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

A rapid and simple MALDI-TOF MS lipid profiling method for differentiating Mycobacterium ulcerans from Mycobacterium marinum

Mycobacterium ulcerans, a slow-growing nontuberculous mycobacterium, causes Buruli ulcer, a neglected tropical disease. Distinguishing M. ulcerans from related species, including Mycobacterium marinum, poses challenges with respect to making accurate identifications. In this study, we developed a rapid and simple identification method based on mycobacterial lipid profiles and used matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) to analyze the lipid profiles of M. ulcerans (n = 35) and M. marinum (n = 19) isolates. Bacterial colonies pre-cultured on 2% Ogawa egg slants for 2 months were collected, and total lipids were extracted using an MBT Lipid Xtract kit. Spectra were obtained in negative ion mode using a MALDI Biotyper Sirius system, with ClinProTools v3.0 being used to analyze the spectra based on the application of three algorithms (genetic algorithm [GA], supervised neural network [SNN], and quick classifier [QC)]). Cross-validation was performed using a 20% leave-out set randomly selected from the samples. Models generated using GA, SNN, and QC showed cross-validation values of 100%, 100%, and 97.9%, respectively, and all algorithms achieved 100% recognition capability values. Our findings indicate that MALDI-TOF analysis of lipid profiles can accurately differentiate two mycobacterial species (M. ulcerans and M. marinum) that are difficult to distinguish using conventional protein-targeting methods.IMPORTANCEBuruli ulcer, caused by Mycobacterium ulcerans, is a neglected tropical disease. However, distinguishing M. ulcerans from related species, including Mycobacterium marinum, presents certain challenges. In this study, we demonstrate the utility of a rapid yet simple method for differentiating isolates of these mycobacteria based on their lipid profiles using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry. This new approach can accurately identify species that are otherwise difficult to distinguish using conventional techniques. This represents a significant diagnostic advance for clinical laboratories, in that it enables a more rapid and precise identification, thereby leading to earlier treatment initiation and more appropriate treatment regimens for infections caused by these bacteria.

The Mass Spectrometry Revolution in Clinical Microbiology Part 1: History and Current Applications

The introduction of matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) has revolutionized infectious disease diagnostics over the past decade. In this review, we will first explore the history of how the once disparate fields of mass spectrometry (MS) and clinical microbiology inextricably merged. We will then review the rapid growth as well as current applications of MALDI-TOF MS in clinical microbiology. In the accompanying review, we will discuss some of the exciting and emerging applications of MS in pathogen detection, identification, and characterization.

Comparison of the molecular FluoroType Mycobacteria VER 1.0 and the Maldi BioTyper Mycobacteria assays for the identification of non-tuberculous mycobacteria

Accurate identification of non-tuberculous mycobacterial (NTM) species is crucial for the diagnosis and appropriate management of NTM infections. This study aimed to evaluate the performance of two assays, FluoroType Mycobacteria VER 1.0 and Maldi BioTyper (MBT) Mycobacteria. The two assays were evaluated using 119 NTM, including 85 slow-growing mycobacteria and 34 rapid-growing mycobacteria, representing a total of 33 species isolated in three French clinical laboratories. We used the GenoType assays as reference method for species identification, followed by 16S rRNA gene sequencing if the GenoType kits returned Mycobacterium sp. Compared to the reference method, the FluoroType Mycobacteria assay provided correct species identification in 89.9% of cases (107/119). Among the most frequently encountered species in clinical settings, low concordance was obtained for Mycobacterium intracellulare (82.4%, 14/17), Mycobacterium gordonae (66.7%, 6/9), and Mycobacterium xenopi (75%, 6/8). Misidentification was obtained in two cases (Mycobacterium smegmatis instead of Mycobacterium mageritense, and Mycobacterium mucogenicum instead of Mycobacterium phocaicum). Using the MBT Mycobacteria assay, 78.1% (93/119) of NTM isolates were correctly identified at the species level. One Mycobacterium europaeum isolate was misidentified as M. intracellulare/Mycobacterium chimaera. In five cases, the assay provided more accurate NTM identification compared to GenoType assays, in which closely related species are identified as a group. The FluoroType Mycobacteria VER 1.0 and the MBT Mycobacteria assays are useful tools for NTM identification from positive cultures, reducing handling time compared to GenoType assays. Their routine use in laboratories must take into consideration their performance and limitations in clinical settings.

