MALDI-TOF MS in a Medical Mycology Laboratory: On Stage and Backstage

Clinical Evaluation of VITEK MS PRIME with PICKME Pen for Bacteria and Yeasts, and RUO Database for Filamentous Fungi

The VITEK MS PRIME (bioMérieux, Marcy-l'Étoile, France), a newly developed matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) system, alongside the VITEK PICKME pen (PICKME), offers easy sample preparation for bacteria and yeasts. The VITEK MS PRIME also offers two software platforms for filamentous fungi: the IVD database and the RUO database. Our study evaluated its identification agreement on 320 clinical isolates of bacteria and yeasts, comparing PICKME and traditional wooden toothpick sampling techniques against MicroIDSys Elite (ASTA) results. Additionally, we assessed the IVD (v3.2) and SARAMIS (v4.16) RUO databases on 289 filamentous fungi against molecular sequencing. The concordance rates for species-level identification of bacteria and yeasts were about 89.4% (286/320) between the PICKME and wooden toothpick, and about 83.4-85.3% between the VITEK MS PRIME and ASTA MicroIDSys Elite. Retesting with PICKME improved concordance to 91.9%. For filamentous fungi, species-level identification reached 71.3% with the IVD database and 85.8% with RUO, which significantly enhanced basidiomycetes' identification from 35.3% to 100%. Some strains in the IVD database, like Aspergillus versicolor, Exophiala xenobiotica, and Nannizzia gypsea, failed to be identified. The VITEK MS PRIME with PICKME offers reliable and efficient microorganism identification. For filamentous fungi, combined use of the RUO database can be beneficial, especially for basidiomycetes.

Proteomic Analyses Reveal the Role of Alpha-2-Macroglobulin in Canine Osteosarcoma Cell Migration

Canine osteosarcoma (OSA) is an aggressive bone neoplasia with high metastatic potential. Metastasis is the main cause of death associated with OSA, and there is no current treatment available for metastatic disease. Proteomic analyses, including matrix-assisted laser desorption/ionisation-time of flight mass spectrometry (MALDI TOF/TOF MS), are widely used to select molecular targets and identify proteins that may play a key role in primary tumours and at various steps of the metastatic cascade. The main aim of this study was to identify proteins differently expressed in canine OSA cell lines with different malignancy phenotypes (OSCA-8 and OSCA-32) compared to canine osteoblasts (CnOb). The intermediate aim of the study was to compare canine OSA cell migration capacity and assess its correlation with the malignancy phenotypes of each cell line. Using MALDI-TOF/TOF MS analyses, we identified eight proteins that were significantly differentially expressed (p ≤ 0.05) in canine OSA cell lines compared to CnOb: cilia- and flagella-associated protein 298 (CFAP298), general transcription factor II-I (GTF2I), mirror-image polydactyly gene 1 protein (MIPOL1), alpha-2 macroglobulin (A2M), phosphoglycerate mutase 1 (PGAM1), ubiquitin (UB2L6), ectodysplasin-A receptor-associated adapter protein (EDARADD), and leucine-rich-repeat-containing protein 72 (LRRC72). Using the Simple Western technique, we confirmed high A2M expression in CnOb compared to OSCA-8 and OSCA-32 cell lines (with intermediate and low A2M expression, respectively). Then, we confirmed the role of A2M in cancer cell migration by demonstrating significantly inhibited OSA cell migration by treatment with A2M (both at 10 and 30 mM concentrations after 12 and 24 h) in a wound-healing assay. This study may be the first report indicating A2M's role in OSA cell metastasis; however, further in vitro and in vivo studies are needed to confirm its possible role as an anti-metastatic agent in this malignancy.

Unveiling the fungal color palette: pigment analysis of Fusarium solani species complex and Curvularia verruculosa clinical isolates

Fungal species in the Nectriaceae, such as Fusarium spp. (Hypocreales: Nectriaceae), are etiologic agents of hyalohyphomycosis capable of producing violaceous or yellowish pigments under certain conditions, while Curvularia spp. (Pleosporales: Pleosporaceae) are agents of phaeohyphomycosis and typically produce melanin in their cell walls. In nectriaceous and pleosporaceous fungi, these pigments are mainly constituted by polyketides (e.g., azaphilones, naphthoquinones, and hydroxyanthraquinones). Considering the importance of pigments synthesized by these genera, this work focused on the selective extraction of pigments produced by eight Fusarium solani species complex and one Curvularia verruculosa isolate recovered from dermatomycosis specimens, their separation, purification, and posterior chemical analysis. The pigments were characterized through spectral and acid-base analysis, and their maximum production time was determined. Moreover, spectral identification of isolates was carried out to approach the taxonomic specificity of pigment production. Herein we describe the isolation and characterization of three acidic pigments, yellowish and pinkish azaphilones (i.e., coaherin A and sclerotiorin), and a purplish xanthone, reported for the first time in the Nectriaceae and Pleosporaceae, which appear to be synthesized in a species-independent manner, in the case of fusaria.

