Comparison of Machine Learning Algorithms for Predictive Modeling of Beef Attributes Using Rapid Evaporative Ionization Mass Spectrometry (REIMS) Data

Discrimination of beef composition and sensory quality by using rapid Evaporative Ionisation Mass Spectrometry (REIMS)

Herein, we investigated the potential of REIMS analysis for classifying muscle composition and meat sensory quality. The study utilized 116 samples from 29 crossbred Angus × Salers, across three muscle types. Prediction models were developed combining REIMS fingerprints and meat quality metrics. Varying efficacy was observed across REIMS discriminations - muscle type (71 %), marbling level (32 %), untrained consumer evaluated tenderness (36 %), flavor liking (99 %) and juiciness (99 %). Notably, REIMS demonstrated the ability to classify 116 beef across four Meat Standards Australia grades with an overall accuracy of 37 %. Specifically, "premium" beef could be differentiated from "unsatisfactory", "good everyday" and "better than everyday" grades with accuracies of 99 %, 84 %, and 62 %, respectively. Limited efficacy was observed however, in classifying trained panel evaluated sensory quality and fatty acid composition. Additionally, key predictive features were tentatively identified from the REIMS fingerprints primarily comprised of molecular ions present in lipids, phospholipids, and amino acids.

Navigating the development of silver nanoparticles based food analysis through the power of artificial intelligence

In the ongoing pursuit of enhancing food safety and quality through advanced technologies, silver nanoparticles (AgNPs) stand out for their antimicrobial properties. Despite being overshadowed by other nanoparticles in food sensing applications, AgNPs possess inherent qualities that make them effective tools for rapid and selective contaminant detection in food matrices. This review aims to reinvigorate the interest in AgNPs in the food industry, emphasizing their sensing mechanism and the transformative potential of integrating them with artificial intelligence (AI) for enhanced food safety monitoring. It discusses key AI tools and principles in the food industry, demonstrating their positive impact on food analytical chemistry. The interplay between AI and biosensors offers many advantages and adaptability to dynamic analytical challenges, significantly improving food safety monitoring and potentially redefining the landscape of food safety and quality assurance.

Rapid evaporative ionization mass spectrometry: A survey through 15 years of applications

Rapid evaporative ionization mass spectrometry (REIMS) is a relatively recent MS technique explored in many application fields, demonstrating high versatility in the detection of a wide range of chemicals, from small molecules (phenols, amino acids, di- and tripeptides, organic acids, and sugars) to larger biomolecules, that is, phospholipids and triacylglycerols. Different sampling devices were used depending on the analyzed matrix (liquid or solid), resulting in distinct performances in terms of automation, reproducibility, and sensitivity. The absence of laborious and time-consuming sample preparation procedures and chromatographic separations was highlighted as a major advantage compared to chromatographic methods. REIMS was successfully used to achieve a comprehensive sample profiling according to a metabolomics untargeted analysis. Moreover, when a multitude of samples were available, the combination with chemometrics allowed rapid sample differentiation and the identification of discriminant features. The present review aims to provide a survey of literature reports based on the use of such analytical technology, highlighting its mode of operation in different application areas, ranging from clinical research, mostly focused on cancer diagnosis for the accurate identification of tumor margins, to the agri-food sector aiming at the safeguard of food quality and security.

Modern machine-learning applications in ambient ionization mass spectrometry

This article provides a comprehensive overview of the applications of methods of machine learning (ML) and artificial intelligence (AI) in ambient ionization mass spectrometry (AIMS). AIMS has emerged as a powerful analytical tool in recent years, allowing for rapid and sensitive analysis of various samples without the need for extensive sample preparation. The integration of ML/AI algorithms with AIMS has further expanded its capabilities, enabling enhanced data analysis. This review discusses ML/AI algorithms applicable to the AIMS data and highlights the key advancements and potential benefits of utilizing ML/AI in the field of mass spectrometry, with a focus on the AIMS community.

A current review of U.S. beef flavor I: Measuring beef flavor

Historically, consumer acceptance of beef was determined by tenderness. Developments in genetics and management over the last couple of decades have improved tenderness to the point that it is secondary to other factors in beef's taste. Flavor, however, is an extraordinarily complex taste attribute dependent on biological sensors in the mouth, sinus cavity, and jaws. The culinary industry has recently focused on innovative ways to give consumers new products satisfying their curiosity about different foods, especially proteins. Competition from plant-based, cell-based, and even other animal-based proteins provides diversity in consumers' ability to select a protein that satisfies their desire to include unique products in their diet. Consequently, the beef industry has focused on flavor for the last 10 to 15 years to determine whether it can provide the guardrails for beef consumption in the future. The U.S. beef industry formed a Flavor Working Group in 2012 composed of the authors listed here to investigate new and innovative ways to manage and measure beef flavor. The results of this working group have resulted in dozens of papers, presentations, abstracts, and symposia. The objective of this manuscript is to summarize the research developed by this working group and by others worldwide that have investigated methodologies that measure beef flavor. This paper will describe the strengths of the research in beef flavor measurement and point out future needs that might be identified as technology advances.