Growing Challenges of Lung Infections with Non-tuberculous Mycobacteria in Immunocompromised Patients: Epidemiology and Treatment

Non-tuberculous mycobacteria (NTM) are increasingly recognized as opportunistic pathogens in humans and animals, particularly affecting those with compromised immune systems. These bacteria encompass a diverse group of mycobacterial species that are responsible for a range of infections, with pulmonary and skin-related conditions being the most common. The rise in NTM infections in recent years is a growing concern for healthcare, highlighting the urgent need to improve our understanding of NTM epidemiology and treatment strategies. This article reviews the NTM species associated with lung infections in immunocompromised patients and underscores the critical importance of advancing diagnostic and therapeutic approaches. The review is based on a thorough analysis of scientific literature from databases such as PubMed, Scopus, and ScienceDirect, covering studies up to June 2024. Through this comprehensive analysis, the article aims to provide detailed insights into the complexities of NTM diseases and spur further research and innovation in combating these challenging infections.

Advancing Laboratory Medicine Practice With Machine Learning: Swift yet Exact

Machine learning (ML) is currently being widely studied and applied in data analysis and prediction in various fields, including laboratory medicine. To comprehensively evaluate the application of ML in laboratory medicine, we reviewed the literature on ML applications in laboratory medicine published between February 2014 and March 2024. A PubMed search using a search string yielded 779 articles on the topic, among which 144 articles were selected for this review. These articles were analyzed to extract and categorize related fields within laboratory medicine, research objectives, specimen types, data types, ML models, evaluation metrics, and sample sizes. Sankey diagrams and pie charts were used to illustrate the relationships between categories and the proportions within each category. We found that most studies involving the application of ML in laboratory medicine were designed to improve efficiency through automation or expand the roles of clinical laboratories. The most common ML models used are convolutional neural networks, multilayer perceptrons, and tree-based models, which are primarily selected based on the type of input data. Our findings suggest that, as the technology evolves, ML will rise in prominence in laboratory medicine as a tool for expanding research activities. Nonetheless, expertise in ML applications should be improved to effectively utilize this technology.

Integration of MALDI-TOF MS and machine learning to classify enterococci: A comparative analysis of supervised learning algorithms for species prediction

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.

Evaluation of the GenoType NTM-DR line probe assay for nontuberculous mycobacteria using whole genome sequences as reference standard

Pulmonary nontuberculous mycobacteria (NTM) disease is an emerging public health challenge that is especially problematic in people with cystic fibrosis (CF). Effective treatment depends on accurate species and subspecies identification and antimicrobial susceptibility status. We evaluated the GenoType NTM-DR VER 1.0 assay using biobanked NTM isolates with whole genome sequence (WGS) data and control isolates (total n=285). Species and subspecies detection sensitivity and specificity were 100 % for all species and subspecies except for two subspecies of M. intracellulare, that demonstrated a small degree of discrepant identification between M. intracellulare subspecies intracellulare and subspecies chimaera. All antimicrobial resistance markers were identified with 100 % sensitivity and specificity. We conclude that the GenoType NTM-DR assay offers a rapid and accurate option for identifying the most frequently encountered pathogenic NTM taxa and drug resistance markers. SUPPORT: Colorado CF Research Development Program and Colorado CF National Resource Centers funded by the Cystic Fibrosis Foundation, NJH Advanced Diagnostics Laboratories, Colorado Advanced Industries Accelerator Grant.

