Identification Of Antimicrobial Peptides Research Articles

TriStack enables accurate identification of antimicrobial and anti-inflammatory peptides by combining machine learning and deep learning approaches

The identification of antimicrobial peptides (AMPs) and anti-inflammatory peptides (AIPs) is crucial for drug design and disease treatment. However, it remains a computational challenge to accurately identify these peptides due to insufficient information encoding the peptide sequences. In this study, we propose TriStack, a powerful and interpretable model for accurate identification of AMPs and AIPs by stacking a machine learning-based module using a multi-layer residual network. It first extracts three types of function-related features from peptide sequences to comprehensively characterize the composition, distribution, and physicochemical properties of residues. Furthermore, these features are fused and fed into a two-module stacked model. The first module provides the preliminary predictions based on three machine learning methods, while the second module refines these predictions further via a multi-layer residual network. After training and testing, TriStack outperforms all the compared leading methods for both AMPs and AIPs predictions. TriStack is expected to contribute to antimicrobial and anti-inflammatory drug based on peptide sequences.

Development of a Selective and Stable Antimicrobial Peptide.

Antimicrobial peptides (AMPs) are presented as potential scaffolds for antibiotic development due to their desirable qualities including broad-spectrum activity, rapid action, and general lack of susceptibility to current resistance mechanisms. However, they often lose antibacterial activity under physiological conditions and/or display mammalian cell toxicity, which limits their potential use. Identification of AMPs that overcome these barriers will help develop rules for how this antibacterial class can be developed to treat infection. Here we describe the development of our novel synthetic AMP, from discovery through in vivo application. Our evolved AMP, DTr18-dab, has broad-spectrum antibacterial activity and is nonhemolytic. It is active against planktonic bacteria and biofilm, is unaffected by colistin resistance, and importantly is active in both human serum and a Galleria mellonella infection model. Several modifications, including the incorporation of noncanonical amino acids, were used to arrive at this robust sequence. We observed that the impact on antibacterial activity with noncanonical amino acids was dependent on assay conditions and therefore not entirely predictable. Overall, our results demonstrate how a relatively weak lead can be developed into a robust AMP with qualities important for potential therapeutic translation.

Embedded-AMP: A Multi-Thread Computational Method for the Systematic Identification of Antimicrobial Peptides Embedded in Proteome Sequences.

Antimicrobial peptides (AMPs) have gained the attention of the research community for being an alternative to conventional antimicrobials to fight antibiotic resistance and for displaying other pharmacologically relevant activities, such as cell penetration, autophagy induction, immunomodulation, among others. The identification of AMPs had been accomplished by combining computational and experimental approaches and have been mostly restricted to self-contained peptides despite accumulated evidence indicating AMPs may be found embedded within proteins, the functions of which are not necessarily associated with antimicrobials. To address this limitation, we propose a machine-learning (ML)-based pipeline to identify AMPs that are embedded in proteomes. Our method performs an in-silico digestion of every protein in the proteome to generate unique k-mers of different lengths, computes a set of molecular descriptors for each k-mer, and performs an antimicrobial activity prediction. To show the efficiency of the method we used the shrimp proteome, and the pipeline analyzed all k-mers between 10 and 60 amino acids in length to predict all AMPs in less than 20 min. As an application example we predicted AMPs in different rodents (common cuy, common rat, and naked mole rat) with different reported longevities and found a relation between species longevity and the number of predicted AMPs. The analysis shows as the longevity of the species is higher, the number of predicted AMPs is also higher. The pipeline is available as a web service.

Do deep learning models make a difference in the identification of antimicrobial peptides?

In the last few decades, antimicrobial peptides (AMPs) have been explored as an alternative to classical antibiotics, which in turn motivated the development of machine learning models to predict antimicrobial activities in peptides. The first generation of these predictors was filled with what is now known as shallow learning-based models. These models require the computation and selection of molecular descriptors to characterize each peptide sequence and train the models. The second generation, known as deep learning-based models, which no longer requires the explicit computation and selection of those descriptors, started to be used in the prediction task of AMPs just four years ago. The superior performance claimed by deep models regarding shallow models has created a prevalent inertia to using deep learning to identify AMPs. However, methodological flaws and/or modeling biases in the building of deep models do not support such superiority. Here, we analyze the main pitfalls that led to establish biased conclusions on the leading performance of deep models. Also, we analyze whether deep models truly contribute to achieve better predictions than shallow models by performing fair studies on different state-of-the-art benchmarking datasets. The experiments reveal that deep models do not outperform shallow models in the classification of AMPs, and that both types of models codify similar chemical information since their predictions are highly similar. Thus, according to the currently available datasets, we conclude that the use of deep learning could not be the most suitable approach to develop models to identify AMPs, mainly because shallow models achieve comparable-to-superior performances and are simpler (Ockham's razor principle). Even so, we suggest the use of deep learning only when its capabilities lead to obtaining significantly better performance gains worth the additional computational cost.

