scholarly journals Machine Learning Designs Non-Hemolytic Antimicrobial Peptides

2021 ◽  
Author(s):  
Alice Capecchi ◽  
Xingguang Cai ◽  
Hippolyte Personne ◽  
Thilo Köhler ◽  
Christian van Delden ◽  
...  
Keyword(s):  
Machine Learning ◽  
Antimicrobial Peptides ◽  
Recurrent Neural Networks ◽  
Blood Cells ◽  
Multidrug Resistant ◽  
Training Data ◽  
Resistant Bacteria ◽  
Large Structure ◽  
Human Red Blood Cells ◽  
Structure Activity

<p>Machine learning (ML) consists in the recognition of patterns from training data and offers the opportunity to exploit large structure-activity database sets for drug design. In the area of peptide drugs, ML is mostly being tested to design antimicrobial peptides (AMPs), a class of biomolecules potentially useful to fight multidrug resistant bacteria. ML models have successfully identified membrane disruptive amphiphilic AMPs, however without addressing the associated toxicity to human red blood cells. Here we trained recurrent neural networks (RNN) with data from DBAASP (Database of Antimicrobial Activity and Structure of Peptides) to design short non-hemolytic AMPs. Synthesis and testing of 28 generated peptides, each at least 5 mutations away from training data, allowed us to identify eight new non-hemolytic AMPs against <i>Pseudomonas aeruginosa</i>, <i>Acinetobacter baumannii</i>, and methicillin resistant<i> Staphylococcus aureus</i> (MRSA). These results show that machine learning (ML) can be used to design new non-hemolytic AMPs.</p>

scholarly journals Machine Learning Designs Non-Hemolytic Antimicrobial Peptides

2021 ◽  
Author(s):  
Alice Capecchi ◽  
Xingguang Cai ◽  
Hippolyte Personne ◽  
Thilo Köhler ◽  
Christian van Delden ◽  
...  
Keyword(s):  
Machine Learning ◽  
Antimicrobial Peptides ◽  
Recurrent Neural Networks ◽  
Blood Cells ◽  
Multidrug Resistant ◽  
Training Data ◽  
Resistant Bacteria ◽  
Large Structure ◽  
Human Red Blood Cells ◽  
Structure Activity

<p>Machine learning (ML) consists in the recognition of patterns from training data and offers the opportunity to exploit large structure-activity database sets for drug design. In the area of peptide drugs, ML is mostly being tested to design antimicrobial peptides (AMPs), a class of biomolecules potentially useful to fight multidrug resistant bacteria. ML models have successfully identified membrane disruptive amphiphilic AMPs, however without addressing the associated toxicity to human red blood cells. Here we trained recurrent neural networks (RNN) with data from DBAASP (Database of Antimicrobial Activity and Structure of Peptides) to design short non-hemolytic AMPs. Synthesis and testing of 28 generated peptides, each at least 5 mutations away from training data, allowed us to identify eight new non-hemolytic AMPs against <i>Pseudomonas aeruginosa</i>, <i>Acinetobacter baumannii</i>, and methicillin resistant<i> Staphylococcus aureus</i> (MRSA). These results show that machine learning (ML) can be used to design new non-hemolytic AMPs.</p>

scholarly journals Machine Learning Designs Non-Hemolytic Antimicrobial Peptides

2021 ◽  
Author(s):  
Alice Capecchi ◽  
Xingguang Cai ◽  
Hippolyte Personne ◽  
Thilo Kohler ◽  
Christian van Delden ◽  
...  
Keyword(s):  
Machine Learning ◽  
Drug Design ◽  
Antimicrobial Peptides ◽  
Training Data ◽  
Large Structure ◽  
Peptide Drugs ◽  
Structure Activity

Machine learning (ML) consists of the recognition of patterns from training data and offers the opportunity to exploit large structure-activity databases for drug design. In the area of peptide drugs,...