Rapid and accurate identification of yeast subspecies by MALDI-MS combined with a cell membrane disruption reagent

Matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) has been widely used for microbial analysis. However, due to the impenetrable shell of fungi the direct identification of fungi remains challenges. Targeting on this problem, the yeast Saccharomyces cerevisiae (S. cerevisiae) was selected as a model fungus, and a new fungal cell membrane disruption reagent C18-G1 was used before MALDI-MS detection. As a result, much more intensive peaks which distributed in wider m/z range of S. cerevisiae have been identified in comparison with the use of traditional fungal pretreatment methods. Furthermore, a differential peak at m/z 4993 between two subspecies of S. cerevisiae has been identified. The corresponding protein with exclusive sequence of the specific peak was obtained based on MS/MS fragments and database searching. In addition, the method was successfully applied for the discrimination of four commercial yeasts.

Classification of Latilactobacillus sakei subspecies based on MALDI-TOF MS protein profiles using machine learning models

Latilactobacillus sakei is an important bacterial species used as a starter culture for fermented foods; however, two subspecies within this species exhibit different properties in the foods. Matrix-assisted laser desorption/ionization-time of flight mass spectrometer (MALDI-TOF MS) is the gold standard for microbial fingerprinting. However, the resolution power is down to the species level. This study was to combine MALDI-TOF mass spectra and machine learning to develop a new method to identify two L. sakei subspecies (L. sakei subsp. sakei and L. sakei subsp. carnosus) and non-L. sakei species. Totally, 227 strains were collected, with 908 spectra obtained via on- and off-plate protein extraction. Only 68.7% of strains were correctly identified at the subspecies level in the Biotyper database; however, a high level of performance was observed from the machine learning models. Partial least squares-discriminant analysis (PLS-DA), principal component analysis-K-nearest neighbor (PCA-KNN), and support vector machine (SVM) demonstrated 0.823, 0.914, and 0.903 accuracies, respectively, whereas the random forest (RF) achieved an accuracy of 0.954, with an area under the receiver operating characteristic (AUROC) curve of 0.99, outperforming the other algorithms in distinguishing the subspecies. The machine learning proved to be a promising technique for the rapid and high-resolution classification of L. sakei subspecies using MALDI-TOF MS.

IMPORTANCE

Latilactobacillus sakei plays a significant role in the realm of food bacteria. One particular subspecies of L. sakei is employed as a protective agent during food fermentation, whereas another strain is responsible for food spoilage. Hence, it is crucial to precisely differentiate between the two subspecies of L. sakei. In this study, machine learning models based on protein mass peaks were developed for the first time to distinguish L. sakei subspecies. Furthermore, the efficacy of three commonly used machine learning algorithms for microbial classification was evaluated. Our results provide the foundation for future research on developing machine learning models for the classification of microbial species or subspecies. In addition, the developed model can be used in the food industry to monitor L. sakei subspecies in fermented foods in a time- and cost-effective method for food quality and safety.

Contribution of machine learning for subspecies identification from Mycobacterium abscessus with MALDI-TOF MS in solid and liquid media

Mycobacterium abscessus (MABS) displays differential subspecies susceptibility to macrolides. Thus, identifying MABS's subspecies (M. abscessus, M. bolletii and M. massiliense) is a clinical necessity for guiding treatment decisions. We aimed to assess the potential of Machine Learning (ML)-based classifiers coupled to Matrix-Assisted Laser Desorption/Ionization Time-of-Flight (MALDI-TOF) MS to identify MABS subspecies. Two spectral databases were created by using 40 confirmed MABS strains. Spectra were obtained by using MALDI-TOF MS from strains cultivated on solid (Columbia Blood Agar, CBA) or liquid (MGIT®) media for 1 to 13 days. Each database was divided into a dataset for ML-based pipeline development and a dataset to assess the performance. An in-house programme was developed to identify discriminant peaks specific to each subspecies. The peak-based approach successfully distinguished M. massiliense from the other subspecies for strains grown on CBA. The ML approach achieved 100% accuracy for subspecies identification on CBA, falling to 77.5% on MGIT®. This study validates the usefulness of ML, in particular the Random Forest algorithm, to discriminate MABS subspecies by MALDI-TOF MS. However, identification in MGIT®, a medium largely used in mycobacteriology laboratories, is not yet reliable and should be a development priority.

