Resistance Profile, Terbinafine Resistance Screening and MALDI-TOF MS Identification of the Emerging Pathogen Trichophyton indotineae.

The emerging pathogen Trichophyton indotineae, often resistant to terbinafine (TRB), is known to cause severe dermatophytoses such as tinea corporis and tinea cruris. In order to achieve successful treatment for these infections, insight in the resistance profile of T. indotineae strains and rapid, reliable identification is necessary. In this research, a screening medium was tested on T. indotineae strains (n = 20) as an indication tool of TRB resistance. The obtained results were confirmed by antifungal susceptibility testing (AST) for TRB following the in vitro broth microdilution reference method. Additionally, AST was performed for eight other antifungal drugs: fluconazole, itraconazole, voriconazole, ketoconazole, griseofulvin, ciclopirox olamine, naftifine and amorolfine. Forty-five percent of the strains were confirmed to be resistant to terbinafine. The TRB resistant strains showed elevated minimal inhibitory concentration values for naftifine and amorolfine as well. DNA sequencing of the squalene epoxidase-encoding gene showed that TRB resistance was a consequence of missense point mutations in this gene, which led to amino acid substitutions F397L or L393F. MALDI-TOF MS was used as a quick, accurate identification tool for T. indotineae, as it can be challenging to distinguish it from closely related species such as Trichophyton mentagrophytes or Trichophyton interdigitale using morphological characteristics. While MALDI-TOF MS could reliably identify ≥ 95% of the T. indotineae strains (depending on the spectral library), it could not be used to successfully distinguish TRB susceptible from TRB resistant strains.

Yeast Biodiversity of Karst Waters: Interest of Four Culture Media and an Improved MALDI-TOF MS Database.

Karst aquifers are a significant source of drinking water and highly vulnerable to pollution and microbial contamination. Microbiological regulations for the quality of drinking water mostly focus on bacterial levels and lack guidance concerning fungal contamination. Moreover, there is no standardised microbial analysis methodology for identifying fungi in water. Our main objective was to establish the most effective culture and identification methodology to examine yeast diversity in karst waters. We assessed the comparative efficacy of four culture media (CHROMagar Candida, dichloran glycerol 18% [DG18], dichloran rose Bengal chloramphenicol [DRBC], and SYMPHONY agar) for yeast isolation from karst water samples. Furthermore, we investigated the comprehensiveness of databases used in MALDI-TOF mass spectrometry (MALDI-TOF MS) for identifying environmental yeast species. In total, we analysed 162 water samples, allowing the identification of 2479 yeast isolates. We demonstrate that a combination of four culture media, each with distinct specifications, more efficiently covers a wide range of yeast species in karst water than a combination of only two or three. Supplementation of a MALDI-TOF MS database is also critical for analysing environmental microbial samples and improved the identification of yeast biodiversity. This study is an initial step towards standardising the analysis of fungal biodiversity in karst waters, enabling a better understanding of the significance of this environmental reservoir in relation to public health.

Nosocomial transmission of Aspergillus flavus in a neonatal intensive care unit: Long-term persistence in environment and interest of MALDI-ToF mass-spectrometry coupled with convolutional neural network for rapid clone recognition.

Aspergillosis of the newborn remains a rare but severe disease. We report four cases of primary cutaneous Aspergillus flavus infections in premature newborns linked to incubators contamination by putative clonal strains. Our objective was to evaluate the ability of matrix-assisted laser desorption/ionisation time of flight (MALDI-TOF) coupled to convolutional neural network (CNN) for clone recognition in a context where only a very small number of strains are available for machine learning. Clinical and environmental A. flavus isolates (n = 64) were studied, 15 were epidemiologically related to the four cases. All strains were typed using microsatellite length polymorphism. We found a common genotype for 9/15 related strains. The isolates of this common genotype were selected to obtain a training dataset (6 clonal isolates/25 non-clonal) and a test dataset (3 clonal isolates/31 non-clonal), and spectra were analysed with a simple CNN model. On the test dataset using CNN model, all 31 non-clonal isolates were correctly classified, 2/3 clonal isolates were unambiguously correctly classified, whereas the third strain was undetermined (i.e., the CNN model was unable to discriminate between GT8 and non-GT8). Clonal strains of A. flavus have persisted in the neonatal intensive care unit for several years. Indeed, two strains of A. flavus isolated from incubators in September 2007 are identical to the strain responsible for the second case that occurred 3 years later. MALDI-TOF is a promising tool for detecting clonal isolates of A. flavus using CNN even with a limited training set for limited cost and handling time.