Identification of antimicrobial peptides from the human gut microbiome using deep learning.

Identification of antimicrobial peptides from the human gut microbiome using deep learning.

Identification of antimicrobial peptides from the human gut microbiome using deep learning.

The human gut microbiome encodes a large variety of antimicrobial peptides (AMPs), but the short lengths of AMPs pose a challenge for computational prediction. Here we combined multiple natural language processing neural network models, including LSTM, Attention and BERT, to form a unified pipeline for candidate AMP identification from human gut microbiome data. Of 2,349 sequences identified as candidate AMPs, 216 were chemically synthesized, with 181 showing antimicrobial activity (a positive rate of >83%). Most of these peptides have less than 40% sequence homology to AMPs in the training set. Further characterization of the 11 most potent AMPs showed high efficacy against antibiotic-resistant, Gram-negative pathogens and demonstrated significant efficacy in lowering bacterial load by more than tenfold against a mouse model of bacterial lung infection. Our study showcases the potential of machine learning approaches for mining functional peptides from metagenome data and accelerating the discovery of promising AMP candidate molecules for in-depth investigations.

Molecular Cloning, Functional and Biophysical Characterization of an Antimicrobial Peptide from Rhizosphere Soil.

This study was designed to screen and identify an antimicrobial peptide from rhizosphere soil. The study was further focused towards overexpression, purification and characterization of this antimicrobial peptide, and to functionally validate its efficiency and efficacy as an antimicrobial agent. Yet, the study was further aimed at corroborating structural and functional studies using biophysical tools. Antimicrobial resistance is emerging as one of the top 10 global health crisis, it is multifaceted and the second largest cause of mortality. According to the World Health Organization (WHO), around the world, an estimated 700,000 people die each year from infection caused by antibiotic-resistant microbes. Antimicrobial peptides offer the best alternative to combat and overcome this crisis. In this manuscript, we report cloning, expression, purification and characterization of an antimicrobial peptide discovered from rhizosphere soil. Objectives of this study include construction, screening and identification of antimicrobial peptide from metagenome followed by its expression, purification and functional and biophysical investigation. Yet another objective of the study was to determine antimicrobial efficacy and efficiency as an antimicrobial peptide against MRSA strains. In this study, we used an array of molecular biology tools that include genetic engineering, PCR amplification, construction of an expression construct and NI-NTA based purification of the recombinant peptide. We have also carried out antimicrobial activity assay to determine MIC (minimum inhibitory concentration) and IC50 values of antimicrobial peptide. To establish the structural and functional relationship, circular dichroism, and both extrinsic and intrinsic fluorescence spectroscopy studies were carried out. Screening of metagenomic library resulted in the identification of gene (~500bp) harbouring an open reading frame (ORF) consisting of 282 bp. Open reading frame identified in gene encodes an antimicrobial peptide which had shared ~95% sequence similarity with the antimicrobial peptide of Bacillus origin. Purification of recombinant protein using Ni-NTA column chromatography demonstrated a purified protein band of ~11 kDa on 14% SDS-PAGE, which is well corroborated to theoretical deduced molecular weight of peptide from its amino acids sequence. Interestingly, the peptide exhibited antimicrobial activity in a broad range of pH and temperature. MIC determined against gram positive Bacillus sp. was found to be 0.015mg/ml, whereas, in the case of gram negative E. coli, it was calculated to be 0.062mg/ml. The peptide exhibited IC50 values corresponding to ~0.25mg/ml against Bacillus and ~0.5 mg/ml against E. coli. Antimicrobial susceptibility assay performed against methicillin resistant Staphylococcus aureus strain ATCC 3412 and standard strain of Staphylococcus aureus ATCC 9144 revealed its strong inhibitory activity against MRSA, whereby we observed a ~16mm clearance zone at higher peptide concentrations ~2mg/ml (~181.8μM). Biophysical investigation carried out using Trp fluorescence, ANS fluorescence and circular dichroism spectroscopy further revealed conformational stability in its secondary and tertiary structure at a wide range of temperature and pH. Altogether, the peptide discovered from rhizosphere metagenome holds potential in inhibiting the growth of both gram positive and gram negative bacteria, and was equally effective in inhibiting the multidrug resistant pathogenic strains (MRSA).