scholarly journals Antimicrobial and Antibiofilm Peptides

Biomolecules ◽  
2020 ◽  
Vol 10 (4) ◽  
pp. 652 ◽  
Author(s):  
Angela Di Somma ◽  
Antonio Moretta ◽  
Carolina Canè ◽  
Arianna Cirillo ◽  
Angela Duilio
Keyword(s):  
Antimicrobial Peptides ◽  
Biofilm Formation ◽  
Bacterial Resistance ◽  
Antimicrobial Agents ◽  
Multidrug Resistant ◽  
Resistant Bacteria ◽  
Antibiofilm Activity ◽  
Chronic Infections ◽  
Planktonic Bacteria ◽  
Hostile Environments

The increasing onset of multidrug-resistant bacteria has propelled microbiology research towards antimicrobial peptides as new possible antibiotics from natural sources. Antimicrobial peptides are short peptides endowed with a broad range of activity against both Gram-positive and Gram-negative bacteria and are less prone to trigger resistance. Besides their activity against planktonic bacteria, many antimicrobial peptides also show antibiofilm activity. Biofilms are ubiquitous in nature, having the ability to adhere to virtually any surface, either biotic or abiotic, including medical devices, causing chronic infections that are difficult to eradicate. The biofilm matrix protects bacteria from hostile environments, thus contributing to the bacterial resistance to antimicrobial agents. Biofilms are very difficult to treat, with options restricted to the use of large doses of antibiotics or the removal of the infected device. Antimicrobial peptides could represent good candidates to develop new antibiofilm drugs as they can act at different stages of biofilm formation, on disparate molecular targets and with various mechanisms of action. These include inhibition of biofilm formation and adhesion, downregulation of quorum sensing factors, and disruption of the pre-formed biofilm. This review focuses on the proprieties of antimicrobial and antibiofilm peptides, with a particular emphasis on their mechanism of action, reporting several examples of peptides that over time have been shown to have activity against biofilm.

Antimicrobial peptides: an overview of a promising class of therapeutics

2007 ◽  
Vol 2 (1) ◽  
pp. 1-33 ◽  
Author(s):  
Andrea Giuliani ◽  
Giovanna Pirri ◽  
Silvia Nicoletto
Keyword(s):  
Antimicrobial Peptides ◽  
Multidrug Resistant ◽  
Innate Immune ◽  
Resistant Bacteria ◽  
Yeast Fungi ◽  
Wide Range ◽  
New Development ◽  
Catheter Site ◽  
Conventional Antibiotics

AbstractAntibiotic resistance is increasing at a rate that far exceeds the pace of new development of drugs. Antimicrobial peptides, both synthetic and from natural sources, have raised interest as pathogens become resistant against conventional antibiotics. Indeed, one of the major strengths of this class of molecules is their ability to kill multidrug-resistant bacteria. Antimicrobial peptides are relatively small (6 to 100 aminoacids), amphipathic molecules of variable length, sequence and structure with activity against a wide range of microorganisms including bacteria, protozoa, yeast, fungi, viruses and even tumor cells. They usually act through relatively non-specific mechanisms resulting in membranolytic activity but they can also stimulate the innate immune response. Several peptides have already entered pre-clinical and clinical trials for the treatment of catheter site infections, cystic fibrosis, acne, wound healing and patients undergoing stem cell transplantation. We review the advantages of these molecules in clinical applications, their disadvantages including their low in vivo stability, high costs of production and the strategies for their discovery and optimization.

scholarly journals Engineered Cationic Antimicrobial Peptides (eCAPs) to Combat Multidrug-Resistant Bacteria

Pharmaceutics ◽  
2020 ◽  
Vol 12 (6) ◽  
pp. 501 ◽  
Author(s):  
Berthony Deslouches ◽  
Ronald C. Montelaro ◽  
Ken L. Urish ◽  
Yuanpu P. Di
Keyword(s):  
Antimicrobial Peptides ◽  
De Novo ◽  
Multidrug Resistant ◽  
Clinical Development ◽  
Resistant Bacteria ◽  
Multidrug Resistant Bacteria ◽  
Health Crisis ◽  
Test Conditions ◽  
Reduced Activity

