1
|
Kim E, Yang SM, Ham JH, Lee W, Jung DH, Kim HY. Integration of MALDI-TOF MS and machine learning to classify enterococci: A comparative analysis of supervised learning algorithms for species prediction. Food Chem 2025; 462:140931. [PMID: 39217752 DOI: 10.1016/j.foodchem.2024.140931] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2024] [Revised: 07/26/2024] [Accepted: 08/19/2024] [Indexed: 09/04/2024]
Abstract
This research focused on distinguishing distinct matrix assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) spectral signatures of three Enterococcus species. We evaluated and compared the predictive performance of four supervised machine learning algorithms, K-nearest neighbor (KNN), support vector machine (SVM), and random forest (RF), to accurately classify Enterococcus species. This study involved a comprehensive dataset of 410 strains, generating 1640 individual spectra through on-plate and off-plate protein extraction methods. Although the commercial database correctly identified 76.9% of the strains, machine learning classifiers demonstrated superior performance (accuracy 0.991). In the RF model, top informative peaks played a significant role in the classification. Whole-genome sequencing showed that the most informative peaks are biomarkers connected to proteins, which are essential for understanding bacterial classification and evolution. The integration of MALDI-TOF MS and machine learning provides a rapid and accurate method for identifying Enterococcus species, improving healthcare and food safety.
Collapse
Affiliation(s)
- Eiseul Kim
- Institute of Life Sciences & Resources and Department of Food Science and Biotechnology, Kyung Hee University, Yongin 17104, Republic of Korea
| | - Seung-Min Yang
- Institute of Life Sciences & Resources and Department of Food Science and Biotechnology, Kyung Hee University, Yongin 17104, Republic of Korea
| | - Jun-Hyeok Ham
- Institute of Life Sciences & Resources and Department of Food Science and Biotechnology, Kyung Hee University, Yongin 17104, Republic of Korea
| | - Woojung Lee
- Institute of Life Sciences & Resources and Department of Food Science and Biotechnology, Kyung Hee University, Yongin 17104, Republic of Korea
| | - Dae-Hyun Jung
- Department of Smart Farm Science, Kyung Hee University, Yongin 17104, Republic of Korea
| | - Hae-Yeong Kim
- Institute of Life Sciences & Resources and Department of Food Science and Biotechnology, Kyung Hee University, Yongin 17104, Republic of Korea.
| |
Collapse
|
2
|
Kim SH, Chon JW, Jeong HW, Song KY, Kim DH, Bae D, Kim H, Seo KH. Identification and phylogenetic analysis of Enterococcus isolates using MALDI-TOF MS and VITEK 2. AMB Express 2023; 13:21. [PMID: 36813859 PMCID: PMC9947212 DOI: 10.1186/s13568-023-01525-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/05/2022] [Accepted: 02/07/2023] [Indexed: 02/24/2023] Open
Abstract
The bacterial genus Enterococcus encompasses 38 species. Two of the most common species are E. faecalis and E. faecium. Recently, however, there has been an increase in clinical reports concerning less prevalent Enterococcus species, such as E. durans, E. hirae, and E. gallinarum. Rapid and accurate laboratory methods are needed to facilitate the identification of all these bacterial species. In the present study, we compared the relative accuracy of matrix-assisted laser desorption/ionisation time-of-flight mass spectrometry (MALDI-TOF MS), VITEK 2, and 16S rRNA gene sequencing using 39 enterococci isolates from dairy samples, and compared the resultant phylogenetic trees. We found that MALDI-TOF MS correctly identified all isolates at the species level except for one, whereas the VITEK 2 system, which is an automated identification system using biochemical characteristics of species, misidentified ten isolates. However, phylogenetic trees constructed from both methods showed all isolates in similar positions. Our results clearly showed that MALDI-TOF MS is a reliable and rapid tool for identifying Enterococcus species with greater discriminatory power than the biochemical assay method of VITEK 2.
