Identification of novel antibacterial peptides by chemoinformatics and machine learning

Christopher D. Fjell, Håvard Jenssen, Kai Hilpert, Warren A. Cheung, Nelly Panté, Robert Hancock, Artem Cherkasov

Research output: Contribution to journalArticle

150 Citations (Scopus)

Abstract

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 combination of QSAR and machine learning techniques. On the basis of initial high-throughput measurements of activity of over 1400 random peptides, artificial neural network models were built using QSAR descriptors and subsequently used to screen an in silico library of approximately 100,000 peptides. In vitro validation of the modeling showed 94% accuracy in identifying highly active peptides. The best peptides identified through screening were found to have activities comparable or superior to those of four conventional antibiotics and superior to the peptide most advanced in clinical development against a broad array of multiresistant human pathogens.

LanguageEnglish
Pages2006-2015
Number of pages10
JournalJournal of Medicinal Chemistry
Volume52
Issue number7
DOIs
Publication statusPublished - 9 Apr 2009

ASJC Scopus subject areas

  • Molecular Medicine
  • Drug Discovery

Cite this

Fjell, C. D., Jenssen, H., Hilpert, K., Cheung, W. A., Panté, N., Hancock, R., & Cherkasov, A. (2009). Identification of novel antibacterial peptides by chemoinformatics and machine learning. Journal of Medicinal Chemistry, 52(7), 2006-2015. https://doi.org/10.1021/jm8015365
Fjell, Christopher D. ; Jenssen, Håvard ; Hilpert, Kai ; Cheung, Warren A. ; Panté, Nelly ; Hancock, Robert ; Cherkasov, Artem. / Identification of novel antibacterial peptides by chemoinformatics and machine learning. In: Journal of Medicinal Chemistry. 2009 ; Vol. 52, No. 7. pp. 2006-2015.
@article{5bbe1558c2034b1f8456c55e28be3476,
title = "Identification of novel antibacterial peptides by chemoinformatics and machine learning",
abstract = "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 combination of QSAR and machine learning techniques. On the basis of initial high-throughput measurements of activity of over 1400 random peptides, artificial neural network models were built using QSAR descriptors and subsequently used to screen an in silico library of approximately 100,000 peptides. In vitro validation of the modeling showed 94{\%} accuracy in identifying highly active peptides. The best peptides identified through screening were found to have activities comparable or superior to those of four conventional antibiotics and superior to the peptide most advanced in clinical development against a broad array of multiresistant human pathogens.",
author = "Fjell, {Christopher D.} and H{\aa}vard Jenssen and Kai Hilpert and Cheung, {Warren A.} and Nelly Pant{\'e} and Robert Hancock and Artem Cherkasov",
year = "2009",
month = "4",
day = "9",
doi = "10.1021/jm8015365",
language = "English",
volume = "52",
pages = "2006--2015",
journal = "Journal of Medicinal Chemistry",
issn = "0022-2623",
publisher = "American Chemical Society",
number = "7",

}

Fjell, CD, Jenssen, H, Hilpert, K, Cheung, WA, Panté, N, Hancock, R & Cherkasov, A 2009, 'Identification of novel antibacterial peptides by chemoinformatics and machine learning', Journal of Medicinal Chemistry, vol. 52, no. 7, pp. 2006-2015. https://doi.org/10.1021/jm8015365

Identification of novel antibacterial peptides by chemoinformatics and machine learning. / Fjell, Christopher D.; Jenssen, Håvard; Hilpert, Kai; Cheung, Warren A.; Panté, Nelly; Hancock, Robert; Cherkasov, Artem.

In: Journal of Medicinal Chemistry, Vol. 52, No. 7, 09.04.2009, p. 2006-2015.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Identification of novel antibacterial peptides by chemoinformatics and machine learning

AU - Fjell, Christopher D.

AU - Jenssen, Håvard

AU - Hilpert, Kai

AU - Cheung, Warren A.

AU - Panté, Nelly

AU - Hancock, Robert

AU - Cherkasov, Artem

PY - 2009/4/9

Y1 - 2009/4/9

N2 - 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 combination of QSAR and machine learning techniques. On the basis of initial high-throughput measurements of activity of over 1400 random peptides, artificial neural network models were built using QSAR descriptors and subsequently used to screen an in silico library of approximately 100,000 peptides. In vitro validation of the modeling showed 94% accuracy in identifying highly active peptides. The best peptides identified through screening were found to have activities comparable or superior to those of four conventional antibiotics and superior to the peptide most advanced in clinical development against a broad array of multiresistant human pathogens.

AB - 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 combination of QSAR and machine learning techniques. On the basis of initial high-throughput measurements of activity of over 1400 random peptides, artificial neural network models were built using QSAR descriptors and subsequently used to screen an in silico library of approximately 100,000 peptides. In vitro validation of the modeling showed 94% accuracy in identifying highly active peptides. The best peptides identified through screening were found to have activities comparable or superior to those of four conventional antibiotics and superior to the peptide most advanced in clinical development against a broad array of multiresistant human pathogens.

UR - http://www.scopus.com/inward/record.url?scp=64549125571&partnerID=8YFLogxK

U2 - 10.1021/jm8015365

DO - 10.1021/jm8015365

M3 - Article

VL - 52

SP - 2006

EP - 2015

JO - Journal of Medicinal Chemistry

T2 - Journal of Medicinal Chemistry

JF - Journal of Medicinal Chemistry

SN - 0022-2623

IS - 7

ER -