Detection of Mycobacterium avium ssp. paratuberculosis in Cultures From Fecal and Tissue Samples Using VOC Analysis and Machine Learning Tools

Detection of Mycobacterium avium subsp. paratuberculosis in Australian Cattle and Sheep by Analysing Volatile Organic Compounds in Faeces

Paratuberculosis is a debilitating disease of ruminants that causes significant economic loss in both cattle and sheep. Early detection of the disease is crucial to controlling the disease; however, current diagnostic tests lack sensitivity. This study evaluated the potential for volatile organic compounds (VOCs) detected by gas chromatography and an electronic nose (eNose) for use as diagnostic tools to differentiate between Map-infected and non-infected cattle and sheep. Solid-phase micro-extraction gas chromatography-mass spectrometry (SPME GC-MS) was used to quantify VOCs from the headspace of faecal samples (cattle and sheep), and partial least squares-discriminant analysis (PLS-DA) was used to determine the suitability as a diagnostic tool. Both the cattle and sheep models had high specificity and sensitivity, 98.1% and 92.3%, respectively, in cattle, and both were 100% in sheep. The eNose was also able to discriminate between Map-infected and non-infected sheep and cattle with 88.9% specificity and 100% sensitivity in sheep and 100% specificity and sensitivity in cattle. This is the first time that VOC analysis by eNose and GCMS has been used for identification of Map in cattle and sheep faeces. GCMS also allowed the identification of putative disease biomarkers, and the eNose diagnostic capability suggests it is a promising tool for point-of-care diagnosis for Map detection on farms.

Comparison of Machine Learning Tree-Based Algorithms to Predict Future Paratuberculosis ELISA Results Using Repeat Milk Tests

Machine learning algorithms have been applied to various animal husbandry and veterinary-related problems; however, its use in Johne's disease diagnosis and control is still in its infancy. The following proof-of-concept study explores the application of tree-based (decision trees and random forest) algorithms to analyze repeat milk testing data from 1197 Canadian dairy cows and the algorithms' ability to predict future Johne's test results. The random forest models using milk component testing results alongside past Johne's results demonstrated a good predictive performance for a future Johne's ELISA result with a dichotomous outcome (positive vs. negative). The final random forest model yielded a kappa of 0.626, a roc AUC of 0.915, a sensitivity of 72%, and a specificity of 98%. The positive predictive and negative predictive values were 0.81 and 0.97, respectively. The decision tree models provided an interpretable alternative to the random forest algorithms with a slight decrease in model sensitivity. The results of this research suggest a promising avenue for future targeted Johne's testing schemes. Further research is needed to validate these techniques in real-world settings and explore their incorporation in prevention and control programs.

A Mass Spectrometry-Machine Learning Approach for Detecting Volatile Organic Compound Emissions for Early Fire Detection

Mass spectrometry in parallel with real-time machine learning techniques were paired in a novel application to detect and identify chemically specific, early indicators of fires and near-fire events involving a set of selected materials: Mylar, Teflon, and poly(methyl methacrylate) (PMMA). The volatile organic compounds emitted during the thermal decomposition of each of the three materials were characterized using a quadrupole mass spectrometer which scanned the 1-200 m/z range. CO2, CH3CHO, and C6H6 were the main volatiles detected during Mylar thermal decomposition, while Teflon's thermal decomposition yielded CO2 and a set of fluorocarbon compounds including CF4, C2F4, C2F6, C3F6, CF2O, and CF3O. PMMA produced CO2 and methyl methacrylate (MMA, C5H8O2). The mass spectral peak patterns observed during the thermal decomposition of each material were unique to that material and were therefore useful as chemical signatures. It was also observed that the chemical signatures remained consistent and detectable when multiple materials were heated together. Mass spectra data sets containing the chemical signatures for each material and mixtures were collected and analyzed using a random forest panel machine learning classification. The classification was tested and demonstrated 100% accuracy for single material spectra and an average of 92.3% accuracy for mixed material spectra. This investigation presents a novel technique for the real-time, chemically specific detection of fire related VOCs through mass spectrometry which shows promise as a more rapid and accurate method for detecting fires or near-fire events.

Breath biomarkers associated withnontuberculosis mycobacteriadisease status in persons with cystic fibrosis: a pilot study

Pulmonary infections caused by mycobacteria cause significant mortality and morbidity in the human population. Diagnosing mycobacterial infections is challenging. An infection can lead to active disease or remain indolent with little clinical consequence. In patients with pulmonarynontuberculosis mycobacteria(PNTM) identification of infection and diagnosis of disease can take months to years. Our previous studies showed the potential diagnostic power of volatile molecules in the exhaled breath samples to detect active pulmonaryM. tuberculosisinfection. Herein, we demonstrate the ability to detect the disease status of PNTM in the breath of persons with cystic fibrosis (PwCF). We putatively identified 17 volatile molecules that could discriminate between active-NTM disease (n= 6), indolent patients (n= 3), and those patients who have never cultured an NTM (n= 2). The results suggest that further confirmation of the breath biomarkers as a non-invasive and culture-independent tool for diagnosis of NTM disease in a larger cohort of PwCF is warranted.