Identification of anti-microbial peptides and traces of microbial DNA in infrainfundibular compartments of human scalp terminal hair follicles.

The upper follicular compartment, a well-known reservoir of cutaneous microbiota, constitutes a space for intensive cross-barrier dialogue. The lower follicle comprises the bulb and bulge, structures with relative immune-privileged status, crucial for physiological cycling, and widely considered to be microbial-free. Following our initial immunohistochemical screening for regulatory cytokines and defensin expression in anagen hair follicles, we aimed to confirm our results with a follow-up ELISA investigation. We postulated that exposure to microbial components may trigger expression, and thus opted to investigate microbial presence in this area. We performed immunohistochemical staining for selected cytokines and antimicrobial peptides, and Gram and Giemsa staining on tissue sections from healthy individuals. Based on ELISA analyses, we confirmed a marked presence of IL-17A- and HBD2 in infrainfundibular compartments from plucked anagen hair follicles of 12 individuals (six females, six males; frontal and occipital scalp sites). 16S rRNA sequencing on microbial DNA extracted from lower follicles, as well as fluorescence in situ hybridization (FISH) were applied to explore bacterial presence in the infrainfundibular compartments. 16S rRNA sequencing yielded reproducible data of bacterial presence in infrainfundibular compartments of plucked scalp follicles; Lawsonella clevelandensis, Staphylococcaceae and Propionibacteriaceae were the most abundant bacteria. Also, FISH revealed biofilm structures formed by Cutibacterium acnes (formerly Propionibacterium acnes) and Staphylococcus sp. below the infundibulum. As the skin microbiome largely influences the local immune system, the presence of bacteria in proximity to follicular immune-privileged areas may be of relevance to hair cycling in health and disease.

Antimicrobial Peptides in Farm Animals: An Updated Review on Its Diversity, Function, Modes of Action and Therapeutic Prospects.

Antimicrobial peptides (AMPs) are the arsenals of the innate host defense system, exhibiting evolutionarily conserved characteristics that are present in practically all forms of life. Recent years have witnessed the emergence of antibiotic-resistant bacteria compounded with a slow discovery rate for new antibiotics that have necessitated scientific efforts to search for alternatives to antibiotics. Research on the identification of AMPs has generated very encouraging evidence that they curb infectious pathologies and are also useful as novel biologics to function as immunotherapeutic agents. Being innate, they exhibit the least cytotoxicity to the host and exerts a wide spectrum of biological activity including low resistance among microbes and increased wound healing actions. Notably, in veterinary science, the constant practice of massive doses of antibiotics with inappropriate withdrawal programs led to a high risk of livestock-associated antimicrobial resistance. Therefore, the world faces tremendous pressure for designing and devising strategies to mitigate the use of antibiotics in animals and keep it safe for posterity. In this review, we illustrate the diversity of farm animal-specific AMPs, and their biochemical foundations, mode of action, and prospective application in clinics. Subsequently, we present the data for their systematic classification under the major and minor groups, antipathogenic action, and allied bioactivities in the host. Finally, we address the limitations of their clinical implementation and envision areas for further advancement.

Characterization and Identification of Natural Antimicrobial Peptides on Different Organisms.

Because of the rapid development of multidrug resistance, conventional antibiotics cannot kill pathogenic bacteria efficiently. New antibiotic treatments such as antimicrobial peptides (AMPs) can provide a possible solution to the antibiotic-resistance crisis. However, the identification of AMPs using experimental methods is expensive and time-consuming. Meanwhile, few studies use amino acid compositions (AACs) and physicochemical properties with different sequence lengths against different organisms to predict AMPs. Therefore, the major purpose of this study is to identify AMPs on seven categories of organisms, including amphibians, humans, fish, insects, plants, bacteria, and mammals. According to the one-rule attribute evaluation, the selected features were used to construct the predictive models based on the random forest algorithm. Compared to the accuracies of iAMP-2L (a web-server for identifying AMPs and their functional types), ADAM (a database of AMP), and MLAMP (a multi-label AMP classifier), the proposed method yielded higher than 92% in predicting AMPs on each category. Additionally, the sensitivities of the proposed models in the prediction of AMPs of seven organisms were higher than that of all other tools. Furthermore, several physicochemical properties (charge, hydrophobicity, polarity, polarizability, secondary structure, normalized van der Waals volume, and solvent accessibility) of AMPs were investigated according to their sequence lengths. As a result, the proposed method is a practical means to complement the existing tools in the characterization and identification of AMPs in different organisms.