Collapse
Affiliation(s)
- Se-Hyung Kim
- grid.258676.80000 0004 0532 8339Center for One Health, Department of Veterinary Public Health, College of Veterinary Medicine, Konkuk University, 120 Neungdong-ro, Gwangjin-gu, Seoul, 05029 Korea
| | - Jung-Whan Chon
- grid.258676.80000 0004 0532 8339Center for One Health, Department of Veterinary Public Health, College of Veterinary Medicine, Konkuk University, 120 Neungdong-ro, Gwangjin-gu, Seoul, 05029 Korea
| | - Hyo-Won Jeong
- grid.484628.4 0000 0001 0943 2764Seoul Metropolitan Government Research Institute of Public Health and Environment, Gyonggi-Do, 13818 Korea
| | - Kwang-Young Song
- grid.258676.80000 0004 0532 8339Center for One Health, Department of Veterinary Public Health, College of Veterinary Medicine, Konkuk University, 120 Neungdong-ro, Gwangjin-gu, Seoul, 05029 Korea
| | - Dong-Hyeon Kim
- grid.258676.80000 0004 0532 8339Center for One Health, Department of Veterinary Public Health, College of Veterinary Medicine, Konkuk University, 120 Neungdong-ro, Gwangjin-gu, Seoul, 05029 Korea
| | - Dongryeoul Bae
- grid.258676.80000 0004 0532 8339Center for One Health, Department of Veterinary Public Health, College of Veterinary Medicine, Konkuk University, 120 Neungdong-ro, Gwangjin-gu, Seoul, 05029 Korea
| | - Hyunsook Kim
- grid.49606.3d0000 0001 1364 9317Department of Food and Nutrition, College of Human Ecology, Hanyang Univeristy, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763 Korea
| | - Kun-Ho Seo
- Center for One Health, Department of Veterinary Public Health, College of Veterinary Medicine, Konkuk University, 120 Neungdong-ro, Gwangjin-gu, Seoul, 05029, Korea.
| |
Collapse
|
3
|
Xiong L, Long X, Ni L, Wang L, Zhang Y, Cui L, Guo J, Yang C. Comparison of Autof Ms1000 and EXS3000 MALDI-TOF MS Platforms for Routine Identification of Microorganisms. Infect Drug Resist 2023; 16:913-921. [PMID: 36814830 PMCID: PMC9939805 DOI: 10.2147/idr.s352307] [Citation(s) in RCA: 8] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/03/2021] [Accepted: 12/20/2022] [Indexed: 02/16/2023] Open
Abstract
Purpose Matrix-assisted laser desorption-ionization-time of flight mass spectrometry (MALDI-TOF) has recently been widely used in clinical microbiology laboratories, with the advantages of being reliable, rapid, and cost-effective. Here, we reported the performance of two MALDI-TOF MS instruments, EXS3000 (Zybio, China) and Autof ms1000 (Autobio, China), which are commonly used in clinical microbiology field. Methods A total of 209 common clinical common isolates, including 70 gram-negative bacteria strains, 58 gram-positive bacteria strains, 33 yeast strains, 15 anaerobic bacteria strains, and 33 mold strains, and 19 mycobacterial strains were tested. All strains were identified by EXS3000 (Zybio, China) and Autof ms1000 (Autobio, China). Sequence analysis of 16S rRNA or ITS regions was used to verify all strains. Results Current study found that species-level discrimination was found to be 191 (91.39%) and 190 (90.91%) by EXS3000 and Autof ms1000, respectively. Genus-level discrimination was 205 (98.09%) by the EXS3000 and 205 (98.09%) by the Autof ms1000, respectively. The correct results at species level of the EXS3000 were 91.43% (64/70) for gram-negative bacteria, 93.1% (54/58) for gram-positive cocci, 93.94% (31/33) for yeast, 100% (15/15) for anaerobes and 81.82% (27/33) for filamentous fungi. The correct results at species level of the Autof ms1000 were 92.86% (65/70) for gram-negative bacteria, 91.38% (53/58) for gram-positive cocci, 93.94% (31/33) for yeast, 100% (15/15) for anaerobes and 78.79% (26/33) for filamentous fungi. Conclusion Although the results show that the EXS3000 and Autof ms1000 systems are equally good choices in terms of analytical efficiency for routine procedures, the test result of EXS3000 is slightly better than Autof ms1000. It's worth mentioning that the target plate of the EXS 3000 instrument is reusable, but the target plate of the Autof ms1000 is disposable, making the EXS3000 more effective in reducing costs.
