Application of machine learning techniques to tuberculosis drug resistance analysis

Samaneh Kouchaki; Yang Yang; Timothy M Walker; A. Sarah Walker; Daniel J. Wilson; Timothy E A Peto; Derrick W Crook; David A Clifton; Sarah J Hoosdally; Ana L. Gibertoni Cruz; Joshua James Carter; Clara Grazian; Philip W. Fowler; Zamin Iqbal; Martin Hunt; E. Grace Smith; Priti Rathod; Lisa Jarrett; Daniela Matias; Daniela Maria Cirillo; Emanuele Borroni; Simone Battaglia; Arash Ghodousi; Andrea Spitaleri; Andrea Maurizio Cabibbe; Sabira Tahseen; Kayzad Soli Nilgiriwala; Sanchi Shah; Camilla Rodrigues; Priti Kambli; Utkarsha Surve; Rukhsar Khot; Stefan Niemann; Thomas Andreas Kohl; Matthias Merker; Harald Hoffmann; N Molodtsov; Sara Plesnik; Nazir Ismail; Shaheed V. Omar; Lavania Joseph; E MARUBINI; Guy Thwaites; Thuong Nguyen Thuy Thuong; Nhung Hoang Ngoc; V Srinivasan; David Moore; Jorge Coronel; Walter Solano; George Fú Gāo; G He; Y Zhao; A Ma; Chunfa Liu; Baoli Zhu; Ian Laurenson; Pauline Claxton; Robert J. Wilkinson; Ajit Lalvani; James Posey; Jennifer Gardy; Jim Werngren; Nicholas Paton; Ruwen Jou; M H Wu; Wan-Hsuan Lin; Lucilaine Ferrazoli; R S de Oliveira

doi:10.1093/bioinformatics/bty949

Back

Application of machine learning techniques to tuberculosis drug resistance analysis

Journal article

Peer reviewed

Application of machine learning techniques to tuberculosis drug resistance analysis

Samaneh Kouchaki, Yang Yang, Timothy M Walker, A. Sarah Walker, Daniel J. Wilson, Timothy E A Peto, Derrick W Crook, David A Clifton, Sarah J Hoosdally, Ana L. Gibertoni Cruz, …

BIOINFORMATICS, Vol.35(13), pp.2276-2282

21/11/2018

DOI: https://doi.org/10.1093/bioinformatics/bty949

PMCID: PMC6596891

PMID: 30462147

Abstract

Biochemical Research Methods

Biochemistry & Molecular Biology

Biotechnology & Applied Microbiology

Computer Science, Interdisciplinary Applications

Life Sciences & Biomedicine

Mathematical & Computational Biology

Science & Technology

Statistics & Probability

Computer Science

Mathematics

Physical Sciences

Technology

Motivation Timely identification of Mycobacterium tuberculosis (MTB) resistance to existing drugs is vital to decrease mortality and prevent the amplification of existing antibiotic resistance. Machine learning methods have been widely applied for timely predicting resistance of MTB given a specific drug and identifying resistance markers. However, they have been not validated on a large cohort of MTB samples from multi-centers across the world in terms of resistance prediction and resistance marker identification. Several machine learning classifiers and linear dimension reduction techniques were developed and compared for a cohort of 13 402 isolates collected from 16 countries across 6 continents and tested 11 drugs. Results Compared to conventional molecular diagnostic test, area under curve of the best machine learning classifier increased for all drugs especially by 23.11%, 15.22% and 10.14% for pyrazinamide, ciprofloxacin and ofloxacin, respectively (P<0.01). Logistic regression and gradient tree boosting found to perform better than other techniques. Moreover, logistic regression/gradient tree boosting with a sparse principal component analysis/non-negative matrix factorization step compared with the classifier alone enhanced the best performance in terms of F1-score by 12.54%, 4.61%, 7.45% and 9.58% for amikacin, moxifloxacin, ofloxacin and capreomycin, respectively, as well increasing area under curve for amikacin and capreomycin. Results provided a comprehensive comparison of various techniques and confirmed the application of machine learning for better prediction of the large diverse tuberculosis data. Furthermore, mutation ranking showed the possibility of finding new resistance/susceptible markers. Availability and implementation The source code can be found at http://www.robots.ox.ac.uk/ davidc/code.php

