Combining comparative genomic analysis with machine learning reveals some promising diagnostic markers to identify five common pathogenic non‐tuberculous mycobacteria
Summary Non‐tuberculous mycobacteria (NTM) can cause various respiratory diseases and even death in severe cases, and its incidence has increased rapidly worldwide. To date, it’s difficult to use routine diagnostic methods and strain identification to precisely diagnose various types of NTM infectio...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-07-01
|
Series: | Microbial Biotechnology |
Online Access: | https://doi.org/10.1111/1751-7915.13815 |
id |
doaj-bcf3b6ba06dc40cc8737622ec983aa4d |
---|---|
record_format |
Article |
spelling |
doaj-bcf3b6ba06dc40cc8737622ec983aa4d2021-07-26T21:47:23ZengWileyMicrobial Biotechnology1751-79152021-07-011441539154910.1111/1751-7915.13815Combining comparative genomic analysis with machine learning reveals some promising diagnostic markers to identify five common pathogenic non‐tuberculous mycobacteriaXinmiao Jia0Linfang Yang1Cuidan Li2Yingchun Xu3Qiwen Yang4Fei Chen5Medical Research Center State Key laboratory of Complex Severe and Rare Diseases Peking Union Medical College Hospital Peking Union Medical College Beijing 100730 ChinaDepartments of Dermatology Affiliated Xingtai People’s Hospital of Hebei Medical University Xingtai, Hebei 054001 ChinaCAS Key Laboratory of Genome Sciences & Information China National Center for Bioinformation Chinese Academy of Sciences Beijing Institute of Genomics Beijing 100101 ChinaDepartment of Clinical Laboratory State Key laboratory of Complex Severe and Rare Diseases Peking Union Medical College Hospital Peking Union Medical College Chinese Academy of Medical Sciences Beijing 100730 ChinaDepartment of Clinical Laboratory State Key laboratory of Complex Severe and Rare Diseases Peking Union Medical College Hospital Peking Union Medical College Chinese Academy of Medical Sciences Beijing 100730 ChinaCAS Key Laboratory of Genome Sciences & Information China National Center for Bioinformation Chinese Academy of Sciences Beijing Institute of Genomics Beijing 100101 ChinaSummary Non‐tuberculous mycobacteria (NTM) can cause various respiratory diseases and even death in severe cases, and its incidence has increased rapidly worldwide. To date, it’s difficult to use routine diagnostic methods and strain identification to precisely diagnose various types of NTM infections. We combined systematic comparative genomics with machine learning to select new diagnostic markers for precisely identifying five common pathogenic NTMs (Mycobacterium kansasii, Mycobacterium avium, Mycobacterium intracellular, Mycobacterium chelonae, Mycobacterium abscessus). A panel including six genes and two SNPs (nikA, benM, codA, pfkA2, mpr, yjcH, rrl C2638T, rrl A1173G) was selected to simultaneously identify the five NTMs with high accuracy (> 90%). Notably, the panel only containing the six genes also showed a good classification effect (accuracy > 90%). Additionally, the two panels could precisely differentiate the five NTMs from M. tuberculosis (accuracy > 99%). We also revealed some new marker genes/SNPs/combinations to accurately discriminate any one of the five NTMs separately, which provided the possibility to diagnose one certain NTM infection precisely. Our research not only reveals novel promising diagnostic markers to promote the development of precision diagnosis in NTM infectious, but also provides an insight into precisely identifying various genetically close pathogens through comparative genomics and machine learning.https://doi.org/10.1111/1751-7915.13815 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xinmiao Jia Linfang Yang Cuidan Li Yingchun Xu Qiwen Yang Fei Chen |
spellingShingle |
Xinmiao Jia Linfang Yang Cuidan Li Yingchun Xu Qiwen Yang Fei Chen Combining comparative genomic analysis with machine learning reveals some promising diagnostic markers to identify five common pathogenic non‐tuberculous mycobacteria Microbial Biotechnology |
