Literature DB >> 35583675

AMR-meta: a k-mer and metafeature approach to classify antimicrobial resistance from high-throughput short-read metagenomics data.

Simone Marini1, Marco Oliva2, Ilya B Slizovskiy3, Rishabh A Das1, Noelle Robertson Noyes3, Tamer Kahveci2, Christina Boucher2, Mattia Prosperi1.   

Abstract

BACKGROUND: Antimicrobial resistance (AMR) is a global health concern. High-throughput metagenomic sequencing of microbial samples enables profiling of AMR genes through comparison with curated AMR databases. However, the performance of current methods is often hampered by database incompleteness and the presence of homology/homoplasy with other non-AMR genes in sequenced samples.
RESULTS: We present AMR-meta, a database-free and alignment-free approach, based on k-mers, which combines algebraic matrix factorization into metafeatures with regularized regression. Metafeatures capture multi-level gene diversity across the main antibiotic classes. AMR-meta takes in reads from metagenomic shotgun sequencing and outputs predictions about whether those reads contribute to resistance against specific classes of antibiotics. In addition, AMR-meta uses an augmented training strategy that joins an AMR gene database with non-AMR genes (used as negative examples). We compare AMR-meta with AMRPlusPlus, DeepARG, and Meta-MARC, further testing their ensemble via a voting system. In cross-validation, AMR-meta has a median f-score of 0.7 (interquartile range, 0.2-0.9). On semi-synthetic metagenomic data-external test-on average AMR-meta yields a 1.3-fold hit rate increase over existing methods. In terms of run-time, AMR-meta is 3 times faster than DeepARG, 30 times faster than Meta-MARC, and as fast as AMRPlusPlus. Finally, we note that differences in AMR ontologies and observed variance of all tools in classification outputs call for further development on standardization of benchmarking data and protocols.
CONCLUSIONS: AMR-meta is a fast, accurate classifier that exploits non-AMR negative sets to improve sensitivity and specificity. The differences in AMR ontologies and the high variance of all tools in classification outputs call for the deployment of standard benchmarking data and protocols, to fairly compare AMR prediction tools.
© The Author(s) 2022. Published by Oxford University Press GigaScience.

Entities:  

Keywords:  antimicrobial resistance; functional metagenomics; machine learning; matrix factorization; short reads

Mesh:

Substances:

Year:  2022        PMID: 35583675      PMCID: PMC9116207          DOI: 10.1093/gigascience/giac029

Source DB:  PubMed          Journal:  Gigascience        ISSN: 2047-217X            Impact factor:   7.658


  42 in total

1.  The antibiotic resistance crisis: part 1: causes and threats.

Authors:  C Lee Ventola
Journal:  P T       Date:  2015-04

2.  Improved annotation of antibiotic resistance determinants reveals microbial resistomes cluster by ecology.

Authors:  Molly K Gibson; Kevin J Forsberg; Gautam Dantas
Journal:  ISME J       Date:  2014-07-08       Impact factor: 10.302

3.  Structure, function and diversity of the healthy human microbiome.

Authors: 
Journal:  Nature       Date:  2012-06-13       Impact factor: 49.962

4.  CLARK: fast and accurate classification of metagenomic and genomic sequences using discriminative k-mers.

Authors:  Rachid Ounit; Steve Wanamaker; Timothy J Close; Stefano Lonardi
Journal:  BMC Genomics       Date:  2015-03-25       Impact factor: 3.969

5.  A large scale evaluation of TBProfiler and Mykrobe for antibiotic resistance prediction in Mycobacterium tuberculosis.

Authors:  Pierre Mahé; Meriem El Azami; Philippine Barlas; Maud Tournoud
Journal:  PeerJ       Date:  2019-05-01       Impact factor: 2.984

6.  MEGARes 2.0: a database for classification of antimicrobial drug, biocide and metal resistance determinants in metagenomic sequence data.

Authors:  Enrique Doster; Steven M Lakin; Christopher J Dean; Cory Wolfe; Jared G Young; Christina Boucher; Keith E Belk; Noelle R Noyes; Paul S Morley
Journal:  Nucleic Acids Res       Date:  2020-01-08       Impact factor: 16.971

7.  Patient similarity by joint matrix trifactorization to identify subgroups in acute myeloid leukemia.

Authors:  F Vitali; S Marini; D Pala; A Demartini; S Montoli; A Zambelli; R Bellazzi
Journal:  JAMIA Open       Date:  2018-05-14

8.  Exploring Prediction of Antimicrobial Resistance Based on Protein Solvent Accessibility Variation.

Authors:  Simone Marini; Marco Oliva; Ilya B Slizovskiy; Noelle Robertson Noyes; Christina Boucher; Mattia Prosperi
Journal:  Front Genet       Date:  2021-01-22       Impact factor: 4.599

9.  DeepARG: a deep learning approach for predicting antibiotic resistance genes from metagenomic data.

Authors:  Gustavo Arango-Argoty; Emily Garner; Amy Pruden; Lenwood S Heath; Peter Vikesland; Liqing Zhang
Journal:  Microbiome       Date:  2018-02-01       Impact factor: 14.650

10.  Discordant bioinformatic predictions of antimicrobial resistance from whole-genome sequencing data of bacterial isolates: an inter-laboratory study.

Authors:  Ronan M Doyle; Denise M O'Sullivan; Sean D Aller; Sebastian Bruchmann; Taane Clark; Andreu Coello Pelegrin; Martin Cormican; Ernest Diez Benavente; Matthew J Ellington; Elaine McGrath; Yair Motro; Thi Phuong Thuy Nguyen; Jody Phelan; Liam P Shaw; Richard A Stabler; Alex van Belkum; Lucy van Dorp; Neil Woodford; Jacob Moran-Gilad; Jim F Huggett; Kathryn A Harris
Journal:  Microb Genom       Date:  2020-02-12
View more
  1 in total

1.  AMR-meta: a k-mer and metafeature approach to classify antimicrobial resistance from high-throughput short-read metagenomics data.

Authors:  Simone Marini; Marco Oliva; Ilya B Slizovskiy; Rishabh A Das; Noelle Robertson Noyes; Tamer Kahveci; Christina Boucher; Mattia Prosperi
Journal:  Gigascience       Date:  2022-05-18       Impact factor: 7.658

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.