Imperial College London
Alternate

Professor Francis Drobniewski

Faculty of Medicine, Department of Infectious Disease

Chair in Global Health and Tuberculosis
 
 
 
//

Contact

 

f.drobniewski

 
 
//

Location

 

Commonwealth BuildingHammersmith Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Kouchaki:2019:bioinformatics/bty949,
author = {Kouchaki, S and Yang, Y and Walker, TM and Sarah, Walker A and Wilson, DJ and Peto, TEA and Crook, DW and Clifton, DA},
doi = {bioinformatics/bty949},
journal = {Bioinformatics},
pages = {2276--2282},
title = {Application of machine learning techniques to tuberculosis drug resistance analysis},
url = {http://dx.doi.org/10.1093/bioinformatics/bty949},
volume = {35},
year = {2019}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - 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.</jats:p>               </jats:sec>               <jats:sec>                  <jats:title>Results</jats:title>                  <jats:p>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.</jats:p>               </jats:sec>               <jats:sec>
AU  - Kouchaki,S
AU  - Yang,Y
AU  - Walker,TM
AU  - Sarah,Walker A
AU  - Wilson,DJ
AU  - Peto,TEA
AU  - Crook,DW
AU  - Clifton,DA
DO  - bioinformatics/bty949
EP  - 2282
PY  - 2019///
SN  - 1367-4803
SP  - 2276
TI  - Application of machine learning techniques to tuberculosis drug resistance analysis
T2  - Bioinformatics
UR  - http://dx.doi.org/10.1093/bioinformatics/bty949
UR  - https://academic.oup.com/bioinformatics/article/35/13/2276/5194336
UR  - http://hdl.handle.net/10044/1/72286
VL  - 35
ER  -
Download