Identification of Antimicrobial Peptides from Novel Lactobacillus fermentum Strain.

Antimicrobial peptides (AMPs) are natural antagonistic tools of many bacteria and are considered as attractive antimicrobial agents for the treatment of bacteria with multidrug resistance. Lactic acid bacteria from the gastrointestinal tract of animals and human produce various AMPs inhibiting the growth of pathogens. Here we report the isolation and identification of novel Lactobacillus fermentum strain HF-D1 from the human gut producing AMPs which prevents the growth of P. aeruginosa and S. marcescens. The active fraction of peptides was obtained from the culture liquid by precipitation at 80% saturation of ammonium sulphate. For peptides identification, the precipitate was treated with guanidine hydrochloride to desorb from proteins, separated with ultrafiltration on spin columns with 10,000 MWCO, desalted with a reversed-phase chromatography and subjected to LC-MS/MS analysis. The in silico analysis of the identified 1111 peptides by using ADAM, CAMPR3 and AMPA prediction servers led to identification of the linear peptide with highly probable antimicrobial activity and further investigation of its antibacterial activity mechanism is promising. By using the dereplication algorithm, the peptide highly similar to non-ribosomal cyclic AMPs originally isolated from Staphylococcus epidermidis has been identified. This indicates that L. fermentum HF-D1 represents a novel strain producing antimicrobial peptides targeting P. aeruginosa and S. marcescens.

Cloning and identification of antimicrobial peptide, hepcidin from freshwater carp, Catla catla on pathogen challenge and PAMPs stimulation.

Hepcidin, a cationic cysteine-rich antimicrobial peptide (AMP) acts in hormone regulation and iron homeostasis in the host body. However, the biological property of hepcidin in immune reaction remains unexplored. In aquatic milieu, environmental and pathogenic stressors cause detrimental infections, which are defended by various immunological cells and antimicrobial peptides. In this study, hepcidin gene has been cloned from freshwater carp, Catla catla. The partially cloned hepcidin consists of 200bp nucleotide sequence encoding 66 amino acids. Nucleotide sequence showed 97% and 91% similarity with Labeo rohita and Cyprinus carpio, respectively. Expression profile revealed significant up-regulation (P ≤ 0.0001) in liver as compared to other tissues in different conditions. In Aeromonas hydrophila challenged C. catla, liver showed higher expression level of hepcidin at 72h as compared to other tissues. In skin, hepcidin expression showed significant upraise during 24h in Streptococcus uberis infection. In Argulus sp. infected fishes, up-regulation of hepcidin expression was noted in liver, intestine and skin. The inactivated viral antigen-stimulated fishes, a substantial rise in liver was observed implying hepcidin as an important molecule in combating the pathogenic infections in freshwater carp, C. catla. Fishes stimulated with pathogen-associated molecular patterns (PAMPs) triggered the increased expression of hepcidin mRNA in liver, kidney and skin. This study indicates the presence of hepcidin as antimicrobial peptide in neutralizing the pathogenic infection in fishes.

Characterization and identification of antimicrobial peptides with different functional activities.