A case report of Pseudomonas citronellolis and Escherichia coli isolated from acute suppurative appendicitis: reveals the potential intestinal colonization and pathogenicity of Pseudomonas citronellolis

Human infections caused by Pseudomonas citronellolis, an environmental bacterium, are infrequent, with only two cases related to uncommon urinary tract infections and bacteremia reported in recent years. All these cases typically occurred in elderly patients with compromised or decreased immune function. Simultaneously, the epithelial barrier disruption induced by invasive biopsy procedures or gastrointestinal disorders such as gastroenteritis provided a pathway for Pseudomonas citronellolis to infiltrate the organism. In this study, we present the first report of a case where Pseudomonas citronellolis and Escherichia coli were isolated from the inflamed appendix of a patient without underlying conditions. Compared to the Escherichia coli, Pseudomonas citronellolis has never been isolated in patients with appendicitis. We identified the species using MALDI-TOF MS and genetic sequencing. Based on our findings, we highlight the perspective that Pseudomonas citronellolis can colonize the intestines of healthy individuals and may trigger infections like appendicitis.

Chip-Based Molecular Evaluation of a DNA Extraction Protocol for Candida Species from Positive Blood Cultures

The diagnosis of Candida bloodstream infection (BSI) may rely on a PCR-based analysis of a positive blood culture (PBC) obtained from the patient at the time of BSI. In this study, a yeast DNA extraction protocol for use on PBCs was developed and evaluated with the molecular mouse (MM) yeast blood (YBL) chip-based PCR assay, which allowed us to detect nine medically relevant Candida species. We studied 125 simulated or clinical PBCs for Candida species. A positive correlation between the DNA concentration and colony-forming unit count was found for simulated (Spearman's ρ = 0.58; p < 0.0001) and clinical (Spearman's ρ = 0.23, p = 0.09) PBCs. The extracted DNA yielded positive results with the MM YBL chip assay that agreed with the Candida species-level identification results for 63 (100%) of 63 isolates from simulated PBCs and 66 (99.5%) of 67 isolates from clinical PBCs. The false-negative result was for one C. tropicalis isolate that grew together with C. albicans in PBC. None of the 30 (Candida)-negative clinical BCs included as negative controls yielded a positive result with the MM YBL chip assay. Our DNA extraction protocol for the Candida species couples efficiency and simplicity together. Nevertheless, further studies are needed before it can be adopted for use with the MM YBL chip assay.

Fungemia due to rare non-Candida yeasts between 2018 and 2021 in a Greek tertiary care university hospital

INTRODUCTION

Non-Candida yeasts, although rare, are increasingly encountered and recognized as a growing threat.

METHODS

Cases of bloodstream infections (BSIs) due to non-Candida yeasts (NCYs) during the last four years (2018-2021) are presented.

RESULTS

During the study period, 16 cases caused by non-Candida yeasts out of 400 cases of yeast BSIs were recorded, corresponding to an incidence of 4%. Yeasts that were isolated included Cryptococcus spp (4 isolates-25%), Rhodotorula mucilaginosa (2 isolates-12.5%), Trichosporon asahii (7 isolates-43.75%) and Saccharomyces cerevisiae (3 isolates-18.75%). Predisposing factors involved mostly hematological malignancies, long term hospitalization or major surgical interventions. Most isolates, 15 out of 16 were susceptible to amphotericin B. Voriconazole was the most active azole in vitro. All isolates, except Saccharomyces spp., were resistant to echinocandins.

DISCUSSION

Early recognition of rare yeasts as causative agents of BSIs and prompt initiation of appropriate treatment based on current guidelines and expertise remain crucial in efficient patient management.