Metrics

11 Record Views

37 Times Cited - Web of Science

See more details

Details

Title: Application of machine learning techniques to tuberculosis drug resistance analysis
Creators: Samaneh Kouchaki
Yang Yang - Univ Oxford, Inst Biomed Engn, Dept Engn Sci, Oxford, England
Timothy M Walker - Univ Oxford, Nuffield Dept Med, Oxford, England
A. Sarah Walker - Univ Oxford, Nuffield Dept Med, Oxford, England
Daniel J. Wilson - Univ Oxford, Li Ka Shing Ctr Hlth Informat & Discovery, Nuffield Dept Populat Hlth, Oxford, England
Timothy E A Peto - Univ Oxford, Nuffield Dept Med, Oxford, England
Derrick W Crook - Univ Oxford, Nuffield Dept Med, Oxford, England
David A Clifton - Univ Oxford, Inst Biomed Engn, Dept Engn Sci, Oxford, England
Sarah J Hoosdally - Univ Oxford, Oxford, England
Ana L. Gibertoni Cruz - Univ Oxford, Oxford, England
Joshua James Carter - Univ Oxford, Oxford, England
Clara Grazian - Univ Oxford, Oxford, England
Philip W. Fowler - Univ Oxford, Oxford, England
Zamin Iqbal - European Bioinformat Inst, Cambridge, England
Martin Hunt - European Bioinformat Inst, Cambridge, England
E. Grace Smith - Publ Hlth England, Birmingham, W Midlands, England
Priti Rathod - Publ Hlth England, Birmingham, W Midlands, England
Lisa Jarrett - Publ Hlth England, Birmingham, W Midlands, England
Daniela Matias - Publ Hlth England, Birmingham, W Midlands, England
Daniela Maria Cirillo - IRCCS, San Raffaele Sci Inst, Emerging Bacterial Pathogens Unit, Milan, Italy
Emanuele Borroni - IRCCS, San Raffaele Sci Inst, Emerging Bacterial Pathogens Unit, Milan, Italy
Simone Battaglia - IRCCS, San Raffaele Sci Inst, Emerging Bacterial Pathogens Unit, Milan, Italy
Arash Ghodousi - IRCCS, San Raffaele Sci Inst, Emerging Bacterial Pathogens Unit, Milan, Italy
Andrea Spitaleri - IRCCS, San Raffaele Sci Inst, Emerging Bacterial Pathogens Unit, Milan, Italy
Andrea Maurizio Cabibbe - IRCCS, San Raffaele Sci Inst, Emerging Bacterial Pathogens Unit, Milan, Italy
Sabira Tahseen - Natl TB Control Program Pakistan, Islamabad, Pakistan
Kayzad Soli Nilgiriwala - Fdn Med Res, Mumbai, Maharashtra, India
Sanchi Shah - Fdn Med Res, Mumbai, Maharashtra, India
Camilla Rodrigues - Hinduja Natl Hosp & Med Res Ctr, Mumbai, Maharashtra, India
Priti Kambli - Hinduja Natl Hosp & Med Res Ctr, Mumbai, Maharashtra, India
Utkarsha Surve - Hinduja Natl Hosp & Med Res Ctr, Mumbai, Maharashtra, India
Rukhsar Khot - Hinduja Natl Hosp & Med Res Ctr, Mumbai, Maharashtra, India
Stefan Niemann - Res Ctr Borstel, Borstel, Germany
Thomas Andreas Kohl - Res Ctr Borstel, Borstel, Germany
Matthias Merker - Res Ctr Borstel, Borstel, Germany
Harald Hoffmann - IML Red, Inst Microbiol & Lab Med, Gauting, Germany
N Molodtsov - IML Red, Inst Microbiol & Lab Med, Gauting, Germany
Sara Plesnik - IML Red, Inst Microbiol & Lab Med, Gauting, Germany