Cutaneous aspergillosis is a rare but potentially fatal disease of the prematurely born infant. We described here several cases due to Aspergillus flavus and have linked them to environnemental strains using MLP genotyping and MALDI-TOF mass spectrometry coupled with artificial intelligence.

Remarkable fungal biodiversity on northern Belgium bats and hibernacula.

Bats can be affected by fungal pathogens such as Pseudogymnoascus destructans, the causative agent of the white-nose syndrome. Their body surface can also be colonized by fungal commensals or carry transient fungal species and participate in their dispersal. In this study, 114 bat specimens belonging to seven species were sampled from various locations in northern Belgium. Culture-based methods revealed an important mycological diversity, with a total of 209 different taxa out of the 418 isolates. Overall, a mean of 3.7 taxa per bat was recorded, but significant differences were observed between sampling sites and seasons. The mycobiomes were dominated by cosmopolitan and plant-associated species, in particular from the genera Cladosporium, Penicillium, and Aspergillus. Other species known to be related to bats or their environment, such as Apiotrichum otae, were also retrieved. Sampling of hibernacula indicated that diverse fungal species can inhabit these sites, including a yet undescribed Pseudogymnoascus species, distinct from Ps. destructans, namely, Ps. cavicola.

Sexually Transmitted Trichophyton mentagrophytes Genotype VII Infection among Men Who Have Sex with Men.

Transmission of dermatophytes, especially Trichophyton mentagrophytes genotype VII, during sexual intercourse has been recently reported. We report 13 such cases in France. All patients were male; 12 were men who have sex with men. Our findings suggest sexual transmission of this pathogen within a specific population, men who have sex with men.

Evaluation of Gradient Concentration Strips for Detection of Terbinafine Resistance in Trichophyton spp.

The number of dermatophytosis cases resistant to terbinafine is increasing all over the world. Therefore, there is a need for antifungal susceptibility testing of dermatophytes for better management of the patients. In the present study, we have evaluated a gradient test (GT) method for testing the susceptibility of dermatophytes to terbinafine. MIC values to terbinafine determined by the EUCAST reference technique and by gradient test were compared for 79 Trichophyton spp. isolates. Overall, MICs were lower with gradient test (MIC50 of 0.002 µg/mL) than with EUCAST (MIC50 of 0.016 µg/mL). Good categorical agreement (>90%) between the 2 techniques was obtained but the essential agreement was variable depending on the batch of gradient test.

Intestinal Candida albicans overgrowth in IgA deficiency.

BACKGROUND: Secretory IgA interacts with commensal bacteria, but its impact on human mycobiota ecology has not been widely explored. In particular, whether human IgA-deficiency is associated with gut fungal dysbiosis remains unknown. OBJECTIVES: Our goal was to study the impact of IgA on gut mycobiota ecology. METHODS: The Fungi-Flow method was used to characterize fecal, systemic, and maternal IgA, IgM, and IgG responses against 14 representative fungal strains (yeast/spores or hyphae forms) in healthy donors (HDs) (n = 34, 31, and 20, respectively) and to also compare gut mycobiota opsonization by secretory antibodies in HDs (n = 28) and patients with selective IgA deficiency (SIgAd) (n = 12). Stool mycobiota composition was determined by internal transcribed spacer gene sequencing in HDs (n = 23) and patients with SIgAd (n = 17). Circulating CD4+ T-cell cytokine secretion profiles were determined by intracellular staining. The impact of secretory IgA, purified from breast milk (n = 9), on Candidaalbicans growth and intestinal Caco-2 cell invasion was tested in vitro. RESULTS: Homeostatic IgA binds commensal fungi with a body fluid-selective pattern of recognition. In patients with SIgAd, fungal gut ecology is preserved by compensatory IgM binding to commensal fungi. Gut Calbicans overgrowth nevertheless occurs in this condition but only in clinically symptomatic patients with decreased TH17/TH22 T-cell responses. Indeed, secretory IgA can reduce in vitro budding and invasion of intestinal cells by Calbicans and therefore exert control on this pathobiont. CONCLUSION: IgA has a selective impact on Calbicans ecology to preserve fungal-host mutualism.