Machine learning-guided REIMS pattern recognition of non-dairy cream, milk fat cream and whipping cream for fraudulence identification

The illegal adulteration of non-dairy cream in milk fat cream during the manufacturing process of baked goods has significantly hindered the robust growth of the dairy industry. In this study, a method based on rapid evaporative ionization mass spectrometry (REIMS) lipidomics pattern recognition integrated with machine learning algorithms was established. A total of 26 ions with importance were picked using multivariate statistical analysis as salient contributing features to distinguish between milk fat cream and non-dairy cream. Furthermore, employing discriminant analysis, decision trees, support vector machines, and neural network classifiers, machine learning models were utilized to classify non-dairy cream, milk fat cream, and minute quantities of non-dairy cream adulterated in milk fat cream. These approaches were enhanced through hyperparameter optimization and feature engineering, yielding accuracy rates at 98.4-99.6%. This artificial intelligent method of machine learning-guided REIMS pattern recognition can accurately identify adulteration of whipped cream and might help combat food fraud.

[Application progress of innovative high resolution separation and analysis technology in food safety detection field]

In the last decade, mass spectrometry (MS) has been widely used in food inspection science, and the continuous improvement of instruments is the key to the breakthrough of analytical chemistry technology. This paper discusses the latest progress and application of high resolution separation and analysis technology in food safety field (2013-2023), focusing on the innovative development technologies such as on-line MS coupling technology, high resolution screening technology and micro mass spectrometer. Finally, the development of new device in the field of food safety detection is prospected.

MSFC: a new feature construction method for accurate diagnosis of mass spectrometry data

Mass spectrometry technology can realize dynamic detection of many complex matrix samples in a simple, rapid, compassionate, precise, and high-throughput manner and has become an indispensable tool in accurate diagnosis. The mass spectrometry data analysis is mainly to analyze all metabolites in the organism quantitatively and to find the relative relationship between metabolites and physiological and pathological changes. A feature construction of mass spectrometry data (MSFS) method is proposed to construct the features of the original mass spectrometry data, so as to reduce the noise in the mass spectrometry data, reduce the redundancy of the original data and improve the information content of the data. Chi-square test is used to select the optimal non-redundant feature subset from high-dimensional features. And the optimal feature subset is visually analyzed and corresponds to the original mass spectrum interval. Training in 10 kinds of supervised learning models, and evaluating the classification effect of the models through various evaluation indexes. Taking two public mass spectrometry datasets as examples, the feasibility of the method proposed in this paper is verified. In the coronary heart disease dataset, during the identification process of mixed batch samples, the classification accuracy on the test set reached 1.000; During the recognition process, the classification accuracy on the test set advanced to 0.979. On the colorectal liver metastases data set, the classification accuracy on the test set reached 1.000. This paper attempts to use a new raw mass spectrometry data preprocessing method to realize the alignment operation of the raw mass spectrometry data, which significantly improves the classification accuracy and provides another new idea for mass spectrometry data analysis. Compared with MetaboAnalyst software and existing experimental results, the method proposed in this paper has obtained better classification results.

Early Diagnosis: End-to-End CNN-LSTM Models for Mass Spectrometry Data Classification

Liquid chromatography-mass spectrometry (LC-MS) is a powerful method for cell profiling. The use of LC-MS technology is a tool of choice for cancer research since it provides molecular fingerprints of analyzed tissues. However, the ubiquitous presence of noise, the peaks shift between acquisitions, and the huge amount of information owing to the high dimensionality of the data make rapid and accurate cancer diagnosis a challenging task. Deep learning (DL) models are not only effective classifiers but are also well suited to jointly learn feature representation and classification tasks. This is particularly relevant when applied to raw LC-MS data and hence avoid the need for costly preprocessing and complicated feature selection. In this study, we propose a new end-to-end DL methodology that addresses all of the above challenges at once, while preserving the high potential of LC-MS data. Our DL model is designed to early discriminate between tumoral and normal tissues. It is a combination of a convolutional neural network (CNN) and a long short-term memory (LSTM) Network. The CNN network allows for significantly reducing the high dimensionality of the data while learning spatially relevant features. The LSTM network enables our model to capture temporal patterns. We show that our model outperforms not only benchmark models but also state-of-the-art models developed on the same data. Our framework is a promising strategy for improving early cancer detection during a diagnostic process.

Molecular insights into quality and authentication of sheep meat from proteomics and metabolomics

Sheep meat (encompassing lamb, hogget and mutton) is an important source of animal protein in many countries, with a unique flavour and sensory profile compared to other red meats. Flavour, colour and texture are the key quality attributes contributing to consumer liking of sheep meat. Over the last decades, various factors from 'farm to fork', including production system (e.g., age, breed, feeding regimes, sex, pre-slaughter stress, and carcass suspension), post-mortem manipulation and processing (e.g., electrical stimulation, ageing, packaging types, and chilled and frozen storage) have been identified as influencing different aspects of sheep meat quality. However conventional meat-quality assessment tools are not able to elucidate the underlying mechanisms and pathways for quality variations. Advances in broad-based analytical techniques have offered opportunities to obtain deeper insights into the molecular changes of sheep meat which may become biomarkers for specific variations in quality traits and meat authenticity. This review provides an overview on how omics techniques, especially proteomics (including peptidomics) and metabolomics (including lipidomics and volatilomics) are applied to elucidate the variations in sheep meat quality, mainly in loin muscles, focusing on colour, texture and flavour, and as tools for authentication. SIGNIFICANCE: From this review, we observed that attempts have been made to utilise proteomics and metabolomics techniques on sheep meat products for elucidating pathways of quality variations due to various factors. For instance, the improvement of colour stability and tenderness could be associated with the changes to glycolysis, energy metabolism and endogenous antioxidant capacity. Several studies identify proteolysis as being important, but potentially conflicting for quality as the enhanced proteolysis improves tenderness and flavour, while reducing colour stability. The use of multiple analytical methods e.g., lipidomics, metabolomics, and volatilomics, detects a wider range of flavour precursors (including both water and lipid soluble compounds) that underlie the possible pathways for sheep meat flavour evolution. The technological advancement in omics (e.g., direct analysis-mass spectrometry) could make analysis of the proteins, lipids and metabolites in sheep meat routine, as well as enhance the confidence in quality determination and molecular-based assurance of meat authenticity.