Diagnosis and Treatment of Fungal Infections in Lung Transplant Recipients

Fungal infections are a significant source of morbidity in the lung transplant population via direct allograft damage and predisposing patients to the development of chronic lung allograft dysfunction. Prompt diagnosis and treatment are imperative to limit allograft damage. This review article discusses incidence, risk factors, and symptoms with a specific focus on diagnostic and treatment strategies in the lung transplant population for fungal infections caused by Aspergillus, Candida, Coccidioides, Histoplasma, Blastomyces, Scedosporium/Lomentospora, Fusarium, and Pneumocystis jirovecii. Evidence for the use of newer triazole and inhaled antifungals to treat isolated pulmonary fungal infections in lung transplant recipients is also discussed.

Malassezia pachydermatis from brown bear: A comprehensive analysis reveals novel genotypes and distribution of all detected variants in domestic and wild animals

Malassezia pachydermatis (phylum Basidiomycota, class Malasseziomycetes) is a zoophilic opportunistic pathogen with recognized potential for invasive infections in humans. Although this pathogenic yeast is widespread in nature, it has been primarily studied in domestic animals, so available data on its genotypes in the wild are limited. In this study, 80 yeast isolates recovered from 42 brown bears (Ursus arctos) were identified as M. pachydermatis by a culture-based approach. MALDI-TOF mass spectrometry (MS) was used to endorse conventional identification. The majority of samples exhibited a high score fluctuation, with 42.5% of isolates generating the best scores in the range confident only for genus identification. However, the use of young biomass significantly improved the identification of M. pachydermatis at the species confidence level (98.8%). Importantly, the same MALDI-TOF MS efficiency would be achieved regardless of colony age if the cut-off value was lowered to ≥1.7. Genotyping of LSU, ITS1, CHS2, and β-tubulin markers identified four distinct genotypes in M. pachydermatis isolates. The most prevalent among them was the genotype previously found in dogs, indicating its transmission potential and adaptation to distantly related hosts. The other three genotypes are described for the first time in this study. However, only one of the genotypes consisted of all four loci with bear-specific sequences, indicating the formation of a strain specifically adapted to brown bears. Finally, we evaluated the specificity of the spectral profiles of the detected genotypes. MALDI-TOF MS exhibited great potential to detect subtle differences between all M. pachydermatis isolates and revealed distinct spectral profiles of bear-specific genotypes.

Fungal Whole-Genome Sequencing for Species Identification: From Test Development to Clinical Utilization

Using next-generation sequencing (NGS), we developed and validated a whole-genome sequencing (WGS)-based clinical test for fungal species identification on clinical isolates. The identification is mainly based on the fungal ribosomal internal transcribed spacer (ITS) region as the primary marker, and additional marker and genomic analysis applied for species within the Mucorales family (using the 28S rRNA gene) and Aspergillus genus (using the beta-tubulin gene and k-mer tree-based phylogenetic clustering). The validation study involving 74 unique fungal isolates (22 yeasts, 51 molds, and 1 mushroom-forming fungus) showed high accuracy, with 100% (74/74) concordance on the genus-level identifications and 89.2% (66/74) concordance on the species level. The 8 discrepant results were due to either the limitation of conventional morphology-based methodology or taxonomic changes. After one year of implementation in our clinical laboratory, this fungal NGS test was utilized in 29 cases; the majority of them were transplant and cancer patients. We demonstrated the utility of this test by detailing five case studies, in which accurate fungal species identification led to correct diagnosis, treatment adjustment or was ruled out for hospital acquired infection. This study provides a model for validation and implementation of WGS for fungal identification in a complex health system that serves a large immunocompromised patient population.

Recent Advances and Potential Future Applications of MALDI-TOF Mass Spectrometry for Identification of Helminths

Helminth infections caused by nematodes, trematodes, and cestodes are major neglected tropical diseases and of great medical and veterinary relevance. At present, diagnosis of helminthic diseases is mainly based on microscopic observation of different parasite stages, but microscopy is associated with limited diagnostic accuracy. Against this background, recent studies described matrix-assisted laser desorption/ionization time-of-flight (MALDI-TOF) mass spectrometry as a potential, innovative tool for helminth identification and differentiation. MALDI-TOF mass spectrometry is based on the analysis of spectra profiles generated from protein extracts of a given pathogen. It requires an available spectra database containing reference spectra, also called main spectra profiles (MSPs), which are generated from well characterized specimens. At present, however, there are no commercially available databases for helminth identification using this approach. In this narrative review, we summarize recent developments and published studies between January 2019 and September 2022 that report on the use of MALDI-TOF mass spectrometry for helminths. Current challenges and future research needs are identified and briefly discussed.

