Multi-Label Random Forest Model for Tuberculosis Drug Resistance Classification and Mutation Ranking

Resistance prediction and mutation ranking are important tasks in the analysis of Tuberculosis sequence data. Due to standard regimens for the use of first-line antibiotics, resistance co-occurrence, in which samples are resistant to multiple drugs, is common. Analysing all drugs simultaneously shou...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Frontiers in microbiology Ročník 11; s. 667
Hlavní autori: Kouchaki, Samaneh, Yang, Yang, Lachapelle, Alexander, Walker, Timothy M., Walker, A. Sarah, Peto, Timothy E. A., Crook, Derrick W., Clifton, David A.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Switzerland Frontiers Media S.A 22.04.2020
Predmet:
ISSN:1664-302X, 1664-302X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Resistance prediction and mutation ranking are important tasks in the analysis of Tuberculosis sequence data. Due to standard regimens for the use of first-line antibiotics, resistance co-occurrence, in which samples are resistant to multiple drugs, is common. Analysing all drugs simultaneously should therefore enable patterns reflecting resistance co-occurrence to be exploited for resistance prediction. Here, multi-label random forest (MLRF) models are compared with single-label random forest (SLRF) for both predicting phenotypic resistance from whole genome sequences and identifying important mutations for better prediction of four first-line drugs in a dataset of 13402 isolates. Results confirmed that MLRFs can improve performance compared to conventional clinical methods (by 18.10%) and SLRFs (by 0.91%). In addition, we identified a list of candidate mutations that are important for resistance prediction or that are related to resistance co-occurrence. Moreover, we found that retraining our analysis to a subset of top-ranked mutations was sufficient to achieve satisfactory performance. The source code can be found at http://www.robots.ox.ac.uk/~davidc/code.php.
AbstractList Resistance prediction and mutation ranking are important tasks in the analysis of Tuberculosis sequence data. Due to standard regimens for the use of first-line antibiotics, resistance co-occurrence, in which samples are resistant to multiple drugs, is common. Analysing all drugs simultaneously should therefore enable patterns reflecting resistance co-occurrence to be exploited for resistance prediction. Here, multi-label random forest (MLRF) models are compared with single-label random forest (SLRF) for both predicting phenotypic resistance from whole genome sequences and identifying important mutations for better prediction of four first-line drugs in a dataset of 13402 isolates. Results confirmed that MLRFs can improve performance compared to conventional clinical methods (by 18.10%) and SLRFs (by 0.91%). In addition, we identified a list of candidate mutations that are important for resistance prediction or that are related to resistance co-occurrence. Moreover, we found that retraining our analysis to a subset of top-ranked mutations was sufficient to achieve satisfactory performance. The source code can be found at http://www.robots.ox.ac.uk/~davidc/code.php.
Resistance prediction and mutation ranking are important tasks in the analysis of Tuberculosis sequence data. Due to standard regimens for the use of first-line antibiotics, resistance co-occurrence, in which samples are resistant to multiple drugs, is common. Analysing all drugs simultaneously should therefore enable patterns reflecting resistance co-occurrence to be exploited for resistance prediction. Here, multi-label random forest (MLRF) models are compared with single-label random forest (SLRF) for both predicting phenotypic resistance from whole genome sequences and identifying important mutations for better prediction of four first-line drugs in a dataset of 13402 Mycobacterium tuberculosis isolates. Results confirmed that MLRFs can improve performance compared to conventional clinical methods (by 18.10%) and SLRFs (by 0.91%). In addition, we identified a list of candidate mutations that are important for resistance prediction or that are related to resistance co-occurrence. Moreover, we found that retraining our analysis to a subset of top-ranked mutations was sufficient to achieve satisfactory performance. The source code can be found at http://www.robots.ox.ac.uk/~davidc/code.php.
