Abstract
Summary Antimicrobial peptides (AMPs) are key components of the innate immune system that protect against pathogens, regulate the microbiome, and are promising targets for pharmaceutical research. Computational tools based on machine learning have the potential to aid discovery of genes encoding novel AMPs but existing approaches are not designed for genome-wide scans. To facilitate such genome-wide discovery of AMPs we developed a fast and accurate AMP classification framework, ampir. ampir is designed for high throughput, integrates well with existing bioinformatics pipelines, and has much higher classification accuracy than existing methods when applied to whole genome data.
Availability and Implementation ampir is implemented primarily in R with core feature calculation methods written in C++. Release versions are available via CRAN and work on all major operating systems. The development version is maintained at https://github.com/legana/ampir
Contact legana.fingerhut{at}my.jcu.edu.au; ira.cooke{at}jcu.edu.au
Supplementary information Supplementary data are available at https://github.com/legana/amp_pub
Competing Interest Statement
The authors have declared no competing interest.