Authentication of beef cuts by multielement and machine learning approaches

BACKGROUND

Brazil has consolidated a relevant position in the world market, being the largest exporter and second producer of beef. Genetics, feeding system, geographic origin and climate influence the multielement profile of beef. The feasibility of combining classification algorithms with major and trace elements was evaluated as a tool for authentication of beef cuts.

METHODS

Animals of Angus, Nelore and Wagyu crossbreeds, raised in a vertically integrated system, were sampled at the slaughterhouse for chuck steak, rump cap and sirloin steak. Supervised learning algorithms i.e. Classification and Regression Tree (CART), Multilayer Perceptron (MLP), Naïve Bayes (NB), Random Forest (RF) and Sequential Minimal Optimization (SMO) were used to build classification models based on the multielement profile of beef determined by neutron activation analysis.

RESULTS

Br, Co, Cs, Fe, K, Na, Rb, Se and Zn were determined in the beef samples. The classification accuracy values obtained for the beef cuts were 96% (MLP), 95% (SMO), 91% (RF), 86% (NB) and 70% (CART).

CONCLUSION

The Multilayer Perceptron algorithm provided the best classification performance towards authentication of beef cuts on basis of major and trace element mass fractions.

Rapid Evaporative Ionisation Mass Spectrometry fingerprinting can discriminate lamb meat due to different ageing methods and levels of dehydration

Dry-ageing is a technique for developing characteristic dry-aged flavour through the interplay of dehydration, lipid oxidation and microbial activities. In this study, we tested the hypothesis that the extent of drying influences the metabolite profile and the final flavour of lamb using an "Age-and-Dry" regime; and that Rapid Evaporative Ionisation Mass Spectrometry (REIMS) fingerprinting can be used to discriminate the metabolic fingerprints of lambs due to ageing methods and dehydration levels. Lamb loins (n = 60) were dehydrated with low (12%), medium (17%) and high (22%) weight losses and compared with the wet-aged equivalents using REIMS and evaluated by 12-member sensory panel. Orthogonal projection to latent structures-discriminant analysis (OPLS-DA) models based on 1400 tentatively identified m/z features were obtained for ageing methods (Q² > 0.95) and dehydration levels (Q² > 0.82) with high discrimination accuracy. Increased concentrations of dipeptides and metabolites associated with energy metabolism were observed in aged-and-dried lamb meat which supports the umami and savoury taste perceived by the sensory panel. A reduced concentration of polyunsaturated fatty acids with more aldehydes was observed in aged-and-dried lamb meat contributing to the nutty, roasted, and fatty flavour notes detected by the sensory panellists in these samples compared to the wet-aged. SIGNIFICANCE: Outcomes of this study demonstrated that REIMS can be used to accurately discriminate between different ageing methods and dehydration levels of meat, and the compounds that are associated with lamb flavour. The implications of this finding include: (1) the metabolite concentrating effect of dehydration and the associated effect on aged lamb flavour determined in this study could be used to tailor the processing of dry-aged lamb to deliver specific flavour outcomes in an industrial setting; (2) the ability of REIMS to rapidly detect differences in the aged lamb flavour due to dehydration effect would improve the quality of dry-aged meat and the efficiency with which it can be industrially produced. Thus, REIMS can be used as a rapid authentication and quality prediction tool for different ageing regimes and flavour for the meat industry.

- Invited Review - Postmortem skeletal muscle metabolism of farm animals approached with metabolomics

Skeletal muscle metabolism regulates homeostatic balance in animals. The metabolic impact persists even after farm animal skeletal muscle is converted to edible meat through postmortem rigor mortis and aging. Muscle metabolites resulting from animal growth and postmortem storage have a significant impact on meat quality, including flavor and color. Metabolomics studies of postmortem muscle aging have identified metabolisms that contain signatures inherent to muscle properties and the altered metabolites by physiological adaptation, with glycolysis as the pivotal metabolism in postmortem aging. Metabolomics has also played a role in mining relevant postmortem metabolisms and pathways, such as the citrate cycle and mitochondrial metabolism. This leads to a deeper understanding of the mechanisms underlying the generation of key compounds that are associated with meat quality. Genetic background, feeding strategy, and muscle type primarily determine skeletal muscle properties in live animals and affect post-mortem muscle metabolism. With comprehensive metabolite detection, metabolomics is also beneficial for exploring biomarker candidates that could be useful to monitor meat production and predict the quality traits. The present review focuses on advances in farm animal muscle metabolomics, especially postmortem muscle metabolism associated with genetic factors and muscle type.