Machine Learning Approaches to Identify Discriminative Signatures of Volatile Organic Compounds (VOCs) from Bacteria and Fungi Using SPME-DART-MS

Point-of-care screening tools are essential to expedite patient care and decrease reliance on slow diagnostic tools (e.g., microbial cultures) to identify pathogens and their associated antibiotic resistance. Analysis of volatile organic compounds (VOC) emitted from biological media has seen increased attention in recent years as a potential non-invasive diagnostic procedure. This work explores the use of solid phase micro-extraction (SPME) and ambient plasma ionization mass spectrometry (MS) to rapidly acquire VOC signatures of bacteria and fungi. The MS spectrum of each pathogen goes through a preprocessing and feature extraction pipeline. Various supervised and unsupervised machine learning (ML) classification algorithms are trained and evaluated on the extracted feature set. These are able to classify the type of pathogen as bacteria or fungi with high accuracy, while marked progress is also made in identifying specific strains of bacteria. This study presents a new approach for the identification of pathogens from VOC signatures collected using SPME and ambient ionization MS by training classifiers on just a few samples of data. This ambient plasma ionization and ML approach is robust, rapid, precise, and can potentially be used as a non-invasive clinical diagnostic tool for point-of-care applications.

(S)-Reutericyclin: Susceptibility Testing and In Vivo Effect on Murine Fecal Microbiome and Volatile Organic Compounds

We aimed to assess the in vitro antimicrobial activity and the in vivo effect on the murine fecal microbiome and volatile organic compound (VOC) profile of (S)-reutericyclin. The antimicrobial activity of (S)-reutericyclin was tested against Clostridium difficile, Listeria monocytogenes, Escherichia coli, Enterococcus faecium, Staphylococcus aureus, Staphylococcus (S.) epidermidis, Streptococcus agalactiae, Pseudomonas aeruginosa and Propionibacterium acnes. Reutericyclin or water were gavage fed to male BALBc mice for 7 weeks. Thereafter stool samples underwent 16S based microbiome analysis and VOC analysis by gas chromatography mass spectrometry (GC-MS). (S)-reutericyclin inhibited growth of S. epidermidis only. Oral (S)-reutericyclin treatment caused a trend towards reduced alpha diversity. Beta diversity was significantly influenced by reutericyclin. Linear discriminant analysis Effect Size (LEfSe) analysis showed an increase of Streptococcus and Muribaculum as well as a decrease of butyrate producing Ruminoclostridium, Roseburia and Eubacterium in the reutericyclin group. VOC analysis revealed significant increases of pentane and heptane and decreases of 2,3-butanedione and 2-heptanone in reutericyclin animals. The antimicrobial activity of (S)-reutericyclin differs from reports of (R)-reutericyclin with inhibitory effects on a multitude of Gram-positive bacteria reported in the literature. In vivo (S)-reutericyclin treatment led to a microbiome shift towards dysbiosis and distinct alterations of the fecal VOC profile.

Detection of Paratuberculosis in Dairy Herds by Analyzing the Scent of Feces, Alveolar Gas, and Stable Air

Paratuberculosis is an important disease of ruminants caused by Mycobacterium avium ssp. paratuberculosis (MAP). Early detection is crucial for successful infection control, but available diagnostic tests are still dissatisfying. Methods allowing a rapid, economic, and reliable identification of animals or herds affected by MAP are urgently required. This explorative study evaluated the potential of volatile organic compounds (VOCs) to discriminate between cattle with and without MAP infections. Headspaces above fecal samples and alveolar fractions of exhaled breath of 77 cows from eight farms with defined MAP status were analyzed in addition to stable air samples. VOCs were identified by GC-MS and quantified against reference substances. To discriminate MAP-positive from MAP-negative samples, VOC feature selection and random forest classification were performed. Classification models, generated for each biological specimen, were evaluated using repeated cross-validation. The robustness of the results was tested by predicting samples of two different sampling days. For MAP classification, the different biological matrices emitted diagnostically relevant VOCs of a unique but partly overlapping pattern (fecal headspace: 19, alveolar gas: 11, stable air: 4-5). Chemically, relevant compounds belonged to hydrocarbons, ketones, alcohols, furans, and aldehydes. Comparing the different biological specimens, VOC analysis in fecal headspace proved to be most reproducible, discriminatory, and highly predictive.