author_facet |
Xinmiao Jia Linfang Yang Cuidan Li Yingchun Xu Qiwen Yang Fei Chen |
author_sort |
Xinmiao Jia |
title |
Combining comparative genomic analysis with machine learning reveals some promising diagnostic markers to identify five common pathogenic non‐tuberculous mycobacteria |
title_short |
Combining comparative genomic analysis with machine learning reveals some promising diagnostic markers to identify five common pathogenic non‐tuberculous mycobacteria |
title_full |
Combining comparative genomic analysis with machine learning reveals some promising diagnostic markers to identify five common pathogenic non‐tuberculous mycobacteria |
title_fullStr |
Combining comparative genomic analysis with machine learning reveals some promising diagnostic markers to identify five common pathogenic non‐tuberculous mycobacteria |
title_full_unstemmed |
Combining comparative genomic analysis with machine learning reveals some promising diagnostic markers to identify five common pathogenic non‐tuberculous mycobacteria |
title_sort |
combining comparative genomic analysis with machine learning reveals some promising diagnostic markers to identify five common pathogenic non‐tuberculous mycobacteria |
publisher |
Wiley |
series |
Microbial Biotechnology |
issn |
1751-7915 |
publishDate |
2021-07-01 |
description |
Summary Non‐tuberculous mycobacteria (NTM) can cause various respiratory diseases and even death in severe cases, and its incidence has increased rapidly worldwide. To date, it’s difficult to use routine diagnostic methods and strain identification to precisely diagnose various types of NTM infections. We combined systematic comparative genomics with machine learning to select new diagnostic markers for precisely identifying five common pathogenic NTMs (Mycobacterium kansasii, Mycobacterium avium, Mycobacterium intracellular, Mycobacterium chelonae, Mycobacterium abscessus). A panel including six genes and two SNPs (nikA, benM, codA, pfkA2, mpr, yjcH, rrl C2638T, rrl A1173G) was selected to simultaneously identify the five NTMs with high accuracy (> 90%). Notably, the panel only containing the six genes also showed a good classification effect (accuracy > 90%). Additionally, the two panels could precisely differentiate the five NTMs from M. tuberculosis (accuracy > 99%). We also revealed some new marker genes/SNPs/combinations to accurately discriminate any one of the five NTMs separately, which provided the possibility to diagnose one certain NTM infection precisely. Our research not only reveals novel promising diagnostic markers to promote the development of precision diagnosis in NTM infectious, but also provides an insight into precisely identifying various genetically close pathogens through comparative genomics and machine learning. |
url |
https://doi.org/10.1111/1751-7915.13815 |
work_keys_str_mv |
AT xinmiaojia combiningcomparativegenomicanalysiswithmachinelearningrevealssomepromisingdiagnosticmarkerstoidentifyfivecommonpathogenicnontuberculousmycobacteria AT linfangyang combiningcomparativegenomicanalysiswithmachinelearningrevealssomepromisingdiagnosticmarkerstoidentifyfivecommonpathogenicnontuberculousmycobacteria AT cuidanli combiningcomparativegenomicanalysiswithmachinelearningrevealssomepromisingdiagnosticmarkerstoidentifyfivecommonpathogenicnontuberculousmycobacteria AT yingchunxu combiningcomparativegenomicanalysiswithmachinelearningrevealssomepromisingdiagnosticmarkerstoidentifyfivecommonpathogenicnontuberculousmycobacteria AT qiwenyang combiningcomparativegenomicanalysiswithmachinelearningrevealssomepromisingdiagnosticmarkerstoidentifyfivecommonpathogenicnontuberculousmycobacteria AT feichen combiningcomparativegenomicanalysiswithmachinelearningrevealssomepromisingdiagnosticmarkerstoidentifyfivecommonpathogenicnontuberculousmycobacteria |
_version_ |
1721280681806397440 |