Accurate classification of Listeria species by MALDI-TOF mass spectrometry incorporating denoising autoencoder and machine learning

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.

Application of Matrix-Assisted Laser Desorption Ionization Time-of-Flight Mass Spectrometry for Identification of Foodborne Pathogens: Current Developments and Future Trends

Foodborne pathogens have gained sustained public attention, exerted significant pressure on food manufacturers, and posed serious health risks to human. Matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) has been employed for quick and accurate identification of microorganisms in the prevention of foodborne epidemics in recent years. Herein, we first summarize the principle of MALDI and its workflow for foodborne pathogens. Subsequently, we review the recent progress and applications of MALDI-TOF MS in foodborne pathogen determination. Additionally, we outline the expanded utilization of MALDI-based techniques for the identification of closely related species. We also assess the current gaps and propose possible solutions to address the existing challenges. MALDI-TOF MS is a promising biotool for rapid and accurate identification of foodborne microbes at the species and genus level in food samples. Database expansion and direct quantification of spoilage microbes are two promising areas for future progress in MALDI-TOF MS applications.

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.

Comparison of Zybio Kit and saponin in-house method in rapid identification of bacteria from positive blood cultures by EXS2600 matrix-assisted laser desorption ionization time-of-flight mass spectrometry system

We evaluated the performance of Zybio EXS2600 matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) (Zybio Inc., Chongqing, China) for the identification of bacteria from positive blood culture (BC) bottles using Blood Culture Positive Sample Pretreatment Kit (Zybio Inc., Chongqing, China) in comparison to an in-house saponin method. Following a positive signal by the BACTEC™ FX system, confirmation of identification was achieved using subcultured growing biomass used for MALDI-TOF MS analysis. A total of 94 positive BC bottles with 97 bacterial isolates were analyzed. The overall identification rates at the genus and species levels for the saponin method were 89.7% (87/97) and 74.2% (72/97), respectively. With the Zybio Kit, 88.7% (86/97) and 80.4% (78/97) of microorganisms were correctly identified to the genus and species levels, respectively. The saponin method identified 65.3% (32/49) of Gram-positive bacteria at the species level, whereas the Zybio Kit achieved a higher species-level identification rate of 79.6% (39/49) (p = 0.1153). The saponin method with additional on-plate formic acid extraction showed a significantly higher overall identification rate in comparison to the saponin method without that step for both genus (87.6% [85/97] vs. 70.1% [68/97], p = 0.0029) and species level (70.1% [68/97] vs. 46.4% [45/97], p = 0.0008). Identification rates of Gram-negative bacteria showed a higher identification rate, however, not statistically significant with additional Zybio Kit protocol step on both genus (85.4% [41/48] vs. 81.3% [39/48], p = 0.5858) and species level (77.1% [37/48] vs. 75% [36/48], p = 0.8120). Zybio Kit could offer an advantage in species-level identification, particularly for Gram-positive bacteria. The inclusion of on-plate formic acid extraction in the saponin method notably enhanced identification at both genus and species levels for Gram-positive bacteria. The extended protocol provided by the Zybio Kit could potentially offer an advantage in the identification of Gram-negative bacteria at both genus and species levels. Enhancements to the Zybio EXS2600 MALDI-TOF instrument software database are necessary.

Mass Spectrometry Imaging Combined with Sparse Autoencoder Method Reveals Altered Phosphorylcholine Distribution in Imipramine Treated Wild-Type Mice Brains

