Identification of Mycobacterium abscessus Subspecies by MALDI-TOF Mass Spectrometry and Machine Learning

被引:17
作者
Rodriguez-Temporal, David [1 ,2 ]
Herrera, Laura [3 ]
Alcaide, Fernando [4 ,5 ]
Domingo, Diego [6 ]
Hery-Arnaud, Genevieve [7 ,8 ]
van Ingen, Jakko [9 ]
Van den Bossche, An [10 ]
Ingebretsen, Andre [11 ]
Beauruelle, Clemence [7 ,8 ]
Terschlusen, Eva [9 ]
Boarbi, Samira [10 ]
Vila, Neus [4 ]
Arroyo, Manuel J. [12 ]
Mendez, Gema [12 ]
Munoz, Patricia [1 ,2 ,13 ,14 ]
Mancera, Luis [12 ]
Ruiz-Serrano, Maria Jesus [1 ]
Rodriguez-Sanchez, Belen [1 ,2 ]
机构
[1] Hosp Gen Univ Gregorio Maranon, Clin Microbiol & Infect Dis Dept, Madrid, Spain
[2] Inst Invest Sanitaria Gregorio Maranon, Madrid, Spain
[3] Inst Salud Carlos III, Ctr Nacl Microbiol, Serv Bacteriol, Majadahonda, Spain
[4] Hosp Univ Bellvitge IDIBELL, Serv Microbiol, Lhospitalet De Llobregat, Spain
[5] Univ Barcelona, Dept Patol & Terapeut Expt, Lhospitalet De Llobregat, Spain
[6] Hosp Univ La Princesa, Serv Microbiol, Madrid, Spain
[7] Brest Univ Hosp, Unit Bacteriol, Brest, France
[8] Brest Univ, INSERM, UMR 1078, GGB,Microbiota Axis, Brest, France
[9] Radboud Univ Nijmegen, Dept Med Microbiol, Med Ctr, Nijmegen, Netherlands
[10] Sciensano, Div Human Bacterial Dis, Brussels, Belgium
[11] Oslo Univ Hosp, Oslo, Norway
[12] Clover Bioanalyt Software, Granada, Spain
[13] CIBER Enfermedades Resp CIBERES CB06 06 0058, Madrid, Spain
[14] Univ Complutense Madrid, Fac Med, Med Dept, Madrid, Spain
关键词
Mycobacterium abscessus; subspecies differentiation; MALDI-TOF; mass spectrometry; machine learning; Mycobacterium bolletii; Mycobacterium massiliense; LASER-DESORPTION IONIZATION; TIME;
D O I
10.1128/jcm.01110-22
中图分类号
Q93 [微生物学];
学科分类号
071005 ; 100705 ;
摘要
Mycobacterium abscessus is one of the most common and pathogenic nontuberculous mycobacteria (NTM) isolated in clinical laboratories. It consists of three subspecies: M. abscessus subsp. abscessus, M. abscessus subsp. bolletii, and M. abscessus subsp. massiliense. Due to their different antibiotic susceptibility pattern, a rapid and accurate identification method is necessary for their differentiation. Although matrix-assisted laser desorption/ionization-time of flight mass spectrometry (MALDI-TOF MS) has proven useful for NTM identification, the differentiation of M. abscessus subspecies is challenging. In this study, a collection of 325 clinical isolates of M. abscessus was used for MALDI-TOF MS analysis and for the development of machine learning predictive models based on MALDI-TOF MS protein spectra. Overall, using a random forest model with several confidence criteria (samples by triplicate and similarity values >60%), a total of 96.5% of isolates were correctly identified at the subspecies level. Moreover, an improved model with Spanish isolates was able to identify 88.9% of strains collected in other countries. In addition, differences in culture media, colony morphology, and geographic origin of the strains were evaluated, showing that the latter had an impact on the protein spectra. Finally, after studying all protein peaks previously reported for this species, two novel peaks with potential for subspecies differentiation were found. Therefore, machine learning methodology has proven to be a promising approach for rapid and accurate identification of subspecies of M. abscessus using MALDI-TOF MS. Mycobacterium abscessus is one of the most common and pathogenic nontuberculous mycobacteria (NTM) isolated in clinical laboratories. It consists of three subspecies: M. abscessus subsp. abscessus, M. abscessus subsp. bolletii, and M. abscessus subsp. massiliense.