Collapse
Affiliation(s)
- Lijuan Xiong
- Department of Laboratory Medicine, the Second Affiliated Hospital of Guizhou University of Traditional Chinese Medicine, Guizhou, People’s Republic of China
| | - Xu Long
- Department of Laboratory Medicine, the Second Affiliated Hospital of Guizhou University of Traditional Chinese Medicine, Guizhou, People’s Republic of China
| | - Lijun Ni
- Department of Laboratory Medicine, Shanghai East Hospital, Tongji University School of Medicine, Shanghai, People’s Republic of China
| | - Lili Wang
- Department of Laboratory Medicine, Shanghai East Hospital, Tongji University School of Medicine, Shanghai, People’s Republic of China
| | - Yang Zhang
- Department of Laboratory Medicine, the Second Affiliated Hospital of Guizhou University of Traditional Chinese Medicine, Guizhou, People’s Republic of China
| | - Lili Cui
- Department of Laboratory Medicine, the Second Affiliated Hospital of Guizhou University of Traditional Chinese Medicine, Guizhou, People’s Republic of China
| | - Jian Guo
- Department of Laboratory Medicine, Shanghai East Hospital, Tongji University School of Medicine, Shanghai, People’s Republic of China,Correspondence: Jian Guo, Department of Laboratory Medicine, Shanghai East Hospital, Tongji University School of Medicine, No. 1800 Yuntai Road, Pudong New Area, Shanghai, People’s Republic of China, Tel +86-17701810639, Email
| | - Chunying Yang
- Department of Laboratory Medicine, the Second Affiliated Hospital of Guizhou University of Traditional Chinese Medicine, Guizhou, People’s Republic of China,Chunying Yang, Department of Laboratory Medicine, the Second Affiliated Hospital of Guizhou University of Traditional Chinese Medicine, No. 83 Feishan Street, Yunyan District, Guiyang City, Guizhou Province, People’s Republic of China, Tel +86-13658504875, Email
| |
Collapse
|
4
|
Virulence Factor Genes and Cytotoxicity of Streptococcus agalactiae Isolated from Bovine Mastitis in Poland. Microbiol Spectr 2022; 10:e0222421. [PMID: 35608349 PMCID: PMC9241884 DOI: 10.1128/spectrum.02224-21] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022] Open
Abstract
Streptococcus agalactiae can produce a wide variety of virulence factors, including toxins and proteins which facilitate adhesion to and colonization and invasion of the host cells. There are few reports on the characteristics of field isolates from bovine mastitis in Poland. Thus, the aim of this study was to determine the occurrence of types of hemolysis on blood agar, virulence factor genes, and cytotoxicity of S. agalactiae isolates derived from cows with mastitis across Poland. The study included 68 isolates. Virulence genes were tested using standard PCR, and cytotoxicity was determined using methylthiazol tetrazolium (MTT) and lactate dehydrogenase (LDH) tests. Among the tested isolates, 89.7% were β-hemolytic, 8.8% γ-hemolytic, and 1.5% alpha-hemolytic. The only genes detected in all isolates were the cfb, cspA, hylB, and sip genes. Cytotoxicity assessment based on the LDH test revealed that isolates were cytotoxic only to Vero cells. However, according to the results obtained from the MTT test, more than half of the isolates exhibited low cytotoxicity to both SK and Vero cells, whereas the other isolates showed moderate or no cytotoxicity to both cell lines. Our research confirms the prevalence of various virulence genes in S. agalactiae isolated from Polish dairy herds, which have previously been found in isolates recovered from human and animal infections. For the first time, the presence of bac- and scpB-positive isolates of S. agalactiae was determined in Polish dairy cattle, and the cytotoxicity of bovine isolates was assessed. IMPORTANCE We believe that this manuscript is one of the few reports on the characteristics of field S. agalactiae isolates derived from cases of bovine mastitis in cows in Poland in terms of the occurrence of virulence genes and cytotoxicity. For the first time, the presence of bac- and scpB-positive isolates of S. agalactiae was determined in Polish dairy cattle, and the cytotoxicity of bovine isolates was assessed.