Multifocal cutaneous phaeohyphomycosis caused by Exophiala spinifera with clinical resolution in an immunocompromised cat.

Case summary: A 3-year-old neutered domestic shorthair cat with a long history of idiopathic immune-mediated haemolytic anaemia and thrombocytopenia treated with ciclosporin and prednisolone was referred 2 months after the appearance of nodular dermatitis. A single pigmented nodule was present in the lateral carpal region of the right foreleg. The lesion was 7 mm in diameter, non-exudative and cutaneous to subcutaneous. Fine-needle aspiration of the mass revealed the presence of pigmented fungal elements. Excisional surgery was planned; in the meantime, a plaque-like lesion developed in the interorbital region. Histopathological examination confirmed the presumptive diagnosis of phaeohyphomycosis, and Exophiala spinifera was identified as the aetiological agent. Itraconazole, given orally at a dose of 10 mg/kg for 8 weeks following surgery, enabled clinical resolution despite continued use of immunosuppressants. The follow-up was carried out over 14 weeks. Relevance and novel information: This case report provides the first evidence of multifocal cutaneous phaeohyphomycosis caused by E spinifera with clinical resolution after combined surgical and itraconazole treatment in an immunocompromised cat.

Reliability of a terbinafine agar containing method for the screening of dermatophyte resistance.

The increase in terbinafine resistance worldwide due to Trichophyton indotineae underlies the need for surveillance networks, deploying easy to perform methods to correctly identify resistant isolates and thereby reduce their spread. In the present study, we evaluated the performances of the terbinafine containing agar method (TCAM). Different technical parameters, such as culture medium (RPMI agar [RPMIA] or Sabouraud dextrose agar [SDA]) and inoculum size, were evaluated. Our study showed that terbinafine susceptibility determined using the TCAM was reliable and independent of the inoculum or medium used. We then performed a multicenter, blinded study. 5 isolates of T. indotineae and 15 of genotype I or II of T. interdigitale, including 5 terbinafine-resistant isolates (4 T. indotineae and 1 T. interdigitale), were sent to eight clinical microbiology laboratories. Each laboratory analyzed the 20 isolates' terbinafine susceptibility by the TCAM using both culture media. TCAM allowed all participants to correctly determine the terbinafine susceptibility of analyzed isolates without prior training. All participants agreed that the dermatophyte tested, regardless of species or genotype, grew better on SDA than on RPMIA medium but accumulated fungal growth after 14 days eventually minimized the effect of this difference. In conclusion, TCAM is a reliable, easy to perform screening method for assessing terbinafine resistance. However, despite good performances, TCAM is a qualitative method and minimal inhibitory concentrations must be determined by the European Committee for Antimicrobial Susceptibility Testing standardized method to follow the evolution of terbinafine resistance levels.

The increase in terbinafine resistance worldwide due to Trichophyton indotineae underlies the need for surveillance networks. The terbinafine containing agar method is a reliable and easy-to-use tool in clinical microbiology laboratories. It can be used to rapidly screening resistant isolates, thereby reducing their spread.

Improving the Detection of Epidemic Clones in Candida parapsilosis Outbreaks by Combining MALDI-TOF Mass Spectrometry and Deep Learning Approaches.

Identifying fungal clones propagated during outbreaks in hospital settings is a problem that increasingly confronts biologists. Current tools based on DNA sequencing or microsatellite analysis require specific manipulations that are difficult to implement in the context of routine diagnosis. Using deep learning to classify the mass spectra obtained during the routine identification of fungi by MALDI-TOF mass spectrometry could be of interest to differentiate isolates belonging to epidemic clones from others. As part of the management of a nosocomial outbreak due to Candida parapsilosis in two Parisian hospitals, we studied the impact of the preparation of the spectra on the performance of a deep neural network. Our purpose was to differentiate 39 otherwise fluconazole-resistant isolates belonging to a clonal subset from 56 other isolates, most of which were fluconazole-susceptible, collected during the same period and not belonging to the clonal subset. Our study carried out on spectra obtained on four different machines from isolates cultured for 24 or 48 h on three different culture media showed that each of these parameters had a significant impact on the performance of the classifier. In particular, using different culture times between learning and testing steps could lead to a collapse in the accuracy of the predictions. On the other hand, including spectra obtained after 24 and 48 h of growth during the learning step restored the good results. Finally, we showed that the deleterious effect of the device variability used for learning and testing could be largely improved by including a spectra alignment step during preprocessing before submitting them to the neural network. Taken together, these experiments show the great potential of deep learning models to identify spectra of specific clones, providing that crucial parameters are controlled during both culture and preparation steps before submitting spectra to a classifier.