Aggregation of Multimodal ICE-MS Data into Joint Classifier Increases Quality of Brain Cancer Tissue Classification

Mass spectrometry fingerprinting combined with multidimensional data analysis has been proposed in surgery to determine if a biopsy sample is a tumor. In the specific case of brain tumors, it is complicated to obtain control samples, leading to model overfitting due to unbalanced sample cohorts. Usually, classifiers are trained using a single measurement regime, most notably single ion polarity, but mass range and spectral resolution could also be varied. It is known that lipid groups differ significantly in their ability to produce positive or negative ions; hence, using only one polarity significantly restricts the chemical space available for sample discrimination purposes. In this work, we have developed an approach employing mass spectrometry data obtained by eight different regimes of measurement simultaneously. Regime-specific classifiers are trained, then a mixture of experts techniques based on voting or mean probability is used to aggregate predictions of all trained classifiers and assign a class to the whole sample. The aggregated classifiers have shown a much better performance than any of the single-regime classifiers and help significantly reduce the effect of an unbalanced dataset without any augmentation.

Harmonization of Rapid Evaporative Ionization Mass Spectrometry Workflows across Four Sites and Testing Using Reference Material and Local Food-Grade Meats

Rapid evaporative ionization mass spectrometry (REIMS) is a direct tissue metabolic profiling technique used to accurately classify tissues using pre-built mass spectral databases. The reproducibility of the analytical equipment, methodology and tissue classification algorithms has yet to be evaluated over multiple sites, which is an essential step for developing this technique for future clinical applications. In this study, we harmonized REIMS methodology using single-source reference material across four sites with identical equipment: Imperial College London (UK); Waters Research Centre (Hungary); Maastricht University (The Netherlands); and Queen's University (Canada). We observed that method harmonization resulted in reduced spectral variability across sites. Each site then analyzed four different types of locally-sourced food-grade animal tissue. Tissue recognition models were created at each site using multivariate statistical analysis based on the different metabolic profiles observed in the m/z range of 600-1000, and these models were tested against data obtained at the other sites. Cross-validation by site resulted in 100% correct classification of two reference tissues and 69-100% correct classification for food-grade meat samples. While we were able to successfully minimize between-site variability in REIMS signals, differences in animal tissue from local sources led to significant variability in the accuracy of an individual site's model. Our results inform future multi-site REIMS studies applied to clinical samples and emphasize the importance of carefully-annotated samples that encompass sufficient population diversity.

Evaluating the ability of rapid evaporative ionization mass spectrometry to differentiate beef palatability based on consumer preference

Rapid Evaporative Ionization Mass Spectrometry (REIMS) is a type of ambient ionization mass spectrometry, which enables real-time evaluation of several complex traits from a single measurement. The objective of this study was to evaluate the capability of REIMS analysis of raw samples coupled with chemometrics to accurately identify and predict cooked beef palatability. REIMS analysis and consumer sensory evaluation were conducted for beef arm center roasts (n = 20), top loin steaks (n = 20), top sirloin steaks (n = 20), and 20% lipid ground beef (n = 20). These data were used to train predictive models for six classification sets representing different sensory traits. The maximum prediction accuracies achieved (from high to low): beefy flavor acceptance (86.25%), juiciness acceptance (83.75%), overall acceptance (81.25%), overall flavor acceptance (81.25%), grilled flavor acceptance (78.75%), and tenderness acceptance (75%). The current study demonstrates that REIMS analysis of raw meat has the potential to predict and classify cooked beef palatability.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13197-022-05562-6.

Rapid Evaporative Ionization Mass Spectrometry (REIMS): a Potential and Rapid Tool for the Identification of Insecticide Resistance in Mosquito Larvae

Insecticide resistance is a significant challenge facing the successful control of mosquito vectors globally. Bioassays are currently the only method for phenotyping resistance. They require large numbers of mosquitoes for testing, the availability of a susceptible comparator strain, and often insectary facilities. This study aimed to trial the novel use of rapid evaporative ionization mass spectrometry (REIMS) for the identification of insecticide resistance in mosquitoes. No sample preparation is required for REIMS and analysis can be rapidly conducted within hours. Temephos resistant Aedes aegypti (Linnaeus) larvae from Cúcuta, Colombia and temephos susceptible larvae from two origins (Bello, Colombia, and the lab reference strain New Orleans) were analyzed using REIMS. We tested the ability of REIMS to differentiate three relevant variants: population source, lab versus field origin, and response to insecticide. The classification of these data was undertaken using linear discriminant analysis (LDA) and random forest. Classification models built using REIMS data were able to differentiate between Ae. aegypti larvae from different populations with 82% (±0.01) accuracy, between mosquitoes of field and lab origin with 89% (±0.01) accuracy and between susceptible and resistant larvae with 85% (±0.01) accuracy. LDA classifiers had higher efficiency than random forest with this data set. The high accuracy observed here identifies REIMS as a potential new tool for rapid identification of resistance in mosquitoes. We argue that REIMS and similar modern phenotyping alternatives should complement existing insecticide resistance management tools.

