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.

Multifocal pneumonia caused by Bordetella bronchiseptica: Insights from a human case study

This case report describes a 43-year-old man who presented with respiratory distress and was diagnosed with an exacerbation of congestive heart failure and multifocal pneumonia caused by Bordetella bronchiseptica. Microbiological work up of a respiratory sample identified the causative organism, prompting antibiotic treatment and recommending vaccination for his dog. This case emphasizes the need to consider diverse origins in respiratory infections for effective clinical management.

Differentiation between Weissella cibaria and Weissella confusa Using Machine-Learning-Combined MALDI-TOF MS

Although Weissella cibaria and W. confusa are essential food-fermenting bacteria, they are also opportunistic pathogens. Despite these species being commercially crucial, their taxonomy is still based on inaccurate identification methods. In this study, we present a novel approach for identifying two important Weissella species, W. cibaria and W. confusa, by combining matrix-assisted laser desorption/ionization and time-of-flight mass spectrometer (MALDI-TOF MS) data using machine-learning techniques. After on- and off-plate protein extraction, we observed that the BioTyper database misidentified or could not differentiate Weissella species. Although Weissella species exhibited very similar protein profiles, these species can be differentiated on the basis of the results of a statistical analysis. To classify W. cibaria, W. confusa, and non-target Weissella species, machine learning was used for 167 spectra, which led to the listing of potential species-specific mass-to-charge (m/z) loci. Machine-learning techniques including artificial neural networks, principal component analysis combined with the K-nearest neighbor, support vector machine (SVM), and random forest were used. The model that applied the Radial Basis Function kernel algorithm in SVM achieved classification accuracy of 1.0 for training and test sets. The combination of MALDI-TOF MS and machine learning can efficiently classify closely-related species, enabling accurate microbial identification.

Macrolide Resistance in Bordetella pertussis: Current Situation and Future Challenges

Pertussis is a highly contagious respiratory infection caused by Bordetella pertussis bacterium. The mainstay of treatment is macrolide antibiotics that reduce transmissibility, shorten the duration of symptoms and decrease mortality in infants. Recently, the macrolide resistance of B. pertussis has been reported globally but is especially widespread in mainland China. In this review, we aim to summarise the current understanding of the epidemiology, resistance mechanisms and clinical implications of B. pertussis macrolide resistance. Since the first appearance of macrolide-resistant B. pertussis in Arizona, USA, in 1994, only sporadic cases have been reported outside China. In certain parts of China, on the other hand, up to 70-100% of the recent clinical isolates have been found to be macrolide resistant. Reasons for macrolide resistance being centred upon China during the last decade can only be speculated on, but the dominant B. pertussis lineage is different between China and most of the high-income countries. It seems evident that efforts to increase awareness, guide molecular epidemiological surveillance and carry out systematic screening of B. pertussis positive samples for macrolide resistance should be implemented globally. In addition, practices to improve the clinical care of infants with pertussis caused by resistant strains should be studied vigorously.

Matrix-assisted laser desorption ionization-time-of-flight mass spectrometry in veterinary medicine: Recent advances (2019-present)

Matrix-assisted laser desorption ionization-time-of-flight (MALDI-TOF) mass spectrometry (MS) has become a valuable laboratory tool for rapid diagnostics, research, and exploration in veterinary medicine. While instrument acquisition costs are high for the technology, cost per sample is very low, the method requires minimal sample preparation, and analysis is easily conducted by end-users requiring minimal training. Matrix-assisted laser desorption ionization-time-of-flight MS has found widespread application for the rapid identification of microorganisms, diagnosis of dermatophytes and parasites, protein/lipid profiling, molecular diagnostics, and the technique demonstrates significant promise for 2D chemical mapping of tissue sections collected postmortem. In this review, an overview of the MALDI-TOF technique will be reported and manuscripts outlining current uses of the technology for veterinary science since 2019 will be summarized. The article concludes by discussing gaps in knowledge and areas of future growth.