Resistance prediction and mutation ranking are important tasks in the analysis of Tuberculosis sequence data. Due to standard regimens for the use of first-line antibiotics, resistance co-occurrence, in which samples are resistant to multiple drugs, is common. Analysing all drugs simultaneously should therefore enable patterns reflecting resistance co-occurrence to be exploited for resistance prediction. Here, multi-label random forest (MLRF) models are compared with single-label random forest (SLRF) for both predicting phenotypic resistance from whole genome sequences and identifying important mutations for better prediction of four first-line drugs in a dataset of 13402 Mycobacterium tuberculosis isolates. Results confirmed that MLRFs can improve performance compared to conventional clinical methods (by 18.10%) and SLRFs (by 0.91%). In addition, we identified a list of candidate mutations that are important for resistance prediction or that are related to resistance co-occurrence. Moreover, we found that retraining our analysis to a subset of top-ranked mutations was sufficient to achieve satisfactory performance. The source code can be found at http://www.robots.ox.ac.uk/~davidc/code.php.Resistance prediction and mutation ranking are important tasks in the analysis of Tuberculosis sequence data. Due to standard regimens for the use of first-line antibiotics, resistance co-occurrence, in which samples are resistant to multiple drugs, is common. Analysing all drugs simultaneously should therefore enable patterns reflecting resistance co-occurrence to be exploited for resistance prediction. Here, multi-label random forest (MLRF) models are compared with single-label random forest (SLRF) for both predicting phenotypic resistance from whole genome sequences and identifying important mutations for better prediction of four first-line drugs in a dataset of 13402 Mycobacterium tuberculosis isolates. Results confirmed that MLRFs can improve performance compared to conventional clinical methods (by 18.10%) and SLRFs (by 0.91%). In addition, we identified a list of candidate mutations that are important for resistance prediction or that are related to resistance co-occurrence. Moreover, we found that retraining our analysis to a subset of top-ranked mutations was sufficient to achieve satisfactory performance. The source code can be found at http://www.robots.ox.ac.uk/~davidc/code.php.
Author Kouchaki, Samaneh
Walker, Timothy M.
Lachapelle, Alexander
Walker, A. Sarah
Clifton, David A.
Peto, Timothy E. A.
Yang, Yang
Crook, Derrick W.
AuthorAffiliation 3 Nuffield Department of Medicine, University of Oxford , Oxford , United Kingdom
6 NIHR Biomedical Research Centre , Oxford , United Kingdom
2 Oxford-Suzhou Centre for Advanced Research , Suzhou , China
5 Oxford University Clinical Research Unit , Ho Chi Minh City , Vietnam
1 Department of Engineering Science, Institute of Biomedical Engineering, University of Oxford , Oxford , United Kingdom
4 National Institute of Health Research Oxford Biomedical Research Centre, John Radcliffe Hospital , Oxford , United Kingdom
AuthorAffiliation_xml – name: 1 Department of Engineering Science, Institute of Biomedical Engineering, University of Oxford , Oxford , United Kingdom
– name: 2 Oxford-Suzhou Centre for Advanced Research , Suzhou , China
– name: 6 NIHR Biomedical Research Centre , Oxford , United Kingdom
– name: 3 Nuffield Department of Medicine, University of Oxford , Oxford , United Kingdom
– name: 5 Oxford University Clinical Research Unit , Ho Chi Minh City , Vietnam
– name: 4 National Institute of Health Research Oxford Biomedical Research Centre, John Radcliffe Hospital , Oxford , United Kingdom
Author_xml – sequence: 1
  givenname: Samaneh
  surname: Kouchaki
  fullname: Kouchaki, Samaneh
– sequence: 2
  givenname: Yang
  surname: Yang
  fullname: Yang, Yang
– sequence: 3
  givenname: Alexander
  surname: Lachapelle
  fullname: Lachapelle, Alexander
– sequence: 4
  givenname: Timothy M.
  surname: Walker
  fullname: Walker, Timothy M.
– sequence: 5
  givenname: A. Sarah
  surname: Walker
  fullname: Walker, A. Sarah
– sequence: 6
  givenname: Timothy E. A.
  surname: Peto
  fullname: Peto, Timothy E. A.
– sequence: 7
  givenname: Derrick W.
  surname: Crook
  fullname: Crook, Derrick W.
– sequence: 8
  givenname: David A.
  surname: Clifton
  fullname: Clifton, David A.