Rapid evaporative ionization mass spectrometry (REIMS) combined with chemometrics for real-time beer analysis

The beer industry plays an important role in the economy since this is the third most consumed beverage worldwide. Efficient analytical methods must be developed to ensure the quality of the product. Rapid evaporative ionization mass spectrometry (REIMS) can provide molecular-level information, while enabling fast analysis. REIMS requires minimal sample preparation and it is ideal for the analysis of homogeneous liquid samples, such as beers, within only five seconds. In this article, 32 different beers were analyzed by REIMS in positive and negative ionization modes using a hybrid quadrupole time-of-flight mass spectrometer. The positive and negative MS spectrum blocks were augmented for data fusion. A predictive model by partial least squares discriminant analysis (PLS-DA) was used to discriminate the samples (i) by their brands and (ii) by the beer type (Premium and Standard American lagers). The results showed that REIMS provided a rich fingerprint of beers, which was successfully used to discriminate the brands and types with 96.9% and 97.9% accuracy, respectively. We believe that this proof-of-concept has great potential to be applied on a larger scale for industrial purposes due to its high-throughput.

Application of Intraoperative Mass Spectrometry and Data Analytics for Oncological Margin Detection, A Review

OBJECTIVE

A common phase of early-stage oncological treatment is the surgical resection of cancerous tissue. The presence of cancer cells on the resection margin, referred to as positive margin, is correlated with the recurrence of cancer and may require re-operation, negatively impacting many facets of patient outcomes. There exists a significant gap in the surgeons ability to intraoperatively delineate between tissues. Mass spectrometry methods have shown considerable promise as intraoperative tissue profiling tools that can assist with the complete resection of cancer. To do so, the vastness of the information collected through these modalities must be digested, relying on robust and efficient extraction of insights through data analysis pipelines.

METHODS

We review clinical mass spectrometry literature and prioritize intraoperatively applied modalities. We also survey the data analysis methods employed in these studies.

RESULTS

Our review outlines the advantages and shortcomings of mass spectrometry imaging and point-based tissue probing methods. For each modality, we identify statistical, linear transformation and machine learning techniques that demonstrate high performance in classifying cancerous tissues across several organ systems. A limited number of studies presented results captured intraoperatively.

CONCLUSION

Through continued research of data centric techniques, like mass spectrometry, and the development of robust analysis approaches, intraoperative margin assessment is becoming feasible.

SIGNIFICANCE

By establishing the relatively short history of mass spectrometry techniques applied to surgical studies, we hope to inform future applications and aid in the selection of suitable data analysis frameworks for the development of intraoperative margin detection technologies.

The Relationship between Satellite-Derived Vegetation Indices and Live Weight Changes of Beef Cattle in Extensive Grazing Conditions

The live weight (LW) and live weight change (LWC) of cattle in extensive beef production is associated with pasture availability and quality. The remote monitoring of pastures and cattle LWC can be achieved with a combination of satellite imagery and walk-over-weighing (WoW) stations. The objective of the present study is to determine the association, if any, between vegetation indices (VIs) (pasture availability) and the LWC of beef cattle in an extensive breeding operation in Northern Australia. The study also tests a suite of VIs along with variables such as rainfall and Julian day to predict the LWC of breeding cows. The VIs were calculated from Sentinel-2 satellite imagery over a 2-year period from a paddock with 378 cattle. Animal LW was measured remotely using a weighing scale at the water point. The relationship between VIs, the LWC, and LW was assessed using linear mixed-effects regression models and random forest modelling. Findings demonstrate that all VIs calculated had a significant positive relationship with the LWC and LW (p < 0.001). Machine learning predictive modelling showed that the LWC of breeding cows could be predicted from VIs, Julian day, and rainfall information, with a Lin’s Concordance Correlation Coefficient of 0.62 when using the leave-one-month-out cross-validation. The LW and LWC were greater during the wet season when VIs were higher compared to the dry season (p < 0.001). Results suggest that the remote monitoring of pasture availability, the LWC and LW is possible under extensive grazing conditions. Further, the use of VIs and other readily available data such as rainfall can be used to predict the LWC of a breeding herd in extensive conditions. Such information could be used to increase the productivity and land management in extensive beef production. The integration of these data streams offers great potential to improve the monitoring, management, and productivity of grazing or cropping enterprises.

An appraisal of data collection, analysis, and reporting adopted for water quality assessment: A case of Nigeria water quality research

The appropriate acquisition and processing of water quality data are crucial for water resource management. As such, published articles on water quality monitoring and assessment are meant to convey essential and reliable information to water quality experts, decision-makers, researchers, students, and the public. The implication is that such information must emanate from data obtained and analysed in an up-to-date, scientifically sound manner. Thus, inappropriate data analysis and reporting techniques could yield misleading results and mar the endeavours of achieving error-free conclusions. This study utilises the findings on water quality assessment in Nigeria over the last 20 years to reveal the likely trends in water quality research regarding data collection, data analysis, and reporting for physicochemical, bacteriological parameters, and trace organics. A total of 123 Web of Science and quartile ranked (Q1-Q4) published articles involving water quality assessment in Nigeria were analysed. Results indicated shortcomings in various aspects of data analysis and reporting. Consequently, we use simulated heatmaps and graphs to illustrate preferred ways of analysing, reporting, and visualising some regularly used descriptive and inferential statistics of water quality variables. Finally, we highlight alternative approaches to the customarily applied water quality assessment methods in Nigeria and emphasise other areas of deficiency that need attention for improved water quality research.