The increasing rate of antibiotic resistance constitutes a global health crisis. Antimicrobial peptides (AMPs) have the property to selectively kill bacteria regardless of resistance to traditional antibiotics. However, several challenges (e.g., reduced activity in the presence of serum and lack of efficacy in vivo) to clinical development need to be overcome. In the last two decades, we have addressed many of those challenges by engineering cationic AMPs de novo for optimization under test conditions that typically inhibit the activities of natural AMPs, including systemic efficacy. We reviewed some of the most promising data of the last two decades in the context of the advancement of the field of helical AMPs toward clinical development.

Using chemical synthesis to optimise antimicrobial peptides in the fight against antimicrobial resistance

2019 ◽  
Vol 91 (2) ◽  
pp. 181-198 ◽  
Author(s):  
Freda F. Li ◽  
Margaret A. Brimble
Keyword(s):  
Antimicrobial Peptides ◽  
Multidrug Resistant ◽  
Great Promise ◽  
Resistant Bacteria ◽  
Manufacturing Cost ◽  
Animal Cells ◽  
Design And Synthesis ◽  
Living Organisms ◽  
High Manufacturing Cost ◽  
Natural Peptides

Abstract The emergence of multidrug-resistant bacteria has necessitated the urgent need for novel antibacterial agents. Antimicrobial peptides (AMPs), the host-defence molecules of most living organisms, have shown great promise as potential antibiotic candidates due to their multiple mechanisms of action which result in very low or negligible induction of resistance. However, the development of AMPs for clinical use has been limited by their potential toxicity to animal cells, low metabolic stability and high manufacturing cost. Extensive efforts have therefore been directed towards the development of enhanced variants of natural AMPs to overcome these aforementioned limitations. In this review, we present our efforts focused on development of efficient strategies to prepare several recently discovered AMPs including antitubercular peptides. The design and synthesis of more potent and stable AMP analogues with synthetic modifications made to the natural peptides containing glycosylated residues or disulfide bridges are described.

scholarly journals Two Hits Are Better than One: Membrane-Active and DNA Binding-Related Double-Action Mechanism of NK-18, a Novel Antimicrobial Peptide Derived from Mammalian NK-Lysin

2012 ◽  
Vol 57 (1) ◽  
pp. 220-228 ◽  
Author(s):  
Jiexi Yan ◽  
Kairong Wang ◽  
Wen Dang ◽  
Ru Chen ◽  
Junqiu Xie ◽  
...  
Keyword(s):  
Antimicrobial Peptides ◽  
Cytotoxic T Cells ◽  
Multidrug Resistant ◽  
Chemotherapeutic Agents ◽  
Resistant Bacteria ◽  
Multidrug Resistant Bacteria ◽  
Content Type ◽  
New Strategy ◽  
Conventional Antibiotics ◽  
Double Targets

ABSTRACTThe extensive use and misuse of antibiotics in medicine result in the emergence of multidrug-resistant bacteria, creating an urgent need for the development of new chemotherapeutic agents. Nowadays, antimicrobial peptides are widely recognized as a class of promising candidates with activity against multidrug-resistant bacteria. NK-18 is a truncated peptide derived from NK-Lysin, an effector of cytotoxic T cells and natural killer cells. In this study, we studied the antibacterial mechanism of action of NK-18. The results revealed that NK-18 has potent antibacterial activity againstEscherichia coliandStaphylococcus aureus. According to our findings, NK-18 is membrane active and its target of action is not only the bacterial membrane but also the DNA in the cytoplasm. The double targets of NK-18 make it difficult for bacteria to generate resistance, which may present a new strategy to defend against multidrug-resistant bacteria and provide a new lead in the design of potent antimicrobial peptides with therapeutic application in the presence of increasing resistance to conventional antibiotics.

Sign in / Sign up

Export Citation Format

Share Document