BackLink https://www.ncbi.nlm.nih.gov/pubmed/32390972$$D View this record in MEDLINE/PubMed
BookMark eNp1ks9vFCEUx4mpse3auyfD0cus_BoYLiZma2uT3Zg0NfFGgGFWKgMVZkz876U7rWlN5MLj8d7nhS_fU3AUU3QAvMFoTWkn3w-jt2ZNEEFrhDgXL8AJ5pw1FJFvR0_iY3BWyi2qi9VahF6BY0qoRFKQE9Dv5jD5ZquNC_Baxz6N8CJlVya4S33NDSnDm9m4bOeQii_wPM97eO1qOOloHdwEXYofvNWTTxFWBNzN03KowB8-7l-Dl4MOxZ097Cvw9eLTzeZzs_1yebX5uG0s42RquBGdZB0zgkreUqqd1RQzywyVkjkqhrpabjiuTxmc0EL2BlmCLR56KiRdgauF2yd9q-6yH3X-rZL26pBIea90nrwNThnkeN9J2WrRVVbVs-W0JRYjbIRkuLI-LKy72Yyuty5OWYdn0Oc30X9X-_RLCdx1XRV4Bd49AHL6OVdB1eiLdSHo6NJcFGEIYyxFy2rp26ez_g55_KZawJcCm1Mp2Q3K-kXiOtoHhZG6t4Q6WELdW0IdLFEb0T-Nj-z_tvwB-Bm6Xg
CitedBy_id crossref_primary_10_1002_cpe_6695
crossref_primary_10_1128_mbio_02852_24
crossref_primary_10_1093_bib_bbab299
crossref_primary_10_1109_ACCESS_2021_3096194
crossref_primary_10_1109_ACCESS_2020_3026758
crossref_primary_10_1109_ACCESS_2022_3216896
crossref_primary_10_1186_s12866_023_03147_7
crossref_primary_10_1093_bib_bbac041
crossref_primary_10_1016_j_bjid_2022_102332
crossref_primary_10_3389_fmed_2024_1386161
crossref_primary_10_1109_TCBB_2022_3148577
crossref_primary_10_1186_s12864_024_10066_y
crossref_primary_10_3390_microorganisms11081872
crossref_primary_10_1093_bib_bbae206
crossref_primary_10_3390_genes14010071
crossref_primary_10_1007_s11042_022_12716_3
crossref_primary_10_1109_TSE_2022_3212329
crossref_primary_10_56061_fbujohs_1636654
Cites_doi 10.1007/978-3-642-23808-6_10
10.1038/ncomms8119
10.1038/ng.2735
10.1128/AAC.00112-06
10.1186/1756-0500-4-504
10.1038/srep46327
10.1371/journal.pone.0033275
10.1056/NEJMoa1800474
10.3390/diagnostics9020049
10.1093/emph/eot003
10.1128/JCM.39.2.636-641.2001
10.1093/bioinformatics/bty949
10.1016/S1473-3099(15)00062-6
10.1186/s13073-015-0164-0
10.1093/bioinformatics/btx801
10.1007/978-3-642-33460-3_49
10.3389/fgene.2019.00922
10.1145/1014052.1014067
10.1164/rccm.201510-2091OC
10.1038/ng.3767
ContentType Journal Article
Copyright Copyright © 2020 Kouchaki, Yang, Lachapelle, Walker, Walker, CRyPTIC Consortium, Peto, Crook and Clifton.
Copyright © 2020 Kouchaki, Yang, Lachapelle, Walker, Walker, CRyPTIC Consortium, Peto, Crook and Clifton. 2020 Kouchaki, Yang, Lachapelle, Walker, Walker, CRyPTIC Consortium, Peto, Crook and Clifton
Copyright_xml – notice: Copyright © 2020 Kouchaki, Yang, Lachapelle, Walker, Walker, CRyPTIC Consortium, Peto, Crook and Clifton.