Diagnosis and Treatment of Invasive Candidiasis

Candida species, belonging to commensal microbial communities in humans, cause opportunistic infections in individuals with impaired immunity. Pathogens encountered in more than 90% cases of invasive candidiasis include C. albicans, C. glabrata, C. krusei, C. tropicalis, and C. parapsilosis. The most frequently diagnosed invasive infection is candidemia. About 50% of candidemia cases result in deep-seated infection due to hematogenous spread. The sensitivity of blood cultures in autopsy-proven invasive candidiasis ranges from 21% to 71%. Non-cultural methods (beta-D-glucan, T2Candida assays), especially beta-D-glucan in combination with procalcitonin, appear promising in the exclusion of invasive candidiasis with high sensitivity (98%) and negative predictive value (95%). There is currently a clear deficiency in approved sensitive and precise diagnostic techniques. Omics technologies seem promising, though require further development and study. Therapeutic options for invasive candidiasis are generally limited to four classes of systemic antifungals (polyenes, antimetabolite 5-fluorocytosine, azoles, echinocandins) with the two latter being highly effective and well-tolerated and hence the most widely used. Principles and methods of treatment are discussed in this review. The emergence of pan-drug-resistant C. auris strains indicates an insufficient choice of available medications. Further surveillance, alongside the development of diagnostic and therapeutic methods, is essential.

Molecular Diagnosis of Two Major Implantation Mycoses: Chromoblastomycosis and Sporotrichosis

Chromoblastomycosis and sporotrichosis are the two main implantation mycoses that are now recognized as fungal neglected tropical diseases (NTDs). Their laboratory diagnosis mainly relies on direct microscopy, histopathology, and identification of the fungus by culture. However, to be appropriately used, these techniques require mycological expertise that is not widely available and may be absent in peripheral health care facilities in endemic areas. In addition, they lack sensitivity and specificity, and the culture for isolation and identification can have a long time-to-results period. Molecular methods, including matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS), have been developed in well-equipped reference laboratories. They greatly improve the rapidity and accuracy of diagnosis; in particular, for species identification. Recently, PCR and sequencing have paved the way for more user-friendly point-of-care tests, such as those based on LAMP or RCA technologies, which can be used in basic healthcare settings and even in field consultations.

Multiplex size marker (YEAST PLEX) for rapid and accurate identification of pathogenic yeasts

Background

Multiple yeast species can cause human disease, involving superficial to deep‐seated infections. Treatment of these infections depends on the accurate identification of causative agents; however, reliable methods are not available in many laboratories, especially not in resource‐limited settings. Here, a new multiplex assay for rapid and low‐cost identification of pathogenic yeasts is described.

Methods

A two‐step multiplex assay named YEAST PLEX that comprises of four tubes and identifies 17 clinically important common to rare yeasts was designed and evaluated. The set also provides PCR amplicon of unidentified species for direct sequencing. The specificity of YEAST PLEX was tested using 28 reference strains belonging to 17 species and 101 DNA samples of clinically important non‐target bacteria, parasites, and fungi as well as human genomic DNA. The method was further analyzed using 203 previously identified and 89 unknown clinical yeast isolates. Moreover, the method was tested for its ability to identify mixed yeast colonies by using 18 mixed suspensions of two or three species.

Results

YEAST PLEX was able to identify all the target species without any non‐specific PCR products. When compared to PCR‐sequencing/MALDI‐TOF, the results of YEAST PLEX were in 100% agreement. Regarding the 89 unknown clinical isolates, random isolates were selected and subjected to PCR‐sequencing. The results of sequencing were in agreement with those of YEAST PLEX. Furthermore, this method was able to correctly identify all yeasts in mixed suspensions.

Conclusion

YEAST PLEX is an accurate, low‐cost, and rapid method for identification of yeasts, with applicability, especially in developing countries.

Implementation of MALDI-TOF Mass Spectrometry to Identify Fungi From the Indoor Environment as an Added Value to the Classical Morphology-Based Identification Tool

Introduction

During the last decades, molds in the indoor environment have raised concern regarding their potential adverse health effects. The genera Aspergillus, Cladosporium, Penicillium, Alternaria, and yeasts, the most common fungi found indoors, include species with high allergenic and toxigenic potentials. Identification of these molds is generally performed by microscopy. This method has, however, some limitations as it requires mycologists with high expertise while identification is often limited to the genus level. Therefore, it is necessary to seek for fast and accurate tools, such as Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDITOF MS), enabling an identification to the species level and guiding general practitioners in their search for the underlying cause of a health problem.