Trichophyton indotineae, from epidemiology to therapeutic.

Trichophyton indotineae is a newly described dermatophyte species. This fungal pathogen has recently emerged in India and is responsible for chronic or recurrent widespread superficial infections. Resistance to terbinafine is frequently associated to this pathogen and is related to point mutations in the gene encoding the squalene epoxidase. T. indotineae infections have been reported outside India, highlighting the risk of worldwide diffusion of this microorganism. Species identification and antifungal susceptibility determination are key points for infection control but still remain challenging. Systemic treatment is usually required and itraconazole is frequently prescribed in case of terbinafine resistance. This review summarizes main features of T. indotineae taxonomy, epidemiology, clinical manifestations, identification, antifungal profile, treatment and prevention.

Hospital Clonal Outbreak of Fluconazole-Resistant Candida parapsilosis Harboring the Y132F ERG11p Substitution in a French Intensive Care Unit.

We report the first identification of a fluconazole-resistant Candida parapsilosis (FR-Cp) strain in our hospital, which subsequently caused an outbreak involving 17 patients (12 deaths) within a 26-bed French intensive care unit. Microsatellite genotyping confirmed that all FR-Cp isolates belonged to the same clone. Given recent reports of rapid dissemination of these emerging clones, routine testing of azole susceptibility for all Candida parapsilosis isolates should be encouraged, at least in ICU patients.

Hospital outbreak of fluconazole-resistant Candida parapsilosis: arguments for clonal transmission and long-term persistence.

The worldwide emergence of multidrug-resistant pathogenic fungi is a threat to human health. At this very moment, an emergence of Candida parapsilosis isolates harbouring a resistance to fluconazole, one of the most popular antifungal drugs, is being described in several countries. We seek to better understanding the epidemiology, pathogenicity and transmission of resistant Candida parapsilosis Faced with an outbreak of invasive infections due to resistant isolates of C. parapsilosis, we performed a 7-year retrospective and prospective analysis of 283 C. parapsilosis isolates collected in 240 patients, among who 111 had invasive candidiasis. Study included review of hospital records, genotyping analysis and susceptibility testing that allow determining the type and outcome of infections, as well as the spatial and temporal spread of clusters. Overall the incidence of azole resistance was 7.5%. Genotyping analysis unveiled several previously undetected outbreaks and clonal spread of susceptible and resistant isolates over a long period of time. In comparison with susceptible isolates, resistant ones have a more restricted genetic diversity and seem to be more likely to spread and more frequently associated with invasive infections. In intensive care units, patients with invasive infections due to resistant isolates had poorer outcome (overall mortality at day 30 of 40%; 4/10) than susceptible ones (overall mortality at day 30 of 26.5%; 9/34). Our results suggest that the propensity of C. parapsilosis to spread on an epidemic fashion is underestimated, which warrants reinforced control and epidemiological survey of this species.

Evaluation of a Liquid Media MALDI-TOF MS Protocol for the Identification of Dermatophytes Isolated from Tinea capitis Infections.

One of the most common types of tinea is the superficial infection of the hair and scalp area known as tinea capitis. It is responsible for frequent outbreaks in nurseries and schools and represents a global health problem. Correct identification of the infection agent is essential in the determination of the infection source, epidemiological course, and treatment initiation. The conventional identification methods (direct exam, culture, DNA sequencing) are time-consuming, require experienced staff, are time-consuming, and the latter is expensive for routine identifications. Matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) is gaining new ground for routine identification of filamentous fungi. The main advantages of MALDI-TOF MS are its rapid and accurate identification capability, relatively low cost, and easy integration into the laboratory routine. Its accuracy heavily depends on the quality of the reference spectra database. Identification of clinical isolates with MALDI-TOF MS protocol requires a sub-culturing step to ensure reliable identification. It can take days to weeks before fungal growth appears on solid medium. In this study, a unique MALDI-TOF MS protocol using liquid cultures of dermatophyte species was developed in order to shorten the turnaround time for the culture and identification of clinical isolates. Material and Method A standard MALDI-TOF MS protocol was adapted for liquid instead of solid cultures. Three different databases were tested. Results Using the liquid media MALDI-TOF MS protocol, a global rate of 62% correct identification (RCI) was obtained, compared with 87% for the protocol based on solid cultures. Trichophyton tonsurans was not correctly identified in all isolates using liquid cultures, with 88% of the isolates misidentified as Trichophyton interdigitale. The turnaround time for primary isolates for the solid and liquid protocols were respectively 11.7 and 11.6 days (no significant difference between both methods (p = 0.96)). Conclusions The newly designed liquid MALDI-TOF MS protocol did not lead to a significantly shorter turnaround time for the identification of dermatophytes isolated from tinea capitis infections. The turnaround time for the method with primary isolates was not significantly lower, and the rate of correct identification decreased remarkably, which emphasizes the need for a sub-culturing step. Using different database did not lead to improvement in turnaround time or rate of correct identification. This study highlights the importance of the medium and the reference database when performing MALDI-TOF MS.

