Dataset Information

AMPlify: attentive deep learning model for discovery of novel antimicrobial peptides effective against WHO priority pathogens.

ABSTRACT:

Background

Antibiotic resistance is a growing global health concern prompting researchers to seek alternatives to conventional antibiotics. Antimicrobial peptides (AMPs) are attracting attention again as therapeutic agents with promising utility in this domain, and using in silico methods to discover novel AMPs is a strategy that is gaining interest. Such methods can sift through large volumes of candidate sequences and reduce lab screening costs.

Results

Here we introduce AMPlify, an attentive deep learning model for AMP prediction, and demonstrate its utility in prioritizing peptide sequences derived from the Rana [Lithobates] catesbeiana (bullfrog) genome. We tested the bioactivity of our predicted peptides against a panel of bacterial species, including representatives from the World Health Organization's priority pathogens list. Four of our novel AMPs were active against multiple species of bacteria, including a multi-drug resistant isolate of carbapenemase-producing Escherichia coli.

Conclusions

We demonstrate the utility of deep learning based tools like AMPlify in our fight against antibiotic resistance. We expect such tools to play a significant role in discovering novel candidates of peptide-based alternatives to classical antibiotics.

SUBMITTER: Li C

PROVIDER: S-EPMC8788131 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundIn 2018 Pakistan initiated its national antimicrobial resistance (AMR) surveillance aligned with Global Antimicrobial Surveillance System (GLASS). To complement this surveillance, we conducted a situational analysis of AMR rates among GLASS organisms in the country. Data from published studies and from antibiograms was compared and role of antibiograms as potential contributors to national AMR surveillance explored.MethodsAMR rates for GLASS specified pathogen/antimicrobials combination from Pakistan were reviewed. Data sources included published studies (2006-2018) providing AMR rates from Pakistan (n = 54) as well as antibiograms (2011-2018) available on the Pakistan Antimicrobial Resistance Network (PARN) website. Resistance rates were categorized as follows: Very low: 0-10%, Low: 11-30%, Moderate: 30-50% and High: > 50%.ResultsPublished data from hospital and community/laboratory-based studies report resistance rates of > 50% and 30-50% respectively to 3rd generation cephalosporins, fluoroquinolones and cotrimoxazole amongst Klebsiella pneumoniae and Escherichia coli. Carbapenem resistance rates amongst these organisms remained below 30%. High (> 50%) resistance was reported in Acinetobacter species to aminoglycosides and carbapenems among hospitalized patients. The evolution of ceftriaxone resistant Salmonella Typhi and Shigella species is reported. The data showed > 50% to fluoroquinolones amongst Neisseria gonorrhoeae and the spread of methicillin resistant Staphylococcus aureus (< 30%; 2008) to (> 50%; 2010) in hospital settings. Resistance reported in published studies aligned well with antibiogram data. The latter also captured a clear picture of evolution of resistance over the study period.ConclusionBoth published studies as well antibiograms suggest high rates of AMR in Pakistan. Antibiogram data demonstrating steady increase in AMR highlight its potential role towards supplementing national AMR surveillance efforts particularly in settings where reach of national surveillance may be limited.