– notice: Copyright © 2020 Kouchaki, Yang, Lachapelle, Walker, Walker, CRyPTIC Consortium, Peto, Crook and Clifton. 2020 Kouchaki, Yang, Lachapelle, Walker, Walker, CRyPTIC Consortium, Peto, Crook and Clifton
CorporateAuthor CRyPTIC Consortium
CorporateAuthor_xml – name: CRyPTIC Consortium
DBID AAYXX
CITATION
NPM
7X8
5PM
DOA
DOI 10.3389/fmicb.2020.00667
DatabaseName CrossRef
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList PubMed

MEDLINE - Academic

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Biology
EISSN 1664-302X
ExternalDocumentID oai_doaj_org_article_b0e6d8995a784fe38956352c101b7941
PMC7188832
32390972
10_3389_fmicb_2020_00667
Genre Journal Article
GrantInformation_xml – fundername: Wellcome Trust
  grantid: 200205/Z/15/Z
– fundername: Medical Research Council
  grantid: MC_PC_16027
– fundername: Wellcome Trust
– fundername: Medical Research Council
– fundername: Bill and Melinda Gates Foundation
– fundername: Newton Fund
GroupedDBID 53G
5VS
9T4
AAFWJ
AAKDD
AAYXX
ACGFO
ACGFS
ADBBV
ADRAZ
AENEX
AFPKN
ALMA_UNASSIGNED_HOLDINGS
AOIJS
BAWUL
BCNDV
CITATION
DIK
ECGQY
GROUPED_DOAJ
GX1
HYE
KQ8
M48
M~E
O5R
O5S
OK1
PGMZT
RNS
RPM
ACXDI
IPNFZ
NPM
RIG
7X8
5PM
ID FETCH-LOGICAL-c462t-6b789484b7396533aeca314c4b3994e37ffff56b61004fe7a79db0c21c1fd3793
IEDL.DBID DOA
ISICitedReferencesCount 22
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000531636700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1664-302X
IngestDate Fri Oct 03 12:50:36 EDT 2025
Tue Sep 30 16:24:24 EDT 2025
Thu Sep 04 18:36:15 EDT 2025
Sat May 31 02:12:33 EDT 2025
Tue Nov 18 22:01:52 EST 2025
Sat Nov 29 03:09:04 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords mutation ranking
SLRF
drug resistance
MLRF
tuberculosis
Language English
License Copyright © 2020 Kouchaki, Yang, Lachapelle, Walker, Walker, CRyPTIC Consortium, Peto, Crook and Clifton.
This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c462t-6b789484b7396533aeca314c4b3994e37ffff56b61004fe7a79db0c21c1fd3793
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Reviewed by: Francesc Coll, University of London, United Kingdom; Wouter Deelder, University of London, United Kingdom
Edited by: Miguel Viveiros, New University of Lisbon, Portugal
This article was submitted to Antimicrobials, Resistance and Chemotherapy, a section of the journal Frontiers in Microbiology
OpenAccessLink https://doaj.org/article/b0e6d8995a784fe38956352c101b7941
PMID 32390972
PQID 2401119754
PQPubID 23479
ParticipantIDs doaj_primary_oai_doaj_org_article_b0e6d8995a784fe38956352c101b7941
pubmedcentral_primary_oai_pubmedcentral_nih_gov_7188832
proquest_miscellaneous_2401119754
pubmed_primary_32390972
crossref_citationtrail_10_3389_fmicb_2020_00667
crossref_primary_10_3389_fmicb_2020_00667
PublicationCentury 2000
PublicationDate 2020-04-22
PublicationDateYYYYMMDD 2020-04-22
PublicationDate_xml – month: 04
  year: 2020
  text: 2020-04-22
  day: 22
PublicationDecade 2020
PublicationPlace Switzerland
PublicationPlace_xml – name: Switzerland
PublicationTitle Frontiers in microbiology
PublicationTitleAlternate Front Microbiol
PublicationYear 2020
Publisher Frontiers Media S.A
Publisher_xml – name: Frontiers Media S.A
References Evgeniou (B6) 2004
Schleusener (B15) 2017; 7
Manson (B13) 2017; 49
Sechidis (B16) 2011
Deelder (B4) 2019; 10
Hazbón (B10) 2006; 50
Van Rie (B17) 2001; 39
Eldholm (B5) 2015; 6
Farhat (B8) 2016; 194
Georghiou (B9) 2012; 7
Walker (B18) 2015; 15
Zhang (B21) 2013; 45
Khan (B11) 2019; 9
Periwal (B14) 2011; 4
(B19) 2017
Borrell (B1) 2013; 2013
Kouchaki (B12) 2019; 35
Coll (B2) 2015; 7
(B3) 2018; 379
Yang (B20) 2018; 34
Faddoul (B7) 2012
References_xml – start-page: 145
  volume-title: Joint European Conference on Machine Learning and Knowledge Discovery in Databases
  year: 2011
  ident: B16
  article-title: “On the stratification of multi-label data,”
  doi: 10.1007/978-3-642-23808-6_10
– volume: 6
  start-page: 7119
  year: 2015
  ident: B5
  article-title: Four decades of transmission of a multidrug-resistant mycobacterium tuberculosis outbreak strain
  publication-title: Nat. Commun
  doi: 10.1038/ncomms8119
– volume: 45
  start-page: 1255
  year: 2013
  ident: B21
  article-title: Genome sequencing of 161 Mycobacterium tuberculosis isolates from china identifies genes and intergenic regions associated with drug resistance
  publication-title: Nat. Genet
  doi: 10.1038/ng.2735
– volume: 50
  start-page: 2640
  year: 2006
  ident: B10