A Practical Workflow for the Identification of Aspergillus, Fusarium, Mucorales by MALDI-TOF MS: Database, Medium, and Incubation Optimization.

There is an increasing body of literature on the utility of MALDI-TOF MS in the identification of filamentous fungi. However, the process still lacks standardization. In this study, we attempted to establish a practical workflow for the identification of three clinically important molds: Aspergillus, Fusarium, and Mucorales using MALDI-TOF MS. We evaluated the performance of Bruker Filamentous Fungi database v3.0 for the identification of these fungi, highlighting when there would be a benefit of using an additional database, the MSI-2 for further identification. We also examined two other variables, namely, medium effect and incubation time on the accuracy of fungal identification. The Bruker database achieved correct species level identification in 85.7% of Aspergillus and 90% of Mucorales, and correct species-complex level in 94.4% of Fusarium. Analysis of spectra using the MSI-2 database would also offer additional value for species identification of Aspergillus species, especially when suspecting species with known identification limits within the Bruker database. This issue would only be of importance in selected cases where species-level identification would impact therapeutic options. Id-Fungi plates (IDFP) had almost equivalent performance to Sabouraud dextrose agar (SDA) for species-level identification of isolates and enabled an easier harvest of the isolates with occasional faster identification. Our study showed accurate identification at 24 h for Fusarium and Mucorales species, but not for Aspergillus species, which generally required 48 h.

MALDI-TOF Mass Spectrometry Online Identification of Trichophyton indotineae Using the MSI-2 Application.

Trichophyton indotineae is an emerging pathogen which recently spread from India to Europe and that is more prone than other species of the Trichophyton mentagrophytes complex to show resistance to terbinafine, resulting in the necessity of rapid identification. Here, we improved the online MSI-2 MALDI-TOF identification tool in order to identify T. indotineae. By multiplying the culture conditions (2 culture media and 6 stages of growth) prior to protein extractions for both test isolates and reference strains, we added 142 references corresponding to 12 strains inside the T. mentagrophytes complex in the online MSI-2 database, of which 3 are T. indotineae strains. The resulting database was tested with 1566 spectra of 67 isolates from the T. mentagrophytes complex, including 16 T. indotineae isolates. Using the newly improved MSI-2 database, we increased the identification rate of T. indotineae from 5% to 96%, with a sensitivity of 99.6%. We also identified specific peaks (6834/6845 daltons and 10,634/10,680 daltons) allowing for the distinction of T. indotineae from the other species of the complex. Our improved version of the MSI-2 application allows for the identification of T. indotineae. This will improve the epidemiological knowledge of the spread of this species throughout the world and will help to improve patient care.

Species Identification and In Vitro Antifungal Susceptibility of Paecilomyces/Purpureocillium Species Isolated from Clinical Respiratory Samples: A Multicenter Study.

Paecilomyces spp. are emerging fungal pathogens, where Paecilomyceslilacinus and Paecilomyces variotii are the most reported species. Taxonomic and phylogenetic revisions in this genus have shown that P. variotii represents a species complex, whereas P. lilacinus is related to another genus called Purpureocillium. The aims of this study were to identify clinical isolates of Paecilomyces spp. at the species level, and to determine their antifungal susceptibility profiles. 70 clinical Paecilomyces spp. isolates were identified by MALDI-TOF Mass Spectrometry (MS) and by multilocus rDNA genes sequencing including ITS and the D1/D2 genes. Among the 70 Paecilomyces spp. isolates, 28 were identified as P. lilacinum, 26 as P. variotii stricto sensu, and 16 as P. maximus. For antifungal susceptibility testing, Minimal Inhibitory Concentrations (MICs) or Minimal Effective Concentrations (MECs) were determined for 8 antifungals. All P. lilacinum isolates had high MICs and MECs of amphotericin B and echinocandins, respectively, unlike P. variotii and P. maximus. For azole drugs, MICs were molecule- and species- dependent. The differences in in vitro susceptibility to antifungals underline the importance of accurate species identification. The MALDI-TOF MS can be a good alternative in routine laboratory to ensure fast identification of Paecilomyces spp. and P. lilacinum.