Methods

In this study, 149 fungal air and dust isolates from 43 dwellings in Brussels were taken in collaboration with Brussels Environment RCIB/CRIPI and identified by both microscopy and MALDI-TOF MS in Sciensano's Indoor Mycology laboratory. Spectra obtained via MALDI-TOF MS were compared with data available in an in-house created reference database containing over 1,700 strains from the BCCM/IHEM fungal collection.

Results

A total of 149 isolates including 18 yeasts and 131 filamentous fungi were analyzed. Microscopic analysis indicated 18 yeast species and allowed identification of 79 isolates (53%) to the genus level. Only 36 isolates (24%) could be identified to the species complex level. Fifteen molds (10%) could not be identified, and one was indicated as sterile mycelia. No isolate was identified to species level. MALDI-TOF MS analysis identified 137 (92%) of the 149 isolates with a logscore > 1.7. Of these 137 isolates, 129 (87%) were identified to the species level (logscore > 2.0). For only 8 isolates (5%), identification was limited to the genus/section level (1.7 < logscore <2.0), and 12 isolates (8%) could not be identified.

Conclusion

A comparison of results obtained with both methods indicates an increased precision in identifications with MALDI-TOF MS analysis for 92% of the isolates, emphasizing its highly added value to the standard microscopic analysis in routine practice. In addition, MALDI-TOF MS also enables to assess the accuracy of microscopic identifications.

MALDI-Based Mass Spectrometry in Clinical Testing: Focus on Bacterial Identification

The term “proteome” refers to the total of all proteins expressed in an organism. The term “proteomics” refers to the field of research that includes not only information on the expression levels of individual proteins, but also their higher-order structures, intermolecular interactions, and post-translational modifications. The core technology, matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS), is available for protein analysis thanks to the work of Koichi Tanaka and John Fenn, who were awarded the Nobel Prize in Chemistry in 2002. The most successful proteome analysis in clinical practice is rapid microbial identification. This method determines the bacterial species by comparing the proteome profile of the bacteria obtained by matrix-assisted laser desorption ionization-time of flight MS (MALDI-TOF MS) with a database. MS is superior in simplicity, speed, and accuracy to classic speciation by staining and phenotyping. In clinical microbiology, MS has had a large impact on the diagnosis and treatment of infectious disease. Early diagnosis and treatment of infectious disease are important, and rapid identification by MALDI-TOF MS has made a major contribution to this field.

Combination of MALDI-TOF Mass Spectrometry and Machine Learning for Rapid Antimicrobial Resistance Screening: The Case of Campylobacter spp

While MALDI-TOF mass spectrometry (MS) is widely considered as the reference method for the rapid and inexpensive identification of microorganisms in routine laboratories, less attention has been addressed to its ability for detection of antimicrobial resistance (AMR). Recently, some studies assessed its potential application together with machine learning for the detection of AMR in clinical pathogens. The scope of this study was to investigate MALDI-TOF MS protein mass spectra combined with a prediction approach as an AMR screening tool for relevant foodborne pathogens, such as Campylobacter coli and Campylobacter jejuni. A One-Health panel of 224 C. jejuni and 116 C. coli strains was phenotypically tested for seven antimicrobial resistances, i.e., ciprofloxacin, erythromycin, tetracycline, gentamycin, kanamycin, streptomycin, and ampicillin, independently, and were submitted, after an on- and off-plate protein extraction, to MALDI Biotyper analysis, which yielded one average spectra per isolate and type of extraction. Overall, high performance was observed for classifiers detecting susceptible as well as ciprofloxacin- and tetracycline-resistant isolates. A maximum sensitivity and a precision of 92.3 and 81.2%, respectively, were reached. No significant prediction performance differences were observed between on- and off-plate types of protein extractions. Finally, three putative AMR biomarkers for fluoroquinolones, tetracyclines, and aminoglycosides were identified during the current study. Combination of MALDI-TOF MS and machine learning could be an efficient and inexpensive tool to swiftly screen certain AMR in foodborne pathogens, which may enable a rapid initiation of a precise, targeted antibiotic treatment.

