Célio Dias Santos-Júnior1,2, Shaojun Pan1,2, Xing-Ming Zhao1,2, Luis Pedro Coelho1,2. 1. Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China. 2. Ministry of Education, Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Shanghai, China.
Abstract
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 AMP molecules. 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 in low recall. RESULTS: Here, we present Macrel (for metagenomic AMP classification and retrieval), which is an end-to-end pipeline for the prospection of high-quality AMP candidates from (meta)genomes. For this, we introduce a novel set of 22 peptide features. These were used to build classifiers which perform similarly to the state-of-the-art in the prediction of both antimicrobial and hemolytic activity of peptides, but with enhanced precision (using standard benchmarks as well as a stricter testing regime). We demonstrate that Macrel recovers high-quality AMP candidates using realistic simulations and real data. AVAILABILITY: Macrel is implemented in Python 3. It is available as open source at https://github.com/BigDataBiology/macrel and through bioconda. Classification of peptides or prediction of AMPs in contigs can also be performed on the webserver: https://big-data-biology.org/software/macrel.
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 AMP molecules. 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 in low recall. RESULTS: Here, we present Macrel (for metagenomic AMP classification and retrieval), which is an end-to-end pipeline for the prospection of high-quality AMP candidates from (meta)genomes. For this, we introduce a novel set of 22 peptide features. These were used to build classifiers which perform similarly to the state-of-the-art in the prediction of both antimicrobial and hemolytic activity of peptides, but with enhanced precision (using standard benchmarks as well as a stricter testing regime). We demonstrate that Macrel recovers high-quality AMP candidates using realistic simulations and real data. AVAILABILITY: Macrel is implemented in Python 3. It is available as open source at https://github.com/BigDataBiology/macrel and through bioconda. Classification of peptides or prediction of AMPs in contigs can also be performed on the webserver: https://big-data-biology.org/software/macrel.
Authors: Hila Sberro; Brayon J Fremin; Soumaya Zlitni; Fredrik Edfors; Nicholas Greenfield; Michael P Snyder; Georgios A Pavlopoulos; Nikos C Kyrpides; Ami S Bhatt Journal: Cell Date: 2019-08-08 Impact factor: 41.582
Authors: Björn Grüning; Ryan Dale; Andreas Sjödin; Brad A Chapman; Jillian Rowe; Christopher H Tomkins-Tinch; Renan Valieris; Johannes Köster Journal: Nat Methods Date: 2018-07 Impact factor: 28.547
Authors: Michaela Wenzel; Alina Iulia Chiriac; Andreas Otto; Dagmar Zweytick; Caroline May; Catherine Schumacher; Ronald Gust; H Bauke Albada; Maya Penkova; Ute Krämer; Ralf Erdmann; Nils Metzler-Nolte; Suzana K Straus; Erhard Bremer; Dörte Becher; Heike Brötz-Oesterhelt; Hans-Georg Sahl; Julia Elisabeth Bandow Journal: Proc Natl Acad Sci U S A Date: 2014-03-24 Impact factor: 11.205
Authors: Legana C H W Fingerhut; David J Miller; Jan M Strugnell; Norelle L Daly; Ira R Cooke Journal: Bioinformatics Date: 2021-01-29 Impact factor: 6.937
Authors: Paul G Arnison; Mervyn J Bibb; Gabriele Bierbaum; Albert A Bowers; Tim S Bugni; Grzegorz Bulaj; Julio A Camarero; Dominic J Campopiano; Gregory L Challis; Jon Clardy; Paul D Cotter; David J Craik; Michael Dawson; Elke Dittmann; Stefano Donadio; Pieter C Dorrestein; Karl-Dieter Entian; Michael A Fischbach; John S Garavelli; Ulf Göransson; Christian W Gruber; Daniel H Haft; Thomas K Hemscheidt; Christian Hertweck; Colin Hill; Alexander R Horswill; Marcel Jaspars; Wendy L Kelly; Judith P Klinman; Oscar P Kuipers; A James Link; Wen Liu; Mohamed A Marahiel; Douglas A Mitchell; Gert N Moll; Bradley S Moore; Rolf Müller; Satish K Nair; Ingolf F Nes; Gillian E Norris; Baldomero M Olivera; Hiroyasu Onaka; Mark L Patchett; Joern Piel; Martin J T Reaney; Sylvie Rebuffat; R Paul Ross; Hans-Georg Sahl; Eric W Schmidt; Michael E Selsted; Konstantin Severinov; Ben Shen; Kaarina Sivonen; Leif Smith; Torsten Stein; Roderich D Süssmuth; John R Tagg; Gong-Li Tang; Andrew W Truman; John C Vederas; Christopher T Walsh; Jonathan D Walton; Silke C Wenzel; Joanne M Willey; Wilfred A van der Donk Journal: Nat Prod Rep Date: 2013-01 Impact factor: 13.423