FACS: antimicrobial peptide screening in genomes and metagenomes

Motivation: Antimicrobial peptides (AMPs) have the potential to tackle multidrug-resistant pathogens in both clinical and non-clinical contexts. The recent growth in the availability of genomes and metagenomes provides an opportunity for in silico prediction of novel AMPs. However, due to the small size of these peptides, standard gene prospection methods cannot be applied in this domain and alternative approaches are necessary. In particular, standard gene prediction methods have low precision for short peptides, and functional classification by homology results have low recall. Results: Here, we present a novel set of 22 protein features that outperforms the state-of-the-art in the prediction of AMPs as well as their classification into their hemolytic activity. We use these classifiers to build FACS (Fast Antimicrobial Classification System ), an end-to-end tool, which combines assembly, ORF prediction, and AMP classification to work directly on genomes or metagenomes. We demonstrate that FACS recovers high-quality candidates from genomes and metagenomes using realistic simulations and real data. Availability: FACS is implemented in Bash and its source code is freely available for download at https://github.com/FACSAntimicrobial-Peptides-Prospection/FACS. The functionality is also available as a webserver: http://big-databiology.org/software/facs. Supplementary information: Supplementary data are available online.