引用
收藏
页数:9
相关论文
共 50 条
  • [31] MALDI-TOF mass spectrometry and bacterial taxonomy
    Lay, JO
    TRAC-TRENDS IN ANALYTICAL CHEMISTRY, 2000, 19 (08) : 507 - 516
  • [32] Application of MALDI-TOF mass spectrometry in lipidomics
    Fuchs, Beate
    Schiller, Juergen
    EUROPEAN JOURNAL OF LIPID SCIENCE AND TECHNOLOGY, 2009, 111 (01) : 83 - 98
  • [33] MALDI-TOF mass spectrometry of hordeins: rapid approach for identification of malting barley varieties
    Salplachta, Jiri
    Bobalova, Janette
    JOURNAL OF MASS SPECTROMETRY, 2009, 44 (09): : 1287 - 1292
  • [34] Identification of dermatophyte species causing onychomycosis and tinea pedis by MALDI-TOF mass spectrometry
    Erhard, Marcel
    Hipler, Uta-Christina
    Burmester, Anke
    Brakhage, Axel A.
    Woestemeyer, Johannes
    EXPERIMENTAL DERMATOLOGY, 2008, 17 (04) : 356 - 361
  • [35] Evaluation of the MALDI-TOF mass spectrometry technique for the identification of dermatophytes: Use of an extended database
    Maldonado, Ivana
    Relloso, Silvia
    Guelfand, Liliana
    Fox, Barbara
    Azula, Natalia
    Romano, Vanesa
    Cantore, Agostina
    Barrios, Ruben
    Carnovale, Susana
    Nuske, Ezequiel
    Minervini, Patricia
    REVISTA IBEROAMERICANA DE MICOLOGIA, 2023, 40 (2-3): : 19 - 25
  • [36] Use of ribosomal proteins as biomarkers for identification of Flavobacterium psychrophilum by MALDI-TOF mass spectrometry
    Fernandez-Alvarez, Clara
    Tones-Corral, Yolanda
    Santos, Ysabel
    JOURNAL OF PROTEOMICS, 2018, 170 : 59 - 69
  • [37] MALDI-TOF mass spectrometry for early identification of bacteria grown in blood culture bottles
    Zabbe, Jean-Benoit
    Zanardo, Laura
    Megraud, Francis
    Bessede, Emilie
    JOURNAL OF MICROBIOLOGICAL METHODS, 2015, 115 : 45 - 46
  • [38] Catheter-related Mycobacterium fortuitum Bloodstream Infection: Rapid Identification Using MALDI-TOF Mass Spectrometry
    Artacho-Reinoso, M. J.
    Olbrich, P.
    Solano-Paez, P.
    Ybot-Gonzalez, P.
    Lepe, J. A.
    Neth, O.
    Aznar, J.
    KLINISCHE PADIATRIE, 2014, 226 (02): : 68 - 71
  • [39] OplAnalyzer: A toolbox for MALDI-TOF mass spectrometry data analysis
    Pham, Thang V.
    Jimenez, Connie R.
    ADVANCES IN MASS DATA ANALYSIS OF IMAGES AND SIGNALS IN MEDICINE, BIOTECHNOLOGY, CHEMISTRY AND FOOD INDUSTRY, PRCEEDINGS, 2008, 5108 : 73 - 81
  • [40] MALDI-TOF mass spectrometry-based SNP genotyping
    Pusch, W
    Wurmbach, JH
    Thiele, H
    Kostrzewa, M
    PHARMACOGENOMICS, 2002, 3 (04) : 537 - 548