In recent years, antimicrobial peptides (AMPs) have become an emerging area of focus when developing therapeutics hot spot residues of proteins are dominant against infections. Importantly, AMPs are produced by virtually all known living organisms and are able to target a wide range of pathogenic microorganisms, including viruses, parasites, bacteria and fungi. Although several studies have proposed different machine learning methods to predict peptides as being AMPs, most do not consider the diversity of AMP activities. On this basis, we specifically investigated the sequence features of AMPs with a range of functional activities, including anti-parasitic, anti-viral, anti-cancer and anti-fungal activities and those that target mammals, Gram-positive and Gram-negative bacteria. A new scheme is proposed to systematically characterize and identify AMPs and their functional activities. The 1st stage of the proposed approach is to identify the AMPs, while the 2nd involves further characterization of their functional activities. Sequential forward selection was employed to extract potentially informative features that are possibly associated with the functional activities of the AMPs. These features include hydrophobicity, the normalized van der Waals volume, polarity, charge and solvent accessibility-all of which are essential attributes in classifying between AMPs and non-AMPs. The results revealed the 1st stage AMP classifier was able to achieve an area under the receiver operating characteristic curve (AUC) value of 0.9894. During the 2nd stage, we found pseudo amino acid composition to be an informative attribute when differentiating between AMPs in terms of their functional activities. The independent testing results demonstrated that the AUCs of the multi-class models were 0.7773, 0.9404, 0.8231, 0.8578, 0.8648, 0.8745 and 0.8672 for anti-parasitic, anti-viral, anti-cancer, anti-fungal AMPs and those that target mammals, Gram-positive and Gram-negative bacteria, respectively. The proposed scheme helps facilitate biological experiments related to the functional analysis of AMPs. Additionally, it was implemented as a user-friendly web server (AMPfun, http://fdblab.csie.ncu.edu.tw/AMPfun/index.html) that allows individuals to explore the antimicrobial functions of peptides of interest.

Discovery and identification of antimicrobial peptides in Sichuan pepper (Zanthoxylum bungeanum Maxim) seeds by peptidomics and bioinformatics.

Antimicrobial peptides (AMPs) have generated growing attention because of the increasing bacterial resistance. However, the discovery and identification of AMPs have proven to be challenging due to the complex purification procedure associated with conventional methods. For the reasons given above, it is necessary to explore more efficient ways to obtain AMPs. We established a new method for discovery and identification of novel AMPs by proteomics and bioinformatics from Zanthoxylum bungeanum Maxim seeds protein hydrolysate directly. This process was initially achieved by employing ultra-performance liquid chromatography-electrospray ionization-mass spectrometry/mass (UPLC-ESI-MS/MS) spectrometry to identify peptides derived from Z. bungeanum Maxim seed protein hydrolysates. Three online servers were introduced to predict potential AMPs. Sixteen potential AMPs ranging from 1.5 to 2.7kDa were predicted and chemically synthesized, one of which, designated NP-6, inhibited activity against all the tested strains according to antimicrobial assay. Time-killing assay indicated that NP-6 could quickly kill almost all the Escherichia coli within 180min and Staphylococcus aureus at 360min. Moreover, the simulation 3D structure of NP-6 was consisted of α-helix and random coil, and this was verified by circular dichroism (CD) spectra. At last, the scanning electron microscope (SEM) images of E. coli and S. aureus treated by NP-6 demonstrated that NP-6 had a significant effect on bacteria cell morphology. Our findings provide an efficient approach for discovery of AMPs, and Z. bungeanum Maxim seeds may be a nature resource to extract antimicrobial agents.

Antimicrobial Peptides of Marine Crustaceans: The Potential and Challenges of Developing Therapeutic Agents.

The alarming increase of antimicrobial resistance has led to a growing number of studies aiming to develop novel antimicrobial therapeutics. Natural antimicrobial peptides possess a potent and broad-spectrum antimicrobial activity combined with diverse and unique structural motifs, which confer their different mechanisms of action. These peptides are ubiquitous in organisms and are integral to the innate immune system. Recently, identification of antimicrobial peptides from marine crustaceans has become the centre of attention of many researchers. This increasing interest stems from the remarkable diversity in the structural and genetic composition of these peptides compared to terrestrial counterparts. Thus, peptides from marine crustaceans can serve as future templates for novel antimicrobial agents. Here, we provide an overview of various antimicrobial peptides from the marine crustaceans, their antimicrobial activity and structure- activity relationships. We also discuss the potential and challenges of their development as new antimicrobial agents.

Extraction and identification of antimicrobial peptides from the Canastra artisanal minas cheese

Canastra artisanal Minas cheese samples were collected in Minas Gerais – Brazil. The samples were evaluated in order to observe the presence of antimicrobial peptides during 30 days of ripening. Soluble peptides extracted from the cheeses were fractionated by reverse phase liquid chromatography and their fractions evaluated for inhibitory action of E. coli. Fractions containing antimicrobial activity were analyzed by MALDI-TOF/TOF and then peptides were sequenced and identified using MASCOT Daemon coupled with UniProt database. The identified peptides were then validated by SCAFFOLD application. The peptides present in fractions with antimicrobial activity were RPKHPIKHQ, RPKHPIKHQG, RPKHPIKHQGLPQ and RPKHPIKHQGLPQE, HQPHQPLPPT and MHQPHQPLPPT. Peptide sequences PKHPIKHQ, RPKHPIKHQG, RPKHPIKHQGLPQ and RPKHPIKHQGLPQE were originated from αs1-casein and are their fragments belonging to Isracidine, which in turn is a well known antimicrobial peptide. The HQPHQPLPPT and MHQPHQPLPPT peptides were related to β-casein and were isolated in other studies, but their biological activities are still unknown.