Collapse
|
5
|
Lüftinger L, Ferreira I, Frank BJH, Beisken S, Weinberger J, von Haeseler A, Rattei T, Hofstaetter JG, Posch AE, Materna A. Predictive Antibiotic Susceptibility Testing by Next-Generation Sequencing for Periprosthetic Joint Infections: Potential and Limitations. Biomedicines 2021; 9:910. [PMID: 34440114 PMCID: PMC8389688 DOI: 10.3390/biomedicines9080910] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/09/2021] [Revised: 07/21/2021] [Accepted: 07/22/2021] [Indexed: 01/18/2023] Open
Abstract
Joint replacement surgeries are one of the most frequent medical interventions globally. Infections of prosthetic joints are a major health challenge and typically require prolonged or even indefinite antibiotic treatment. As multidrug-resistant pathogens continue to rise globally, novel diagnostics are critical to ensure appropriate treatment and help with prosthetic joint infections (PJI) management. To this end, recent studies have shown the potential of molecular methods such as next-generation sequencing to complement established phenotypic, culture-based methods. Together with advanced bioinformatics approaches, next-generation sequencing can provide comprehensive information on pathogen identity as well as antimicrobial susceptibility, potentially enabling rapid diagnosis and targeted therapy of PJIs. In this review, we summarize current developments in next generation sequencing based predictive antibiotic susceptibility testing and discuss potential and limitations for common PJI pathogens.
Collapse
Affiliation(s)
- Lukas Lüftinger
- Ares Genetics GmbH, Karl-Farkas-Gasse 18, 1030 Vienna, Austria; (L.L.); (I.F.); (S.B.); (J.W.); (A.E.P.)
- Division of Computational Systems Biology, Department of Microbiology and Ecosystem Science, University of Vienna, 1030 Vienna, Austria;
| | - Ines Ferreira
- Ares Genetics GmbH, Karl-Farkas-Gasse 18, 1030 Vienna, Austria; (L.L.); (I.F.); (S.B.); (J.W.); (A.E.P.)
- Center for Integrative Bioinformatics Vienna, Max Perutz Laboratories, University of Vienna, 1030 Vienna, Austria;
- Center for Integrative Bioinformatics Vienna, Max Perutz Laboratories, Medical University of Vienna, 1030 Vienna, Austria
| | - Bernhard J. H. Frank
- Michael Ogon Laboratory for Orthopaedic Research, Orthopaedic Hospital Vienna-Speising, 1130 Vienna, Austria; (B.J.H.F.); (J.G.H.)
| | - Stephan Beisken
- Ares Genetics GmbH, Karl-Farkas-Gasse 18, 1030 Vienna, Austria; (L.L.); (I.F.); (S.B.); (J.W.); (A.E.P.)
| | - Johannes Weinberger
- Ares Genetics GmbH, Karl-Farkas-Gasse 18, 1030 Vienna, Austria; (L.L.); (I.F.); (S.B.); (J.W.); (A.E.P.)
| | - Arndt von Haeseler
- Center for Integrative Bioinformatics Vienna, Max Perutz Laboratories, University of Vienna, 1030 Vienna, Austria;
- Center for Integrative Bioinformatics Vienna, Max Perutz Laboratories, Medical University of Vienna, 1030 Vienna, Austria
- Bioinformatics and Computational Biology, Faculty of Computer Science, University of Vienna, 1090 Vienna, Austria
| | - Thomas Rattei
- Division of Computational Systems Biology, Department of Microbiology and Ecosystem Science, University of Vienna, 1030 Vienna, Austria;
| | - Jochen G. Hofstaetter
- Michael Ogon Laboratory for Orthopaedic Research, Orthopaedic Hospital Vienna-Speising, 1130 Vienna, Austria; (B.J.H.F.); (J.G.H.)
| | - Andreas E. Posch
- Ares Genetics GmbH, Karl-Farkas-Gasse 18, 1030 Vienna, Austria; (L.L.); (I.F.); (S.B.); (J.W.); (A.E.P.)