  article-title: Population genetics study of isoniazid resistance mutations and evolution of multidrug-resistant Mycobacterium tuberculosis
  publication-title: Antimicrob. Agents Chemother
  doi: 10.1128/AAC.00112-06
– volume: 4
  start-page: 504
  year: 2011
  ident: B14
  article-title: Predictive models for anti-tubercular molecules using machine learning on high-throughput biological screening datasets
  publication-title: BMC Res. Notes
  doi: 10.1186/1756-0500-4-504
– volume: 7
  start-page: 46327
  year: 2017
  ident: B15
  article-title: Mycobacterium tuberculosis resistance prediction and lineage classification from genome sequencing: comparison of automated analysis tools
  publication-title: Sci. Rep
  doi: 10.1038/srep46327
– volume: 7
  start-page: e33275
  year: 2012
  ident: B9
  article-title: Evaluation of genetic mutations associated with Mycobacterium tuberculosis resistance to amikacin, kanamycin and capreomycin: a systematic review
  publication-title: PLoS ONE
  doi: 10.1371/journal.pone.0033275
– volume: 379
  start-page: 1403
  year: 2018
  ident: B3
  article-title: Prediction of susceptibility to first-line tuberculosis drugs by DNA sequencing
  publication-title: N. Engl. J. Med
  doi: 10.1056/NEJMoa1800474
– volume: 9
  start-page: 49
  year: 2019
  ident: B11
  article-title: Current and emerging methods of antibiotic susceptibility testing
  publication-title: Diagnostics
  doi: 10.3390/diagnostics9020049
– volume: 2013
  start-page: 65
  year: 2013
  ident: B1
  article-title: Epistasis between antibiotic resistance mutations drives the evolution of extensively drug-resistant tuberculosis
  publication-title: Evol. Med. Public Health
  doi: 10.1093/emph/eot003
– year: 2017
  ident: B19
  publication-title: Who Meeting Report of a Technical Expert Consultation: Non-Inferiority Analysis of Xpert MTB/RIF
– volume: 39
  start-page: 636
  year: 2001
  ident: B17
  article-title: Analysis for a limited number of gene codons can predict drug resistance of Mycobacterium tuberculosis in a high-incidence community
  publication-title: J. Clin. Microbiol
  doi: 10.1128/JCM.39.2.636-641.2001
– volume: 35
  start-page: 2276
  year: 2019
  ident: B12
  article-title: Application of machine learning techniques to tuberculosis drug resistance analysis
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/bty949
– volume: 15
  start-page: 1193
  year: 2015
  ident: B18
  article-title: Whole-genome sequencing for prediction of Mycobacterium tuberculosis drug susceptibility and resistance: a retrospective cohort study
  publication-title: Lancet Infect. Dis
  doi: 10.1016/S1473-3099(15)00062-6
– volume: 7
  start-page: 51
  year: 2015
  ident: B2
  article-title: Rapid determination of anti-tuberculosis drug resistance from whole-genome sequences
  publication-title: Genome Med
  doi: 10.1186/s13073-015-0164-0
– volume: 34
  start-page: 1666
  year: 2018
  ident: B20
  article-title: Machine learning for classifying tuberculosis drug-resistance from dna sequencing data
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btx801
– start-page: 681
  volume-title: Joint European Conference on Machine Learning and Knowledge Discovery in Databases
  year: 2012
  ident: B7
  article-title: “Learning multiple tasks with boosted decision trees,”
  doi: 10.1007/978-3-642-33460-3_49
– volume: 10
  start-page: 922
  year: 2019
  ident: B4
  article-title: Machine learning predicts accurately Mycobacterium tuberculosis drug resistance from whole genome sequencing data
  publication-title: Front. Genet
  doi: 10.3389/fgene.2019.00922
– start-page: 109
  volume-title: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
  year: 2004
  ident: B6
  article-title: Regularized multi-task learning,”
  doi: 10.1145/1014052.1014067
– volume: 194
  start-page: 621
  year: 2016
  ident: B8
  article-title: Genetic determinants of drug resistance in Mycobacterium tuberculosis and their diagnostic value
  publication-title: Am. J. Respir. Critical Care Med
  doi: 10.1164/rccm.201510-2091OC
– volume: 49
  start-page: 395
  year: 2017
  ident: B13
  article-title: Genomic analysis of globally diverse Mycobacterium tuberculosis strains provides insights into the emergence and spread of multidrug resistance
  publication-title: Nat. Genet
  doi: 10.1038/ng.3767
SSID ssj0000402000
Score 2.3909695
Snippet Resistance prediction and mutation ranking are important tasks in the analysis of Tuberculosis sequence data. Due to standard regimens for the use of...
