, it is desirable to develop a predictive methodology to categorize membrane active peptides and establish a link to their physicochemical properties. Building upon previous work, we explored the interaction of a range of IAPs with model membranes probed by differential scanning calorimetry (DSC) and circular dichroism (CD) techniques. The biophysical data were submitted to multivariate statistical methods and resulting peptide clusters were correlated to peptide structure and to their antimicrobial activity. A re-evaluation of the physicochemical properties of the peptides was conducted based on peptide cluster memberships. Our data indicate that membranolytic peptides produce characteristic thermal transition (DSC) profiles in model vesicles and that this can be used to categorize novel molecules with unknown biological activity. Incremental expansion of the model presented here might result in a unified experimental framework for the prediction of novel classes of membrane active peptides.

Antimicrobial peptide elicitors: new hope for the post-antibiotic era.

Antimicrobial peptides or host defense peptides are fundamental components of human innate immunity. Recent and growing evidence suggests they have a role in a broad range of diseases, including cancer, allergies and susceptibility to infection, including HIV/AIDS. Antimicrobial peptide elicitors (APEs) are physical, biological or chemical agents that boost human antimicrobial peptide expression. The current knowledge of APEs and their potential use in the treatment of human infectious diseases are reviewed, and a classification system for APEs is proposed. The efficient use of APEs in clinical practice could mark the beginning of the urgently needed post-antibiotic era, but further trials assessing their efficacy and safety are required.

Antimicrobial peptides from marine invertebrates as a new frontier for microbial infection control.

Antimicrobial peptides are widely expressed in organisms and have been linked to innate and acquired immunities in vertebrates. These compounds are constitutively expressed and rapidly induced at different cellular levels to interact directly with infectious agents and/or modulate immunoreactions involved in defense against pathogenic microorganisms. In invertebrates, antimicrobial peptides represent the major humoral defense system against infection, showing a diverse spectrum of action mechanisms, most of them related to plasma membrane disturbance and lethal alteration of microbial integrity. Marine invertebrates are widespread, extremely diverse, and constantly under an enormous microbial challenge from the ocean environment, itself altered by anthropic influences derived from industrialization and transportation. Consequently, this study reexamines the peptides isolated over the past 2 decades from different origins, bringing phyla not previously reviewed up to date. Moreover, a promising novel use of antimicrobial peptides as effective drugs in human and veterinary medicine could be based on their unusual properties and synergic counterparts as immune response humoral effectors, in addition to their direct microbicidal activity. This has been seen in many other marine proteins that are sufficiently immunogenic to humans, not necessarily in terms of antibody generation but as inflammation promoters and recruitment agents or immune enhancers.