Exhaled breath biomarkers of influenza infection and influenza vaccination

Respiratory viral infections are considered a major public health threat, and breath metabolomics can provide new ways to detect and understand how specific viruses affect the human pulmonary system. In this pilot study, we characterized the metabolic composition of human breath for an early diagnosis and differentiation of influenza viral infection, as well as other types of upper respiratory viral infections. We first studied the non-specific effects of planned seasonal influenza vaccines on breath metabolites in healthy subjects after receiving the immunization. We then investigated changes in breath content from hospitalized patients with flu-like symptoms and confirmed upper respiratory viral infection. The exhaled breath was sampled using a custom-made breath condenser, and exhaled breath condensate (EBC) samples were analysed using liquid chromatography coupled to quadruplole-time-of-flight mass spectrometer (LC-qTOF). All metabolomic data was analysed using both targeted and untargeted approaches to detect specific known biomarkers from inflammatory and oxidative stress biomarkers, as well as new molecules associated with specific infections. We were able to find clear differences between breath samples collected before and after flu vaccine administration, together with potential biomarkers that are related to inflammatory processes and oxidative stress. Moreover, we were also able to discriminate samples from patients with flu-related symptoms that were diagnosed with confirmatory respiratory viral panels (RVP). RVP positive and negative differences were identified, as well as differences between specific viruses defined. These results provide very promising information for the further study of the effect of influenza A and other viruses in human systems by using a simple and non-invasive specimen like breath.

Evaluation of ambient mass spectrometry tools for assessing inherent postharvest pepper quality

Horticulturists are interested in evaluating how cultivar, environment, or production system inputs can affect postharvest quality. Ambient mass spectrometry approaches enable analysis of minimally processed samples under ambient conditions and offer an attractive high-throughput alternative for assessing quality characteristics in plant products. Here, we evaluate direct analysis in real time (DART-MS) mass spectrometry and rapid evaporative ionization-mass spectrometry (REIMS) to assess quality characteristics in various pepper (Capsicum annuum L.) cultivars. DART-MS exhibited the ability to discriminate between pod colors and pungency based on chemical fingerprints, while REIMS could distinguish pepper market class (e.g., bell, lunchbox, and popper). Furthermore, DART-MS analysis resulted in the putative detection of important bioactive compounds in human diet such as vitamin C, p-coumaric acid, and capsaicin. The results of this study demonstrate the potential for these approaches as accessible and reliable tools for high throughput screening of pepper quality.

Sample Preparation Free Mass Spectrometry Using Laser-Assisted Rapid Evaporative Ionization Mass Spectrometry: Applications to Microbiology, Metabolic Biofluid Phenotyping, and Food Authenticity

Mass spectrometry has established itself as a powerful tool in the chemical, biological, medical, environmental, and agricultural fields. However, experimental approaches and potential application areas have been limited by a traditional reliance on sample preparation, extraction, and chromatographic separation. Ambient ionization mass spectrometry methods have addressed this challenge but are still somewhat restricted in requirements for sample manipulation to make it suitable for analysis. These limitations are particularly restrictive in view of the move toward high-throughput and automated analytical workflows. To address this, we present what we consider to be the first automated sample-preparation-free mass spectrometry platform utilizing a carbon dioxide (CO₂) laser for sample thermal desorption linked to the rapid evaporative ionization mass spectrometry (LA-REIMS) methodology. We show that the pulsatile operation of the CO₂ laser is the primary factor in achieving high signal-to-noise ratios. We further show that the LA-REIMS automated platform is suited to the analysis of three diverse biological materials within different application areas. First, clinical microbiology isolates were classified to species level with an accuracy of 97.2%, the highest accuracy reported in current literature. Second, fecal samples from a type 2 diabetes mellitus cohort were analyzed with LA-REIMS, which allowed tentative identification of biomarkers which are potentially associated with disease pathogenesis and a disease classification accuracy of 94%. Finally, we showed the ability of the LA-REIMS system to detect instances of adulteration of cooking oil and determine the geographical area of production of three protected olive oil products with 100% classification accuracy.

Machine Learning in Agriculture: A Comprehensive Updated Review

The digital transformation of agriculture has evolved various aspects of management into artificial intelligent systems for the sake of making value from the ever-increasing data originated from numerous sources. A subset of artificial intelligence, namely machine learning, has a considerable potential to handle numerous challenges in the establishment of knowledge-based farming systems. The present study aims at shedding light on machine learning in agriculture by thoroughly reviewing the recent scholarly literature based on keywords' combinations of "machine learning" along with "crop management", "water management", "soil management", and "livestock management", and in accordance with PRISMA guidelines. Only journal papers were considered eligible that were published within 2018-2020. The results indicated that this topic pertains to different disciplines that favour convergence research at the international level. Furthermore, crop management was observed to be at the centre of attention. A plethora of machine learning algorithms were used, with those belonging to Artificial Neural Networks being more efficient. In addition, maize and wheat as well as cattle and sheep were the most investigated crops and animals, respectively. Finally, a variety of sensors, attached on satellites and unmanned ground and aerial vehicles, have been utilized as a means of getting reliable input data for the data analyses. It is anticipated that this study will constitute a beneficial guide to all stakeholders towards enhancing awareness of the potential advantages of using machine learning in agriculture and contributing to a more systematic research on this topic.