Terbinafine Resistance in Dermatophytes: A French Multicenter Prospective Study.

In recent years, we have moved from the sporadic description of terbinafine-resistant (TerR) Trichophyton spp. isolates to the Indian outbreak due to T. indotineae. Population flows have spread TerR worldwide, altering local epidemiology. We conducted a prospective multicentric study to determine the relative frequency of TerR isolates in France (Paris area) and of the newly introduced T. indotineae species. TerR isolates were screened by the terbinafine-containing-agar-medium (TCAM) method and confirmed by EUCAST. Sequencing methods were used to identify isolates to the species/genotype level and to analyze substitutions in the squalene epoxidase gene (SQLE). In total, 3 isolates out of 580 (T. rubrumn = 1; T. interdigitalen = 1; T. indotineaen = 1) grew on TCAM, showed terbinafine resistance by EUCAST and harbored the Phe397Leu (n = 2) or Leu393Ser (n = 1) substitution in the SQLE. ITS-sequencing of isolates of the T. mentagrophytes/interdigitale complex (n = 125) revealed a relative frequency of 4.8% for T. indotineae and the presence of T. mentagrophytes genotype VII. Despite the detection of terbinafine resistance, isolates from this complex remained susceptible to itraconazole, voriconazole and amorolfine. Terbinafine resistance is present in France and the dermatophyte epidemiology is changing. Efficient systems must be implemented to survey the evolution of newly introduced species and to identify TerR isolates.

Investigations upon the Improvement of Dermatophyte Identification Using an Online Mass Spectrometry Application.

Online MALDI-TOF mass spectrometry applications, such as MSI-2, have been shown to help identify dermatophytes, but recurrent errors are still observed between phylogenetically close species. The objective of this study was to assess different approaches to reduce the occurrence of such errors by adding new reference spectra to the MSI-2 application. Nine libraries were set up, comprising an increasing number of spectra obtained from reference strains that were submitted to various culture durations on two distinct culture media: Sabouraud gentamicin chloramphenicol medium and IDFP Conidia medium. The final library included spectra from 111 strains of 20 species obtained from cultures on both media collected every three days after the appearance of the colony. The performance of each library was then analyzed using a cross-validation approach. The spectra acquisitions were carried out using a Microflex Bruker spectrometer. Diversifying the references and adding spectra from various culture media and culture durations improved identification performance. The percentage of correct identification at the species level rose from 63.4 to 91.7% when combining all approaches. Nevertheless, residual confusion between close species, such as Trichophyton rubrum, Trichophyton violaceum and Trichophyton soudanense, remained. To distinguish between these species, mass spectrometry identification should take into account basic morphological and/or clinico-epidemiological features.

Identification of a clonal population of Aspergillus flavus by MALDI-TOF mass spectrometry using deep learning.

The spread of fungal clones is hard to detect in the daily routines in clinical laboratories, and there is a need for new tools that can facilitate clone detection within a set of strains. Currently, Matrix Assisted Laser Desorption-Ionization Time-of-Flight Mass Spectrometry is extensively used to identify microbial isolates at the species level. Since most of clinical laboratories are equipped with this technology, there is a question of whether this equipment can sort a particular clone from a population of various isolates of the same species. We performed an experiment in which 19 clonal isolates of Aspergillus flavus initially collected on contaminated surgical masks were included in a set of 55 A. flavus isolates of various origins. A simple convolutional neural network (CNN) was trained to detect the isolates belonging to the clone. In this experiment, the training and testing sets were totally independent, and different MALDI-TOF devices (Microflex) were used for the training and testing phases. The CNN was used to correctly sort a large portion of the isolates, with excellent (> 93%) accuracy for two of the three devices used and with less accuracy for the third device (69%), which was older and needed to have the laser replaced.