Nazir Ismail - Natl Inst Communicable Dis, Johannesburg, South Africa
Shaheed V. Omar - Natl Inst Communicable Dis, Johannesburg, South Africa
Lavania Joseph - Natl Inst Communicable Dis, Johannesburg, South Africa
E MARUBINI - Natl Inst Communicable Dis, Johannesburg, South Africa
Guy Thwaites - Univ Oxford, Clin Res Unit, Ho Chi Minh City, Vietnam
Thuong Nguyen Thuy Thuong - Univ Oxford, Clin Res Unit, Ho Chi Minh City, Vietnam
Nhung Hoang Ngoc - Univ Oxford, Clin Res Unit, Ho Chi Minh City, Vietnam
V Srinivasan - Univ Oxford, Clin Res Unit, Ho Chi Minh City, Vietnam
David Moore - London Sch Hyg & Trop Med, London, England
Jorge Coronel - London Sch Hyg & Trop Med, London, England
Walter Solano - London Sch Hyg & Trop Med, London, England
George Fú Gāo - China CDC, Beijing, Peoples R China
G He - China CDC, Beijing, Peoples R China
Y Zhao - China CDC, Beijing, Peoples R China
A Ma - China CDC, Beijing, Peoples R China
Chunfa Liu - China CDC, Beijing, Peoples R China
Baoli Zhu - Chinese Acad Sci, Inst Microbiol, Beijing, Peoples R China
Ian Laurenson - Scottish Mycobacteria Reference Lab, Edinburgh, Midlothian, Scotland
Pauline Claxton - Scottish Mycobacteria Reference Lab, Edinburgh, Midlothian, Scotland
Robert J. Wilkinson - Univ Cape Town, Rondebosch, South Africa
Ajit Lalvani - Imperial Coll London, London, England
James Posey - CDC Atlanta, Atlanta, GA USA
Jennifer Gardy - Univ British Columbia, Vancouver, BC, Canada
Jim Werngren - Publ Hlth Agcy Sweden, Stockholm, Sweden
Nicholas Paton - Natl Univ Singapore, Singapore, Singapore
Ruwen Jou - CDC Taiwan, Taipei, Taiwan
M H Wu - CDC Taiwan, Taipei, Taiwan
Wan-Hsuan Lin - CDC Taiwan, Taipei, Taiwan
Lucilaine Ferrazoli - Adolfo Lutz Inst, Sao Paulo, Brazil
R S de Oliveira - Adolfo Lutz Inst, Sao Paulo, Brazil
Publication Details: BIOINFORMATICS, Vol.35(13), pp.2276-2282
Publisher: Oxford Univ Press
Date published: 21/11/2018
Date accepted: 19/11/2018
Grant note: The work was supported by the National Institute for Health Research (NIHR) Oxford Biomedical Research Centre; the CRyPTIC consortium which is funded by a Wellcome Trust/Newton Fund-MRC Collaborative Award [200205/Z/15/Z] and the Bill and Melinda Gates Foundation Trust [OPP1133541]. D.J.W. is a Sir Henry Dale Fellow, jointly funded by the Wellcome Trust and the Royal Society [101237/Z/13/Z]. SK was also supported by EPSRC (Grant EP/N020774/1).
Identifiers: 99777765602346
Copyright: © The Author(s) 2018. Published by Oxford University Press. 2276 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
Academic Unit: School of Computer Science and Electronic Engineering
Language: English
Resource Type: Journal article

Application of machine learning techniques to tuberculosis drug resistance analysis

Abstract

Metrics

Details

Usage Policy