Supporting Patients with Nontuberculous Mycobacterial Pulmonary Disease: Ensuring Best Practice in UK Healthcare Settings

Nontuberculous mycobacterial pulmonary disease (NTM-PD) results from opportunistic lung infections by mycobacteria other than Mycobacterium tuberculosis or Mycobacterium leprae species. Similar to many other countries, the incidence of NTM-PD in the United Kingdom (UK) is on the rise for reasons that are yet to be determined. Despite guidelines established by the American Thoracic Society (ATS), the Infectious Diseases Society of America, and the British Thoracic Society, NTM-PD diagnosis and management remain a significant clinical challenge. In this review article, we comprehensively discuss key challenges in NTM-PD diagnosis and management, focusing on the UK healthcare setting. We also propose countermeasures to overcome these challenges and improve the detection and treatment of patients with NTM-PD.

Contribution of MALDI-TOF mass spectrometry and machine learning including deep learning techniques for the detection of virulence factors of Clostridioides difficile strains

Clostridioides difficile (CD) infections are defined by toxins A (TcdA) and B (TcdB) along with the binary toxin (CDT). The emergence of the 'hypervirulent' (Hv) strain PR 027, along with PR 176 and 181, two decades ago, reshaped CD infection epidemiology in Europe. This study assessed MALDI-TOF mass spectrometry (MALDI-TOF MS) combined with machine learning (ML) and Deep Learning (DL) to identify toxigenic strains (producing TcdA, TcdB with or without CDT) and Hv strains. In total, 201 CD strains were analysed, comprising 151 toxigenic (24 ToxA+B+CDT+, 22 ToxA+B+CDT+ Hv+ and 105 ToxA+B+CDT-) and 50 non-toxigenic (ToxA-B-) strains. The DL-based classifier exhibited a 0.95 negative predictive value for excluding ToxA-B- strains, showcasing accuracy in identifying this strain category. Sensitivity in correctly identifying ToxA+B+CDT- strains ranged from 0.68 to 0.91. Additionally, all classifiers consistently demonstrated high specificity (>0.96) in detecting ToxA+B+CDT+ strains. The classifiers' performances for Hv strain detection were linked to high specificity (≥0.96). This study highlights MALDI-TOF MS enhanced by ML techniques as a rapid and cost-effective tool for identifying CD strain virulence factors. Our results brought a proof-of-concept concerning the ability of MALDI-TOF MS coupled with ML techniques to detect virulence factor and potentially improve the outbreak's management.

Identification of Mycobacterium abscessus using the peaks of ribosomal protein L29, L30 and hemophore-related protein by MALDI-MS proteotyping

Mycobacteroides (Mycobacterium) abscessus, which causes a variety of infectious diseases in humans, is becoming detected more frequently in clinical specimens as cases are spreading worldwide. Taxonomically, M. abscessus is composed of three subspecies of M. abscessus subsp. abscessus, M. abscessus subsp. bolletii, and M. abscessus subsp. massiliense, with different susceptibilities to macrolides. In order to identify rapidly these three subspecies, we determined useful biomarker proteins, including ribosomal protein L29, L30, and hemophore-related protein, for distinguishing the subspecies of M. abscessus using the matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) profiles. Thirty-three clinical strains of M. abscessus were correctly identified at the subspecies-level by the three biomarker protein peaks. This study ultimately demonstrates the potential of routine MALDI-MS-based laboratory methods for early identification and treatment for M. abscessus infections.

Construction of Composite Correlation Index Matrix and Analysis of Cultural Properties of Representatives of Mycobacterium abscessus Complex Isolated from Patients with Cystic Fibrosis

BACKGROUND

Microbiological diagnosis of mycobacteriosis is often difficult, as it is necessary to differentiate between transient colonization and active infection.