Mass spectrometry imaging (MSI) is essential for visualizing drug distribution, metabolites, and significant biomolecules in pharmacokinetic studies. This study mainly focuses on imipramine, a tricyclic antidepressant that affects endogenous metabolite concentrations. The aim was to use atmospheric pressure matrix-assisted laser desorption/ionization (AP-MALDI)-MSI combined with different dimensionality reduction methods to examine the distribution and impact of imipramine on endogenous metabolites in the brains of treated wild-type mice. Brain sections from both control and imipramine-treated mice underwent AP-MALDI-MSI. Dimensionality reduction methods, including principal component analysis, multivariate curve resolution, and sparse autoencoder (SAE), were employed to extract valuable information from the MSI data. Only the SAE method identified phosphorylcholine (ChoP) as a potential marker distinguishing between the control and treated mice brains. Additionally, a significant decrease in ChoP accumulation was observed in the cerebellum, hypothalamus, thalamus, midbrain, caudate putamen, and striatum ventral regions of the treated mice brains. The application of dimensionality reduction methods, particularly the SAE method, to the AP-MALDI-MSI data is a novel approach for peak selection in AP-MALDI-MSI data analysis. This study revealed a significant decrease in ChoP in imipramine-treated mice brains.

Enhancing mass spectrometry imaging accessibility using convolutional autoencoders for deriving hypoxia-associated peptides from tumors

Mass spectrometry imaging (MSI) allows to study cancer's intratumoral heterogeneity through spatially-resolved peptides, metabolites and lipids. Yet, in biomedical research MSI is rarely used for biomarker discovery. Besides its high dimensionality and multicollinearity, mass spectrometry (MS) technologies typically output mass-to-charge ratio values but not the biochemical compounds of interest. Our framework makes particularly low-abundant signals in MSI more accessible. We utilized convolutional autoencoders to aggregate features associated with tumor hypoxia, a parameter with significant spatial heterogeneity, in cancer xenograft models. We highlight that MSI captures these low-abundant signals and that autoencoders can preserve them in their latent space. The relevance of individual hyperparameters is demonstrated through ablation experiments, and the contribution from original features to latent features is unraveled. Complementing MSI with tandem MS from the same tumor model, multiple hypoxia-associated peptide candidates were derived. Compared to random forests alone, our autoencoder approach yielded more biologically relevant insights for biomarker discovery.

Predicting the age of field Anopheles mosquitoes using mass spectrometry and deep learning

Mosquito-borne diseases like malaria are rising globally, and improved mosquito vector surveillance is needed. Survival of Anopheles mosquitoes is key for epidemiological monitoring of malaria transmission and evaluation of vector control strategies targeting mosquito longevity, as the risk of pathogen transmission increases with mosquito age. However, the available tools to estimate field mosquito age are often approximate and time-consuming. Here, we show a rapid method that combines matrix-assisted laser desorption/ionization-time-of-flight mass spectrometry with deep learning for mosquito age prediction. Using 2763 mass spectra from the head, legs, and thorax of 251 field-collected Anopheles arabiensis mosquitoes, we developed deep learning models that achieved a best mean absolute error of 1.74 days. We also demonstrate consistent performance at two ecological sites in Senegal, supported by age-related protein changes. Our approach is promising for malaria control and the field of vector biology, benefiting other disease vectors like Aedes mosquitoes.

A head-to-head comparison of three MALDI-TOF mass spectrometry systems with 16S rRNA gene sequencing

Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) has revolutionized diagnostics in culture-based microbiology. Commonly used MALDI-TOF MS systems in clinical microbiology laboratories are MALDI Biotyper (Bruker Daltonics) and Vitek MS (bioMérieux), but recently the new EXS2600 (Zybio) has been launched. This study aimed to evaluate the performance of the three devices by comparing the results to 16S rRNA gene sequencing. A set of 356 previously collected difficult-to-identify bacteria was tested in parallel with the three systems. Only the direct smear method and simple formic acid extraction were applied. Valid results were achieved for 98.6%, 94.4%, and 93.3% of all isolates by MALDI Biotyper, EXS2600, and Vitek MS, respectively. Of all valid results, agreement with sequencing data was achieved in 98.9%, 98.5%, and 99.7% by MALDI Biotyper, EXS2600, and Vitek MS, respectively. Considering only the isolates with valid measurements at the single-species level, misidentification rates were 0%, 2.6%, and 1.1% for MALDI Biotyper, EXS2600, and Vitek MS, respectively. Apart from minor performance differences, our data demonstrate that the three systems provide comparable results and are suitable for use in medical diagnostic laboratories.