Rapid Evaporative Ionization Mass Spectrometry: A Review on Its Application to the Red Meat Industry with an Australian Context

The red meat supply chain is a complex network transferring product from producers to consumers in a safe and secure way. There can be times when fragmentation can arise within the supply chain, which could be exploited. This risk needs reduction so that meat products enter the market with the desired attributes. Rapid Evaporative Ionisation Mass Spectrometry (REIMS) is a novel ambient mass spectrometry technique originally developed for rapid and accurate classification of biological tissue which is now being considered for use in a range of additional applications. It has subsequently shown promise for a range of food provenance, quality and safety applications with its ability to conduct ex vivo and in situ analysis. These are regarded as critical characteristics for technologies which can enable real-time decision making in meat processing plants and more broadly throughout the sector. This review presents an overview of the REIMS technology, and its application to the areas of provenance, quality and safety to the red meat industry, particularly in an Australian context.

Potential impact of tissue molecular heterogeneity on ambient mass spectrometry profiles: a note of caution in choosing the right disease model

This review provides a summary of known molecular alterations in commonly used cancer models and strives to stipulate how they may affect ambient mass spectrometry profiles. Immortalized cell lines are known to accumulate mutations, and xenografts derived from cell lines are known to contain tumour microenvironment elements from the host animal. While the use of human specimens for mass spectrometry profiling studies is highly encouraged, patient-derived xenografts with low passage numbers could provide an alternative means of amplifying material for ambient MS research when needed. Similarly, genetic preservation of patient tissue seen in some organoid models, further verified by qualitative proteomic and transcriptomic analyses, may argue in favor of organoid suitability for certain ambient profiling studies. However, to choose the appropriate model, pre-evaluation of the model's molecular characteristics in the context of the research question(s) being asked will likely provide the most appropriate strategy to move research forward. This can be achieved by performing comparative ambient MS analysis of the disease model of choice against a small amount of patient tissue to verify concordance. Disease models, however, will continue to be useful tools to orthogonally validate metabolic states of patient tissues through controlled genetic alterations that are not possible with patient specimens.

Cumulative learning enables convolutional neural network representations for small mass spectrometry data classification

Rapid and accurate clinical diagnosis remains challenging. A component of diagnosis tool development is the design of effective classification models with Mass spectrometry (MS) data. Some Machine Learning approaches have been investigated but these models require time-consuming preprocessing steps to remove artifacts, making them unsuitable for rapid analysis. Convolutional Neural Networks (CNNs) have been found to perform well under such circumstances since they can learn representations from raw data. However, their effectiveness decreases when the number of available training samples is small, which is a common situation in medicine. In this work, we investigate transfer learning on 1D-CNNs, then we develop a cumulative learning method when transfer learning is not powerful enough. We propose to train the same model through several classification tasks over various small datasets to accumulate knowledge in the resulting representation. By using rat brain as the initial training dataset, a cumulative learning approach can have a classification accuracy exceeding 98% for 1D clinical MS-data. We show the use of cumulative learning using datasets generated in different biological contexts, on different organisms, and acquired by different instruments. Here we show a promising strategy for improving MS data classification accuracy when only small numbers of samples are available.

Convolutional Neural Networks are powerful tools for clinical diagnosis but their effectiveness decreases when the number of available samples is small. Here, the authors develop a cumulative learning method by training the same model through several classification tasks over various small Mass Spectrometry datasets.

Making complex measurements of meat composition fast: Application of rapid evaporative ionisation mass spectrometry to measuring meat quality and fraud

Increasing demands are being placed on meat producers to verify more about their product with regards to safety, quality and authenticity. There are many methods that can detect aspects of these parameters in meat, yet most are too slow to keep up with the demands of modern meat processing plants and supply chains. A new technology, Rapid Evaporative Ionisation Mass Spectrometry (REIMS), has the potential to bridge the gap between advanced laboratory measurements and technology that can screen for quality, safety and authenticity parameters in a single measurement. Analysis with REIMS generates a detailed mass spectral fingerprint representative of a meat sample without the need for sample processing. REIMS has successfully been used to detect species fraud, detect use of hormones in meat animals, monitor meat processing and to detect off flavours such as boar taint. The aim of this review is to summarize these and other applications to highlight the potential of REIMS for meat analysis. Sampling methods and important considerations for data analysis are discussed as well as limitations of the technology and remaining challenges for practical adoption.