Characterization of Bordetella pertussis Strains Isolated from India

Despite high level vaccination and the availability of two different types of vaccines, whole cell (wP) and acellular vaccines (aP), the resurgence of pertussis has been reported in many countries. Antigenic variation within circulating and vaccine strains is the most documented reason reported for the resurgence of pertussis. Research on genetic divergence among circulating and vaccine strains has largely been reported in countries using aP vaccines. There are inadequate data available for antigenic variation in B. pertussis from wP-using countries. India has used wP for more than 40 years in their primary immunization program. The present study reports five clinical isolates of B. pertussis from samples of pediatric patients with pertussis symptoms observed in India. Genotypic and phenotypic characterization of clinical isolates were performed by serotyping, genotyping, whole genome analyses and comparative genomics. All clinical isolates showed serotype 1, 2 and 3 based on the presence of fimbriae 2 and 3. Genotyping showed genetic similarities in allele types for five aP genes within vaccine strains and clinical isolates reported from India. The presence of the ptxP3 genotype was observed in two out of five clinical isolates. Whole-genome sequencing was performed for clinical isolates using the hybrid strategy of combining Illumina (short reads) and oxford nanopore (long reads) sequencing strategies. Clinical isolates (n = 5) and vaccine strains (n = 7) genomes of B. pertussis from India were compared with 744 B. pertussis closed genomes available in the public databases. The phylogenomic comparison of B. pertussis genomes reported from India will be advantageous in better understanding pertussis resurgence reported globally with respect to pathogen adaptation.

Novel specific peaks for differentiating the Lactobacillus plantarum group using matrix-assisted laser desorption ionization time-of-flight mass spectrometry

Identifying the Lactobacillus plantarum group using conventional taxonomic methods such as biochemical analysis and 16S rRNA gene sequencing is inaccurate, expensive, and time-consuming. In this study, for the first time, matrix-assisted laser desorption/ionization time-of-flight mass spectrometry was used to identify the L. plantarum group and develop a classification method for species level differentiation with specific peaks based on mass spectra. Furthermore, from the mass spectra of 131 isolates aligned with the biotyper database, 131 isolates (100%) were correctly identified at the species level with a mean score of 2.316. However, commercial databases could not accurately differentiate some isolates of L. plantarum group species because the same colony was identified as different species with similar score values. Moreover, these two species showed a similar mass pattern in the main spectrum profiles-dendrogram and Principal component analysis clustering generated by the mass peak of the reference strains and isolates. Specific peaks to each species were investigated from the analyzed mass peak, and they clearly showed that three species could be differentiated. These peaks were verified by re-identifying 131 isolates, and it demonstrated 100% specificity and accuracy. Also, using a specific peak, isolates that were undifferentiated from the biotyper database were clearly identified as one species, similar to species-specific polymerase chain reaction. Our data demonstrate that the specific peaks accurately differentiate the L. plantarum group and enable high-resolution identification at the species level; this methodology can be used to rapidly and easily identify them and determine their nomenclature.

A profile of the Simplexa™ Bordetella Direct assay for the detection and differentiation of Bordetella pertussis and Bordetella parapertussis in nasopharyngeal swabs

INTRODUCTION

Pertussis is a highly contagious respiratory infection caused by Bordetella pertussis and to minor extent B. parapertussis. Despite high vaccination coverage, epidemics persist worldwide. Laboratory testing with the capacity to support increasing demand and generate fast and accurate results is needed to promptly provide treatment to mitigate symptoms, prevent transmission, and thus impact infection control and disease surveillance.

AREAS COVERED

This review will describe the features of the Simplexa™ Bordetella Direct Assay and compare this technology with other existing assays. Unmet needs and future directions will be discussed.

EXPERT COMMENTARY

Resurgence of pertussis highlights the importance of reliable and accurate diagnosis. The Simplexa™ Bordetella Direct Assay provides an easy workflow, reduced hand-on time, less risk of contamination, and rapid turnaround time. The use of efficient molecular assays in routine clinical laboratory is valuable for increasing demand, improvement of infection control, and surveillance.

Pertussis: Identification, Prevention and Control

Pertussis is a vaccine-preventable disease. Despite the high vaccination coverage among children, pertussis is considered a re-emerging disease for which identification, prevention and control strategies need to be improved. To control pertussis it is important to maintain a high vaccination coverage to protect the age groups considered at high risk for the disease. Laboratory confirmation of Bordetella pertussis infection together with a differential diagnostic test for other Bordetellae are prerequisite for a correct and timely diagnosis of pertussis. Moreover, investigations of antimicrobial susceptibility and whole genome sequencing may permit to monitor the circulation of antimicrobials resistant and/or vaccine-escape strains. Finally, the preventive framework should no longer consider pertussis exclusively as a childhood infectious disease, since adults may play a role in transmission events.