Identification of novel antibacterial peptides by chemoinformatics and machine learning.

@article{Fjell2009IdentificationON,
  title={Identification of novel antibacterial peptides by chemoinformatics and machine learning.},
  author={Christopher D. Fjell and H{\aa}vard Jenssen and Kai Hilpert and Warren A. Cheung and Nelly Pant{\'e} and Robert E. W. Hancock and Artem Cherkasov},
  journal={Journal of medicinal chemistry},
  year={2009},
  volume={52 7},
  pages={
          2006-15
        }
}
The rise of antibiotic resistant pathogens is one of the most pressing global health issues. Discovery of new classes of antibiotics has not kept pace; new agents often suffer from cross-resistance to existing agents of similar structure. Short, cationic peptides with antimicrobial activity are essential to the host defenses of many organisms and represent a promising new class of antimicrobials. This paper reports the successful in silico screening for potent antibiotic peptides using a… 

Figures and Tables from this paper

Optimization of Antibacterial Peptides by Genetic Algorithms and Cheminformatics

TLDR
A method of generating candidate peptide sequences using the heuristic evolutionary programming method of genetic algorithms (GA), which provided a large (19‐fold) improvement in identification of novel antibacterial peptides.

Use of artificial intelligence in the design of small peptide antibiotics effective against a broad spectrum of highly antibiotic-resistant superbugs.

TLDR
The best peptides, representing the top quartile of predicted activities, were effective against a broad array of multidrug-resistant "Superbugs" with activities that were equal to or better than four highly used conventional antibiotics.

Discovering new in silico tools for antimicrobial peptide prediction.

TLDR
The standardization of procedures to experimentally evaluate the antimicrobial activity of AMPs, together with the constant growth of current well-established databases, may allow for the future development of new bioinformatics tools to accurately predict antimacterial activity.

First Multitarget Chemo-Bioinformatic Model To Enable the Discovery of Antibacterial Peptides against Multiple Gram-Positive Pathogens

TLDR
This is the first multitarget (mt) chemo-bioinformatic model devoted to performing alignment-free prediction of antibacterial activity of peptides against multiple Gram-positive bacterial strains and constitutes a powerful tool to enable the discovery of potent and versatile AMPs.

Connecting Peptide Physicochemical and Antimicrobial Properties by a Rational Prediction Model

TLDR
An artificial neural network approach, based on the AMP's physicochemical characteristics, that is able not only to identify active peptides but also to assess its antimicrobial potency is described, concluding that sequence derived parameters are enough to characterize antimicrobial peptides.

Enabling the Discovery and Virtual Screening of Potent and Safe Antimicrobial Peptides. Simultaneous Prediction of Antibacterial Activity and Cytotoxicity.

TLDR
This work introduces the first multitasking (mtk) computational model focused on performing simultaneous predictions of antibacterial activities, and cytotoxicities of peptides, which can be considered a very useful tool to support high throughput research for the discovery of potent and safe AMPs.

Computer-Aided Design of Antimicrobial Peptides

TLDR
Two different in silico strategies of computer-aided antibacterial peptide design are discussed, a linear correlation model build as an extension of traditional principal component analysis (PCA) and a non-linear artificial neural network model.

Binary Response Models for Recognition of Antimicrobial Peptides

TLDR
A computational approach to further the understanding of what physicochemical properties or features confer to a peptide antimicrobial activity and provides access to the proposed methodology through a web server, which allows users to replicate the findings here or evaluate their own feature set.

Improving Recognition of Antimicrobial Peptides and Target Selectivity through Machine Learning and Genetic Programming

TLDR
This paper demonstrates for the first time the capability not only to recognize that a peptide is an AMP or not but also to predict its target selectivity based on models of activity againstonly Gram-positive, only Gram-negative, or both types of bacteria.
...

References

SHOWING 1-10 OF 32 REFERENCES

Use of artificial intelligence in the design of small peptide antibiotics effective against a broad spectrum of highly antibiotic-resistant superbugs.

TLDR
The best peptides, representing the top quartile of predicted activities, were effective against a broad array of multidrug-resistant "Superbugs" with activities that were equal to or better than four highly used conventional antibiotics.

QSAR modeling and computer‐aided design of antimicrobial peptides

TLDR
It is confirmed that it is possible to build powerful predictive models using even small sets of structurally different peptides, when using contact‐energy descriptors and inductive and conventional QSAR descriptors in the model design.

Evaluating Different Descriptors for Model Design of Antimicrobial Peptides with Enhanced Activity Toward P. aeruginosa

TLDR
The construction of a mathematical model for prediction, prior to synthesis, of peptide antibacterial activity toward Pseudomonas aeruginosa is described, able to correctly predict the activity of 84% of the tested peptides, within a twofold deviation window of the corresponding IC50 values.

High-throughput generation of small antibacterial peptides with improved activity

TLDR
A high-throughput method to screen large numbers of peptides for improved antimicrobial activity using a complete substitution library of 12-amino-acid peptides based on a linearized variant of the bovine peptide bactenecin was described.

Comparative QSAR- and Fragments Distribution Analysis of Drugs, Druglikes, Metabolic Substances, and Antimicrobial Compounds

TLDR
A number of binary QSAR models have been developed using methods of artificial neural networks, k-nearest neighbors, linear discriminative analysis, and multiple linear regression and have been compared for their ability to recognize five types of chemical compounds, revealing inhomogeneous scale-free organization of human metabolites.

De Novo Design of Potent Antimicrobial Peptides

TLDR
Quantitative structure-activity relationship (QSAR) analysis of peptide sequences and their antimicrobial, cytotoxic, and hemolytic activities revealed that site-directed substitutions of residues in the hydrophobic face of the amphipathic peptides with less lipophilic residues selectively decrease the hemolyic effect without significantly affecting the antimicrobial or cytOToxic activity.

Mechanisms of Antimicrobial Peptide Action and Resistance

TLDR
The intention of this review is to illustrate the contemporary structural and functional themes among mechanisms of antimicrobial peptide action and resistance.

Antimicrobial peptides: current status and therapeutic potential.

TLDR
This review summarises the current knowledge about the basic and applied biology of AMPs and qualifies as prototypes of innovative drugs that may be used as antimicrobials, anti-lipopolysaccharide drugs or modifiers of inflammation.