AmPEP: Sequence-based prediction of antimicrobial peptides using distribution patterns of amino acid properties and random forest

Antimicrobial peptides (AMPs) are promising candidates in the fight against multidrug-resistant pathogens owing to AMPs’ broad range of activities and low toxicity. Nonetheless, identification of AMPs through wet-lab experiments is still expensive and time consuming. Here, we propose an accurate computational method for AMP prediction by the random forest algorithm. The prediction model is based on the distribution patterns of amino acid properties along the sequence. Using our collection of large and diverse sets of AMP and non-AMP data (3268 and 166791 sequences, respectively), we evaluated 19 random forest classifiers with different positive:negative data ratios by 10-fold cross-validation. Our optimal model, AmPEP with the 1:3 data ratio, showed high accuracy (96%), Matthew’s correlation coefficient (MCC) of 0.9, area under the receiver operating characteristic curve (AUC-ROC) of 0.99, and the Kappa statistic of 0.9. Descriptor analysis of AMP/non-AMP distributions by means of Pearson correlation coefficients revealed that reduced feature sets (from a full-featured set of 105 to a minimal-feature set of 23) can result in comparable performance in all respects except for some reductions in precision. Furthermore, AmPEP outperformed existing methods in terms of accuracy, MCC, and AUC-ROC when tested on benchmark datasets.

Predicting antimicrobial peptides with improved accuracy by incorporating the compositional, physico-chemical and structural features into Chou\u2019s general PseAAC

Antimicrobial peptides (AMPs) are important components of the innate immune system that have been found to be effective against disease causing pathogens. Identification of AMPs through wet-lab experiment is expensive. Therefore, development of efficient computational tool is essential to identify the best candidate AMP prior to the in vitro experimentation. In this study, we made an attempt to develop a support vector machine (SVM) based computational approach for prediction of AMPs with improved accuracy. Initially, compositional, physico-chemical and structural features of the peptides were generated that were subsequently used as input in SVM for prediction of AMPs. The proposed approach achieved higher accuracy than several existing approaches, while compared using benchmark dataset. Based on the proposed approach, an online prediction server iAMPpred has also been developed to help the scientific community in predicting AMPs, which is freely accessible at http://cabgrid.res.in:8080/amppred/. The proposed approach is believed to supplement the tools and techniques that have been developed in the past for prediction of AMPs.

Collagen-like antimicrobial peptides.

Combinatorial library composed of rigid rod-like peptides with a triple-helical scaffold was constructed. The component peptides were designed to have various combinations of basic and neutral (or hydrophobic) amino acid residues based on collagen-like (Gly-Pro-Yaa)-repeating sequences, inspired from the basic and amphiphilic nature of naturally occurring antimicrobial peptides. Screening of the peptide pools resulted in identification of antimicrobial peptides. A structure-activity relationship study revealed that the position of Arg-cluster at N-terminus and cystine knots at C-terminus in the triple helix significantly contributed to the antimicrobial activity. The most potent peptide RO-A showed activity against Gram-negative Escherichia coli and Gram-positive Bacillus subtilis. In addition, Escherichia coli exposed to RO-A resulted in abnormal elongation of the cells. RO-A was also shown to have remarkable stability in human serum and low cytotoxicity to mammalian cells. © 2016 Wiley Periodicals, Inc. Biopolymers (Pept Sci) 106: 453-459, 2016.

Identification of antimicrobial peptides by using eigenvectors.

Antibacterial peptides are subject to broad research due to their potential application and the benefit they can provide for a wide range of diseases. In this work, a mathematical-computational method, called the Polarity Vector Method, is introduced that has a high discriminative level (>70%) to identify peptides associated with Gram (-) bacteria, Gram (+) bacteria, cancer cells, fungi, insects, mammalian cells, parasites, and viruses, taken from the Antimicrobial Peptides Database. This supervised method uses only eigenvectors from the incident polar matrix of the group studied. It was verified with a comparative study with another extensively verified method developed previously by our team, the Polarity Index Method. The number of positive hits of both methods was up to 98% in all the tests conducted.