Literature DB >> 33215194

An explainable machine learning platform for pyrazinamide resistance prediction and genetic feature identification of Mycobacterium tuberculosis.

Andrew Zhang1, Ling Teng1, Gil Alterovitz1,2.   

Abstract

OBJECTIVE: Tuberculosis is the leading cause of death from a single infectious agent. The emergence of antimicrobial resistant Mycobacterium tuberculosis strains makes the problem more severe. Pyrazinamide (PZA) is an important component for short-course treatment regimens and first- and second-line treatment regimens. This research aims for fast diagnosis of M. tuberculosis resistance to PZA and identification of genetic features causing resistance.
MATERIALS AND METHODS: We use clinically collected genomic data of M. tuberculosis that are resistant or susceptible to PZA. A machine learning platform is built to diagnose PZA resistance using the whole genome sequence data, and to identify resistance genes and mutations. The platform consists of a deep convolutional neural network (DCNN) model for resistance diagnosis and a support vector machine (SVM) model as a surrogate to identify resistance genes and mutations.
RESULTS: The DCNN model achieves a PZA resistance diagnosis accuracy of 93%. Each prediction takes less than a second. The SVM has revealed 2 novel genes, embB and gyrA, besides the well-known pncA gene, and 9 mutations that harbor PZA resistance. DISCUSSION: The DCNN and SVM machine learning platform, if used together with the real-time genome sequencing machines, could allow for rapid PZA diagnosis, allowing for critical time to ensure good patient outcomes, and preventing outbreaks of deadly infections. Furthermore, identifying pertinent resistance genes and mutations will help researchers better understand the biological mechanisms behind resistance.
CONCLUSIONS: Machine learning can be used to achieve high-accuracy resistance prediction, and identify genes and mutations causing the resistance.
© The Author(s) 2020. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  antimicrobial resistance; explainable AI; machine learning

Year:  2021        PMID: 33215194      PMCID: PMC7936518          DOI: 10.1093/jamia/ocaa233

Source DB:  PubMed          Journal:  J Am Med Inform Assoc        ISSN: 1067-5027            Impact factor:   4.497


  13 in total

1.  Molecular genetic analysis of nucleotide polymorphisms associated with ethambutol resistance in human isolates of Mycobacterium tuberculosis.

Authors:  S V Ramaswamy; A G Amin; S Göksel; C E Stager; S J Dou; H El Sahly; S L Moghazeh; B N Kreiswirth; J M Musser
Journal:  Antimicrob Agents Chemother       Date:  2000-02       Impact factor: 5.191

2.  Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review.

Authors:  Waseem Rawat; Zenghui Wang
Journal:  Neural Comput       Date:  2017-06-09       Impact factor: 2.026

Review 3.  Effect of antibiotic prescribing in primary care on antimicrobial resistance in individual patients: systematic review and meta-analysis.

Authors:  Céire Costelloe; Chris Metcalfe; Andrew Lovering; David Mant; Alastair D Hay
Journal:  BMJ       Date:  2010-05-18

4.  Molecular characterization of fluoroquinolone resistance in Mycobacterium tuberculosis: functional analysis of gyrA mutation at position 74.

Authors:  Ricky W T Lau; Pak-Leung Ho; Richard Y T Kao; Wing-Wai Yew; Terrence C K Lau; Vincent C C Cheng; Kwok-Yung Yuen; Stephen K W Tsui; Xinchun Chen; Wing-Cheong Yam
Journal:  Antimicrob Agents Chemother       Date:  2010-10-18       Impact factor: 5.191

5.  Incidence and impact of adverse effects to antibiotics in hospitalized adults with pneumonia.

Authors:  Robert Y Lin; Farzana Nuruzzaman; Shaili N Shah
Journal:  J Hosp Med       Date:  2009-02       Impact factor: 2.960

6.  United Nations meeting on antimicrobial resistance.

Authors: 
Journal:  Bull World Health Organ       Date:  2016-09-01       Impact factor: 9.408

Review 7.  Transforming clinical microbiology with bacterial genome sequencing.

Authors:  Xavier Didelot; Rory Bowden; Daniel J Wilson; Tim E A Peto; Derrick W Crook
Journal:  Nat Rev Genet       Date:  2012-08-07       Impact factor: 53.242

8.  Tuberculosis drug resistance mutation database.

Authors:  Andreas Sandgren; Michael Strong; Preetika Muthukrishnan; Brian K Weiner; George M Church; Megan B Murray
Journal:  PLoS Med       Date:  2009-02-10       Impact factor: 11.069

9.  A multiple genome analysis of Mycobacterium tuberculosis reveals specific novel genes and mutations associated with pyrazinamide resistance.

Authors:  Patricia Sheen; David Requena; Eduardo Gushiken; Robert H Gilman; Ricardo Antiparra; Bryan Lucero; Pilar Lizárraga; Basilio Cieza; Elisa Roncal; Louis Grandjean; Arnab Pain; Ruth McNerney; Taane G Clark; David Moore; Mirko Zimic
Journal:  BMC Genomics       Date:  2017-10-11       Impact factor: 3.969

10.  A Diagnostic Algorithm To Investigate Pyrazinamide and Ethambutol Resistance in Rifampin-Resistant Mycobacterium tuberculosis Isolates in a Low-Incidence Setting.

Authors:  Söenke Andres; Matthias I Gröschel; Doris Hillemann; Matthias Merker; Stefan Niemann; Katharina Kranzer
Journal:  Antimicrob Agents Chemother       Date:  2019-01-29       Impact factor: 5.191

View more
  1 in total

1.  Accurate and rapid prediction of tuberculosis drug resistance from genome sequence data using traditional machine learning algorithms and CNN.

Authors:  Xingyan Kuang; Fan Wang; Kyle M Hernandez; Zhenyu Zhang; Robert L Grossman
Journal:  Sci Rep       Date:  2022-02-14       Impact factor: 4.379

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.