MEATabolomics: Muscle and Meat Metabolomics in Domestic Animals

In the past decades, metabolomics has been used to comprehensively understand a variety of food materials for improvement and assessment of food quality. Farm animal skeletal muscles and meat are one of the major targets of metabolomics for the characterization of meat and the exploration of biomarkers in the production system. For identification of potential biomarkers to control meat quality, studies of animal muscles and meat with metabolomics (MEATabolomics) has been conducted in combination with analyses of meat quality traits, focusing on specific factors associated with animal genetic background and sensory scores, or conditions in feeding system and treatments of meat in the processes such as postmortem storage, processing, and hygiene control. Currently, most of MEATabolomics approaches combine separation techniques (gas or liquid chromatography, and capillary electrophoresis)-mass spectrometry (MS) or nuclear magnetic resonance (NMR) approaches with the downstream multivariate analyses, depending on the polarity and/or hydrophobicity of the targeted metabolites. Studies employing these approaches provide useful information to monitor meat quality traits efficiently and to understand the genetic background and production system of animals behind the meat quality. MEATabolomics is expected to improve the knowledge and methodologies in animal breeding and feeding, meat storage and processing, and prediction of meat quality.

Prediction of marbling score and carcass traits in Korean Hanwoo beef cattle using machine learning methods and synthetic minority oversampling technique

Pricing of Hanwoo beef in the Korean market is primarily based on meat quality, and particularly on marbling score. The ability to accurately predict marbling score early in the life of an animal is extremely valuable for producers to meet the requirements of their target market, and for genetic selection. A total of 3989 Korean Hanwoo cattle (2108 with 50 k SNP genotypes) and 45 phenotypic features were available for this study. Four machine learning (ML) algorithms were applied to predict six carcass traits and compared against linear regression prediction models. In most scenarios, SMO was the best performing algorithm. The most and least accurately predicted traits were carcass weight and marbling score with correlation of 0.95 and 0.64 respectively. Additionally, the value of using a synthetic minority over-sampling technique (SMOTE) was evaluated and results showed a slight improvement in the prediction error of marbling score. Machine Learning approaches can be useful tools to predict important carcass traits in beef cattle.

Combination of an Automated 3D Field Phenotyping Workflow and Predictive Modelling for High-Throughput and Non-Invasive Phenotyping of Grape Bunches

In grapevine breeding, loose grape bunch architecture is one of the most important selection traits, contributing to an increased resilience towards Botrytis bunch rot. Grape bunch architecture is mainly influenced by the berry number, berry size, the total berry volume, and bunch width and length. For an objective, precise, and high-throughput assessment of these architectural traits, the 3D imaging sensor Artec® Spider was applied to gather dense point clouds of the visible side of grape bunches directly in the field. Data acquisition in the field is much faster and non-destructive in comparison to lab applications but results in incomplete point clouds and, thus, mostly incomplete phenotypic values. Therefore, lab scans of whole bunches (360°) were used as ground truth. We observed strong correlations between field and lab data but also shifts in mean and max values, especially for the berry number and total berry volume. For this reason, the present study is focused on the training and validation of different predictive regression models using 3D data from approximately 2000 different grape bunches in order to predict incomplete bunch traits from field data. Modeling concepts included simple linear regression and machine learning-based approaches. The support vector machine was the best and most robust regression model, predicting the phenotypic traits with an R2 of 0.70–0.91. As a breeding orientated proof-of-concept, we additionally performed a Quantitative Trait Loci (QTL)-analysis with both the field modeled and lab data. All types of data resulted in joint QTL regions, indicating that this innovative, fast, and non-destructive phenotyping method is also applicable for molecular marker development and grapevine breeding research.

Monitoring recombinant protein expression in bacteria by rapid evaporative ionisation mass spectrometry

RATIONALE

There is increasing interest in methods of direct analysis mass spectrometry that bypass complex sample preparation steps.

METHODS

One of the most interesting new ionisation methods is rapid evaporative ionisation mass spectrometry (REIMS) in which samples are vapourised and the combustion products are subsequently ionised and analysed by mass spectrometry (Synapt G2si). The only sample preparation required is the recovery of a cell pellet from a culture that can be analysed immediately.

RESULTS

We demonstrate that REIMS can be used to monitor the expression of heterologous recombinant proteins in Escherichia coli. Clear segregation was achievable between bacteria harvesting plasmids that were strongly expressed and other cultures in which the plasmid did not result in the expression of large amounts of recombinant product.

CONCLUSIONS

REIMS has considerable potential as a near-instantaneous monitoring tool for protein production in a biotechnology environment.

Rapid identification of species, sex and maturity by mass spectrometric analysis of animal faeces

BACKGROUND

We describe a new approach to the recovery of information from faecal samples, based on the analysis of the molecular signature generated by rapid evaporative ionisation mass spectrometry (REIMS).

RESULTS

Faecal pellets from five different rodent species were analysed by REIMS, and complex mass spectra were acquired rapidly (typically a few seconds per sample). The uninterpreted mass spectra (signatures) were then used to seed linear discriminant analysis and classification models based on random forests. It was possible to classify each species of origin with a high rate of accuracy, whether faeces were from animals maintained under standard laboratory conditions or wild-caught. REIMS signatures were stable to prior storage of the faecal material under a range of different conditions and were not altered rapidly or radically by changes in diet. Further, within species, REIMS signatures could be used to discriminate faeces from adult versus juvenile mice, male versus female mice and those from three different laboratory strains.

CONCLUSIONS

REIMS offers a completely novel method for the rapid analysis of faecal samples, extending faecal analysis (previously focused on DNA) to an assessment of phenotype, and has considerable potential as a new tool in the armamentarium of the field biologist.