Fungal infections diagnosis - Past, present and future

Despite the scientific advances observed in the recent decades and the emergence of new methodologies, the diagnosis of systemic fungal infections persists as a problematic issue. Fungal cultivation, the standard method that allows a proven diagnosis, has numerous disadvantages, as low sensitivity (only 50% of the patients present positive fungal cultures), and long growth time. These are factors that delay the patient's treatment and, consequently, lead to higher hospital costs. To improve the accuracy and quickness of fungal infections diagnosis, several new methodologies attempt to be implemented in clinical microbiology laboratories. Most of these innovative methods are independent of pathogen isolation, which means that the diagnosis goes from being considered proven to probable. In spite of the advantage of being culture-independent, the majority of the methods lack standardization. PCR-based methods are becoming more and more commonly used, which has earned them an important place in hospital laboratories. This can be perceived now, as PCR-based methodologies have proved to be an essential tool fighting against the COVID-19 pandemic. This review aims to go through the main steps of the diagnosis for systemic fungal infection, from diagnostic classifications, through methodologies considered as "gold standard", to the molecular methods currently used, and finally mentioning some of the more futuristic approaches.

Mycotoxigenic and phylogenetic perspective to the yeasts and filamentous moulds in mould-matured Turkish cheese

This study was conducted to determine the diversity of yeasts and filamentous moulds in mould-matured cheese (MMC) consumed in Turkey. Overall, 120 samples were collected from 12 different geographical locations between March 2016 and April 2017. The morphological observation was applied in combination with matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) and molecular analyses to determine yeasts and filamentous moulds in the cheeses. High-performance liquid chromatography (HPLC) technique was used to evaluate the ability of mycotoxins production of fungal isolates and the presence of mycotoxins in cheese samples. A total of 241 fungi (81 filamentous moulds and 160 yeast) were recovered, and Penicillium roqueforti and Debaryomyces hansenii were the most frequently isolated species in all cheese samples. The rep-PCR results indicated a high level of genetic diversity among fungal isolates, regardless of isolation source or geographical origin. Filamentous mould strains isolated from MMC were found to synthesize at least one mycotoxin (Aflatoxin B₁, B₂, G₁ and G₂, citrinine, cyclopiazonic acid, mycophenolic acid, ochratoxin A, penicillic acid and roquefortine C). Although mycotoxin producing ability was observed from all isolates, none of the cheese samples were found positive for these mycotoxins. AFM₁ was detected in 8 (6.6%) MMC samples from which 2 (1.6%) were above the legal limits (0.05 μg/kg) set by the Turkish Food Codex (TFC) and European Commission (EC). In conclusion, Turkish MMCs were found to be contaminated with toxigenic fungi, so a potential public health risk, while low, exists. Therefore, the selection of nontoxigenic filamentous mould strains for cheese manufacturing and control of the ripening conditions is a critical need to ensure the quality and safety of Turkish MMC.

Investigation of MALDI-TOF Mass Spectrometry for Assessing the Molecular Diversity of Campylobacter jejuni and Comparison with MLST and cgMLST: A Luxembourg One-Health Study

There is a need for active molecular surveillance of human and veterinary Campylobacter infections. However, sequencing of all isolates is associated with high costs and a considerable workload. Thus, there is a need for a straightforward complementary tool to prioritize isolates to sequence. In this study, we proposed to investigate the ability of MALDI-TOF MS to pre-screen C. jejuni genetic diversity in comparison to MLST and cgMLST. A panel of 126 isolates, with 10 clonal complexes (CC), 21 sequence types (ST) and 42 different complex types (CT) determined by the SeqSphere+ cgMLST, were analysed by a MALDI Biotyper, resulting into one average spectra per isolate. Concordance and discriminating ability were evaluated based on protein profiles and different cut-offs. A random forest algorithm was trained to predict STs. With a 94% similarity cut-off, an AWC of 1.000, 0.933 and 0.851 was obtained for MLST_CC, MLST_ST and cgMLST profile, respectively. The random forest classifier showed a sensitivity and specificity up to 97.5% to predict four different STs. Protein profiles allowed to predict C. jejuni CCs, STs and CTs at 100%, 93% and 85%, respectively. Machine learning and MALDI-TOF MS could be a fast and inexpensive complementary tool to give an early signal of recurrent C. jejuni on a routine basis.