SourceID doaj
pubmedcentral
proquest
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage 667
SubjectTerms drug resistance
Microbiology
MLRF
mutation ranking
SLRF
tuberculosis
Title Multi-Label Random Forest Model for Tuberculosis Drug Resistance Classification and Mutation Ranking
URI https://www.ncbi.nlm.nih.gov/pubmed/32390972
https://www.proquest.com/docview/2401119754
https://pubmed.ncbi.nlm.nih.gov/PMC7188832
https://doaj.org/article/b0e6d8995a784fe38956352c101b7941
Volume 11
WOSCitedRecordID wos000531636700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1664-302X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000402000
  issn: 1664-302X
  databaseCode: DOA
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1664-302X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000402000
  issn: 1664-302X
  databaseCode: M~E
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELagAokLgvLaQitX4sIhamI7fhyBtuqhraqqoL1ZfgVW2mbRZoPUC7-dGWe77CJEL80hh8RxnJmxZyYzno-Q94bphjfGF02MvBCNqwsvkiyCU7JmWvKUoRO-nqrzcz0em4s1qC_MCRvKAw-EO_BlkhGcgtopLZoE-rUGHckCiJIHWcqOT6nMmjOV12B0i8pyiEuCF2aATZPgwR9kOZUrw8r_0UO5XP-_bMy_UyXXdM_xM_J0aTTSj8Ngn5MHqd0mjwcYyZsXJOZdtMWp82lKL10bZ9cUITe7BUWosykFw5Re9T7NQz-ddZOOHs77b_QydWg8AtdphsbEpKHMJwpd0LN-CNJjh_g7_SX5cnx09fmkWKInFEFItiikV9oILbziRoJR51JwvBJBeLBJROKqgaOWXmLNuCYpp0z0ZWBVqJrIYdq-IlvtrE1vCOUsOtxLouogRBTGgZulmAxR6qhUJUbk4JaWNixLiyPCxdSCi4HUt5n6FqlvM_VH5MPqiR9DWY3_tP2E7Fm1w4LY-QKIiV2Kib1LTEZk_5a5FiYQRkVcm2Z9Z8GkqTCWWsNnvB6YvXoVZ9xgfaMRURtisDGWzTvt5Hsu0g06X8NquXMfg39LniA5MIjF2DuytZj3aZc8Cj8Xk26-Rx6qsd7L8g_ns19HvwHVjAm0
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Multi-Label+Random+Forest+Model+for+Tuberculosis+Drug+Resistance+Classification+and+Mutation+Ranking&rft.jtitle=Frontiers+in+microbiology&rft.au=Samaneh+Kouchaki&rft.au=Yang+Yang&rft.au=Yang+Yang&rft.au=Alexander+Lachapelle&rft.date=2020-04-22&rft.pub=Frontiers+Media+S.A&rft.eissn=1664-302X&rft.volume=11&rft_id=info:doi/10.3389%2Ffmicb.2020.00667&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_b0e6d8995a784fe38956352c101b7941
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1664-302X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1664-302X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1664-302X&client=summon