METHODS

We studied the cultural properties of Mycobacterium abscessus complex (MABSc) strains obtained from cystic fibrosis patients, and also analyzed composite correlation index (CCI) values in patients with repeated MABSc inoculation and their correlation with the presence of clinical and radiological manifestations of mycobacteriosis.

RESULTS

As a result, MABSc more often grew in S-form colonies in patients without clinical manifestations of chronic infection, while R-form colonies were characteristic of patients with chronic infection and clinical symptoms. At the same time, in patients examined once, no growth of colonies in the R-form was recorded, and all strains produced growth in the form of either S-colonies or in the S- and R-forms simultaneously. Statistically significant results were obtained for the relationship of the CCI with the clinical and radiological picture. In addition, a heterogeneous MABSc population with low CCI score values correlated with the development of mycobacteriosis in patients. In patients with high CCI score values (homogeneity of isolated strains), on the contrary, there were no radiological or clinical signs of the disease.

CONCLUSION

These data make it possible to build a strategy for monitoring patients depending on changes in CCI score values. The use of CCI matrix to evaluate microorganisms' identification results is a potentially new method that expands the use of matrix-assisted laser desorption ionization time-of-flight mass spectrometry.

Cutaneous Mycobacterium Abscessus Infection Following Plastic Surgery: Three Case Reports

Aim

Mycobacterium abscessus is ubiquitous in the environment and seldom causes infections in immunocompetent individuals. However, skin and soft tissue infections caused by M. abscessus have been reported in recent years. Additionally, the cutaneous infections or outbreaks post cosmetic surgery caused by M. abscessus have been increasing due to the popularity of plastic surgery. The main modes of transmission are through contaminated saline, disinfectants, or surgery equipment, as well as close contact between patients. This article describes three patients who were admitted to our hospital between November 2019 and October 2020. They presented with long-term non-healing wounds caused by M. abscessus infection after undergoing plastic surgery. Symptoms presented by the three patients included swelling, ulceration, secretion, and pain. After identification of M. abscessus with Ziehl-Neelsen staining and MALDI-TOF MS system, the patients were treated with surgical debridement and clarithromycin.

Conclusion

It is important to note that a long-term wound that does not heal, especially after plastic surgery, should raise suspicion for M. abscessus infection. The infection mechanism in these three patients may have been due to exposure to surgical equipment that was not properly sterilized or due to poor sterile technique by the plastic surgeon. To prevent such infections, it is important to ensure proper sterilization of surgical equipment and saline.

Rapid discrimination of Bifidobacterium longum subspecies based on MALDI-TOF MS and machine learning

Although MALDI-TOF mass spectrometry (MS) is widely known as a rapid and cost-effective reference method for identifying microorganisms, its commercial databases face limitations in accurately distinguishing specific subspecies of Bifidobacterium. This study aimed to explore the potential of MALDI-TOF MS protein profiles, coupled with prediction methods, to differentiate between Bifidobacterium longum subsp. infantis (B. infantis) and Bifidobacterium longum subsp. longum (B. longum). The investigation involved the analysis of mass spectra of 59 B. longum strains and 41 B. infantis strains, leading to the identification of five distinct biomarker peaks, specifically at m/z 2,929, 4,408, 5,381, 5,394, and 8,817, using Recurrent Feature Elimination (RFE). To facilate classification between B. longum and B. infantis based on the mass spectra, machine learning models were developed, employing algorithms such as logistic regression (LR), random forest (RF), and support vector machine (SVM). The evaluation of the mass spectrometry data showed that the RF model exhibited the highest performace, boasting an impressive AUC of 0.984. This model outperformed other algorithms in terms of accuracy and sensitivity. Furthermore, when employing a voting mechanism on multi-mass spectrometry data for strain identificaton, the RF model achieved the highest accuracy of 96.67%. The outcomes of this research hold the significant potential for commercial applications, enabling the rapid and precise discrimination of B. longum and B. infantis using MALDI-TOF MS in conjunction with machine learning. Additionally, the approach proposed in this study carries substantial implications across various industries, such as probiotics and pharmaceuticals, where the precise differentiation of specific subspecies is essential for product development and quality control.