A 2D image 3D reconstruction function adaptive denoising algorithm

To address the issue of image denoising algorithms blurring image details during the denoising process, we propose an adaptive denoising algorithm for the 3D reconstruction of 2D images. This algorithm takes into account the inherent visual characteristics of human eyes and divides the image into regions based on the entropy value of each region. The background region is subject to threshold denoising, while the target region undergoes processing using an adversarial generative network. This network effectively handles 2D target images with noise and generates a 3D model of the target. The proposed algorithm aims to enhance the noise immunity of 2D images during the 3D reconstruction process and ensure that the constructed 3D target model better preserves the original image's detailed information. Through experimental testing on 2D images and real pedestrian videos contaminated with noise, our algorithm demonstrates stable preservation of image details. The reconstruction effect is evaluated in terms of noise reduction and the fidelity of the 3D model to the original target. The results show an average noise reduction exceeding 95% while effectively retaining most of the target's feature information in the original image. In summary, our proposed adaptive denoising algorithm improves the 3D reconstruction process by preserving image details that are often compromised by conventional denoising techniques. This has significant implications for enhancing image quality and maintaining target information fidelity in 3D models, providing a promising approach for addressing the challenges associated with noise reduction in 2D images during 3D reconstruction.

Accurate noise-robust classification of Bacillus species from MALDI-TOF MS spectra using a denoising autoencoder

Bacillus strains are ubiquitous in the environment and are widely used in the microbiological industry as valuable enzyme sources, as well as in agriculture to stimulate plant growth. The Bacillus genus comprises several closely related groups of species. The rapid classification of these remains challenging using existing methods. Techniques based on MALDI-TOF MS data analysis hold significant promise for fast and precise microbial strains classification at both the genus and species levels. In previous work, we proposed a geometric approach to Bacillus strain classification based on mass spectra analysis via the centroid method (CM). One limitation of such methods is the noise in MS spectra. In this study, we used a denoising autoencoder (DAE) to improve bacteria classification accuracy under noisy MS spectra conditions. We employed a denoising autoencoder approach to convert noisy MS spectra into latent variables representing molecular patterns in the original MS data, and the Random Forest method to classify bacterial strains by latent variables. Comparison of the DAE-RF with the CM method using the artificially noisy test samples showed that DAE-RF offers higher noise robustness. Hence, the DAE-RF method could be utilized for noise-robust, fast, and neat classification of Bacillus species according to MALDI-TOF MS data.

Listeria monocytogenes in foods-From culture identification to whole-genome characteristics

Listeria monocytogenes is an important foodborne pathogen, which is able to persist in the food production environments. The presence of these bacteria in different niches makes them a potential threat for public health. In the present review, the current information on the classical and alternative methods used for isolation and identification of L. monocytogenes in food have been described. Although these techniques are usually simple, standardized, inexpensive, and are routinely used in many food testing laboratories, several alternative molecular-based approaches for the bacteria detection in food and food production environments have been developed. They are characterized by the high sample throughput, a short time of analysis, and cost-effectiveness. However, these methods are important for the routine testing toward the presence and number of L. monocytogenes, but are not suitable for characteristics and typing of the bacterial isolates, which are crucial in the study of listeriosis infections. For these purposes, novel approaches, with a high discriminatory power to genetically distinguish the strains during epidemiological studies, have been developed, e.g., whole-genome sequence-based techniques such as NGS which provide an opportunity to perform comparison between strains of the same species. In the present review, we have shown a short description of the principles of microbiological, alternative, and modern methods of detection of L. monocytogenes in foods and characterization of the isolates for epidemiological purposes. According to our knowledge, similar comprehensive papers on such subject have not been recently published, and we hope that the current review may be interesting for research communities.