| | - Arne Materna
- Ares Genetics GmbH, Karl-Farkas-Gasse 18, 1030 Vienna, Austria; (L.L.); (I.F.); (S.B.); (J.W.); (A.E.P.)
| |
Collapse
|
6
|
Garza-González E, Bocanegra-Ibarias P, Dinh A, Morfín-Otero R, Camacho-Ortiz A, Rojas-Larios F, Rodríguez-Zulueta P, Arias CA. Species identification of Enterococcus spp: Whole genome sequencing compared to three biochemical test-based systems and two Matrix-Assisted Laser Desorption/Ionization Time-of-Flight Mass Spectrometry (MALDI-TOF MS) systems. J Clin Lab Anal 2020; 34:e23348. [PMID: 32358872 PMCID: PMC7439347 DOI: 10.1002/jcla.23348] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2020] [Revised: 04/06/2020] [Accepted: 04/08/2020] [Indexed: 11/09/2022] Open
Abstract
Aim Here, we evaluated the performance of two commercial MALDI‐TOF MS systems and three biochemical‐based systems and compared them to WGS as the gold standard for identifying isolates of vancomycin‐resistant enterococci (VRE). Methods A total of 87 VRE clinical isolates were included. The mass spectrometers were the Microflex system with Biotyper software 3.1 and the Vitek MS system. The biochemical‐based systems included the Vitek 2, Phoenix, and MicroScan WalkAway systems. WGS was performed on an Illumina MiSeq instrument using the MiSeq v3 reagent kit. Vancomycin resistance was determined according to CLSI criteria. Results Among the 87 VRE, 71 and 16 were identified as Enterococcus faecium and Enterococcus faecalis by WGS. All 71 E faecium were correctly identified by both mass spectrometers, as well as the Vitek 2 and Phoenix instruments. However, only 51 E faecium isolates were correctly identified by the MicroScan system. The most frequent misidentification was Enterococcus casseliflavus (n = 20). For vancomycin‐resistant E faecium, the Microflex Biotyper system had the highest sensitivity (85.54%), and all instruments (except for the Microscan) had a 100% specificity and PPV. Up to 87% of E faecalis isolates were misidentified by VITEK MS and VITEK2, 81% by Microscan and Phoenix, and 75% by Bruker biotyper. Conclusion As the coverage of type strain‐genome sequence database continues to grow and the cost of DNA sequencing continues to decrease, genome‐based identification can be a useful tool for diagnostic laboratories, with its superior accuracy even over MALDI‐TOF and database‐driven operations.
Collapse
Affiliation(s)
- Elvira Garza-González
- Hospital Universitario "Dr. José Eleuterio González", Universidad Autónoma de Nuevo León, Monterrey, Mexico
| | - Paola Bocanegra-Ibarias
- Hospital Universitario "Dr. José Eleuterio González", Universidad Autónoma de Nuevo León, Monterrey, Mexico
| | - An Dinh
- Division of Infectious Diseases and Center for Antimicrobial Resistance and Microbial Genomics (CARMiG), McGovern Medical School, UTHealth, Houston, TX, USA
| | - Rayo Morfín-Otero
- Centro Universitario de Ciencias de la Salud, Hospital Civil de Guadalajara "Fray Antonio Alcalde" e Instituto de Patología Infecciosa y Experimental, Universidad de Guadalajara, Guadalajara, Mexico
| | - Adrián Camacho-Ortiz
- Hospital Universitario "Dr. José Eleuterio González", Universidad Autónoma de Nuevo León, Monterrey, Mexico
| | | | | | - Cesar A Arias
- Division of Infectious Diseases and Center for Antimicrobial Resistance and Microbial Genomics (CARMiG), McGovern Medical School, UTHealth, Houston, TX, USA.,School of Public Health, Center for Infectious Diseases, UTHealth, Houston, TX, USA.,Molecular Genetics and Antimicrobial Resistance Unit and International Center for Microbial Genomics, Universidad El Bosque, Bogotá, Colombia
| |
Collapse
|