@article{Yang:2019:bioinformatics/btz067,
author = {Yang, Y and Walker, TM and Walker, AS and Wilson, DJ and Peto, TEA and Crook, DW and Shamout, F and Zhu, T and Clifton, DA and Arandjelovic, I and Comas, I and Farhat, MR and Gao, Q and Sintchenko, V and van, Soolingen D and Hoosdally, S and Cruz, ALG and Carter, J and Grazian, C and Earle, SG and Kouchaki, S and Fowler, PW and Iqbal, Z and Hunt, M and Smith, EG and Rathod, P and Jarrett, L and Matias, D and Cirillo, DM and Borroni, E and Battaglia, S and Ghodousi, A and Spitaleri, A and Cabibbe, A and Tahseen, S and Nilgiriwala, K and Shah, S and Rodrigues, C and Kambli, P and Surve, U and Khot, R and Niemann, S and Kohl, T and Merker, M and Hoffmann, H and Molodtsov, N and Plesnik, S and Ismail, N and Omar, SV and Thwaites, G and Thuong, NTT and Nhung, HN and Srinivasan, V and Moore, D and Coronel, J and Solano, W and Gao, GF and He, G and Zhao, Y and Ma, A and Liu, C and Zhu, B and Laurenson, I and Claxton, P and Koch, A and Wilkinson, R and Lalvani, A and Posey, J and Gardy, J and },
doi = {bioinformatics/btz067},
journal = {Bioinformatics},
pages = {3240--3249},
title = {DeepAMR for predicting co-occurrent resistance of Mycobacterium tuberculosis},
url = {http://dx.doi.org/10.1093/bioinformatics/btz067},
volume = {35},
year = {2019}
}

Download

TY  - JOUR
AB  - MotivationResistance co-occurrence within first-line anti-tuberculosis (TB) drugs is a common phenomenon. Existing methods based on genetic data analysis of Mycobacterium tuberculosis (MTB) have been able to predict resistance of MTB to individual drugs, but have not considered the resistance co-occurrence and cannot capture latent structure of genomic data that corresponds to lineages.ResultsWe used a large cohort of TB patients from 16 countries across six continents where whole-genome sequences for each isolate and associated phenotype to anti-TB drugs were obtained using drug susceptibility testing recommended by the World Health Organization. We then proposed an end-to-end multi-task model with deep denoising auto-encoder (DeepAMR) for multiple drug classification and developed DeepAMR_cluster, a clustering variant based on DeepAMR, for learning clusters in latent space of the data. The results showed that DeepAMR outperformed baseline model and four machine learning models with mean AUROC from 94.4% to 98.7% for predicting resistance to four first-line drugs [i.e. isoniazid (INH), ethambutol (EMB), rifampicin (RIF), pyrazinamide (PZA)], multi-drug resistant TB (MDR-TB) and pan-susceptible TB (PANS-TB: MTB that is susceptible to all four first-line anti-TB drugs). In the case of INH, EMB, PZA and MDR-TB, DeepAMR achieved its best mean sensitivity of 94.3%, 91.5%, 87.3% and 96.3%, respectively. While in the case of RIF and PANS-TB, it generated 94.2% and 92.2% sensitivity, which were lower than baseline model by 0.7% and 1.9%, respectively. t-SNE visualization shows that DeepAMR_cluster captures lineage-related clusters in the latent space.Availability and implementationThe details of source code are provided at http://www.robots.ox.ac.uk/∼davidc/code.php.
AU  - Yang,Y
AU  - Walker,TM
AU  - Walker,AS
AU  - Wilson,DJ
AU  - Peto,TEA
AU  - Crook,DW
AU  - Shamout,F
AU  - Zhu,T
AU  - Clifton,DA
AU  - Arandjelovic,I
AU  - Comas,I
AU  - Farhat,MR
AU  - Gao,Q
AU  - Sintchenko,V
AU  - van,Soolingen D
AU  - Hoosdally,S
AU  - Cruz,ALG
AU  - Carter,J
AU  - Grazian,C
AU  - Earle,SG
AU  - Kouchaki,S
AU  - Fowler,PW
AU  - Iqbal,Z
AU  - Hunt,M
AU  - Smith,EG
AU  - Rathod,P
AU  - Jarrett,L
AU  - Matias,D
AU  - Cirillo,DM
AU  - Borroni,E
AU  - Battaglia,S
AU  - Ghodousi,A
AU  - Spitaleri,A
AU  - Cabibbe,A
AU  - Tahseen,S
AU  - Nilgiriwala,K
AU  - Shah,S
AU  - Rodrigues,C
AU  - Kambli,P
AU  - Surve,U
AU  - Khot,R
AU  - Niemann,S
AU  - Kohl,T
AU  - Merker,M
AU  - Hoffmann,H
AU  - Molodtsov,N
AU  - Plesnik,S
AU  - Ismail,N
AU  - Omar,SV
AU  - Thwaites,G
AU  - Thuong,NTT
AU  - Nhung,HN
AU  - Srinivasan,V
AU  - Moore,D
AU  - Coronel,J
AU  - Solano,W
AU  - Gao,GF
AU  - He,G
AU  - Zhao,Y
AU  - Ma,A
AU  - Liu,C
AU  - Zhu,B
AU  - Laurenson,I
AU  - Claxton,P
AU  - Koch,A
AU  - Wilkinson,R
AU  - Lalvani,A
AU  - Posey,J
AU  - Gardy,J
AU  - Werngren,J
AU  - Paton,N
AU  - Jou,R
AU  - Wu,M-H
AU  - Lin,W-H
AU  - Ferrazoli,L
AU  - de,Oliveira RS
DO  - bioinformatics/btz067
EP  - 3249
PY  - 2019///
SN  - 1367-4803
SP  - 3240
TI  - DeepAMR for predicting co-occurrent resistance of Mycobacterium tuberculosis
T2  - Bioinformatics
UR  - http://dx.doi.org/10.1093/bioinformatics/btz067
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000487327500005&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://academic.oup.com/bioinformatics/article/35/18/3240/5303535
UR  - http://hdl.handle.net/10044/1/77500
VL  - 35
ER  - 

Download