Fourier Transform Mid-infrared Spectroscopy Research Articles

Spectrochemical analysis of seasonal and sexual variation of antioxidants in Corema album (L.) D. Don leaf extracts

Bioactive phytoconstituents have been increasingly investigated for their potential human health benefits. Corema album (L.) D. Don, an Ericaceae, reportedly has antioxidant, antimicrobial and anticancer properties. Aiming at enhancing its nutraceutical potential, we performed a spectrochemical analysis of hydroethanolic extracts from C. album leaves. We report on changes in the antioxidant activity of the extracts, as well as in the accumulation of key phytoconstituents (namely phenolic compounds), in female and male samples, throughout three harvesting seasons (February, July, and October). For each extract, the antioxidant activity was assessed by different spectrophotometric methods. Simultaneously, attenuated total reflectance Fourier transform mid-infrared spectroscopy (FTIR-ATR), and high-performance liquid chromatography – electrospray ionisation – quadrupole time-of-flight mass spectrometry (HPLC-ESI-Q-TOF-MS), were used to identify and monitor variations in the composition of phenolic compounds in the extracts. The main compounds identified were epicatechin, laricitrin-O-hexoside isomers, and myricetin-O-hexoside isomers. Significant differences were found in the composition and relative abundance of the compounds of interest, according to sex and season. Overall, a trend was observed whereby phenolic content and antioxidant activities were higher in males and increased between the earlier and the latest harvests. Based on these results, we may conclude that late summer or early autumn harvests are preferable when aiming at the highest yearly content of bioactive compounds. Additionally, it should be considered that extracts from male individuals typically display higher antioxidant activities. Ultimately, our understanding of C. album in the context of nutraceutical applications is benefited from the quantitative and qualitative portrait provided here, thus promoting its relevance as a source of bioactive compounds.

A new effective method for identifying boletes species based on FT-MIR and three dimensional correlation spectroscopy projected image processing

This study proposed the necessity of identifying the species for boletes in combination with the medicinal value, nutritional value and the problems existing in the industrial development of boletes. Based on the preprocessing of Fourier transform mid-infrared spectroscopy (FT-MIR) by 1st, 2nd, SNV, 2nd + MSC and 2nd + SG, Multilayer Perceptron (MLP) and CatBoost models were established. To avoid complex preprocessing and feature extraction, we try deep learning modeling methods based on image processing. In this paper, the concept of three-dimensional correlation spectroscopy (3DCOS) projection image was proposed, and 9 datasets of synchronous, asynchronous and integrative images are generated by computer method. In addition, 18 deep learning models were established for 9 image datasets with different sizes. The results showed that the accuracy of the three types of synchronous spectral models reached 100%, while the accuracy of the asynchronous spectral and integrative spectral models of 3DCOS projection images were 96.97% and 97.98% in the case of big datasets, which overcame the defects of poor modeling effect of asynchronous spectral and integrative spectral in previous two-dimensional correlation spectroscopy (2DCOS) studies. In conclusion, the modeling results of 3DCOS projection images are perfect, and we can apply this method to other identification fields in the future.

Machine learning and deep learning based on the small FT-MIR dataset for fine-grained sampling site recognition of boletus tomentipes

This study proposed the necessity of identifying the sampling sites for Boletus tomentipes (B.tomentipes) in combination with cadmium content and environmental factors. Based on fourier transform mid-infrared spectroscopy (FT-MIR) preprocessing by 1st, 2nd, MSC, SNV and SG, five machine learning (ML) algorithms (NB, DT, KNN, RF, SVM) and three Gradient Boosting Machine (GBM) algorithms (XGBoost, LightGBM, CatBoost) were built. To avoid complex preprocessing, we construct BoletusResnet model, propose the concepts of 3DCOS, 3DCOS projected images, index images in addition to 2DCOS, and combine them with deep learning (DL) for classification for the first time. It shows that GBM has higher accuracy than ML and DL has better accuracy than GBM. The four DL models presented in this paper achieve fine-grained sampling sites recognition based on small samples with 100 % accuracy, and a computer application system was developed on them. Therefore, spectral image processing combined with DL is a rapid and efficient classification method which can be widely used in food identification.

Establishment and Validation of Fourier Transform Infrared Spectroscopy (FT–MIR) Methodology for the Detection of Linoleic Acid in Buffalo Milk

Buffalo milk is a dairy product that is considered to have a higher nutritional value compared to cow's milk. Linoleic acid (LA) is an essential fatty acid that is important for human health. This study aimed to investigate and validate the use of Fourier transform mid-infrared spectroscopy (FT-MIR) for the quantification of the linoleic acid in buffalo milk. Three machine learning models were used to predict linoleic acid content, and random forest was employed to select the most important subset of spectra for improved model performance. The validity of the FT-MIR methods was evaluated in accordance with ICH Q2 (R1) guidelines using the accuracy profile method, and the precision, the accuracy, and the limit of quantification were determined. The results showed that Fourier transform infrared spectroscopy is a suitable technique for the analysis of linoleic acid, with a lower limit of quantification of 0.15 mg/mL milk. Our results showed that FT-MIR spectroscopy is a viable method for LA concentration analysis.

Toward the Non-Targeted Detection of Adulterated Virgin Olive Oil with Edible Oils via FTIR Spectroscopy & Chemometrics: Research Methodology Trends, Gaps and Future Perspectives.

Fourier-Transform mid-infrared (FTIR) spectroscopy offers a strong candidate screening tool for rapid, non-destructive and early detection of unauthorized virgin olive oil blends with other edible oils. Potential applications to the official anti-fraud control are supported by dozens of research articles with a "proof-of-concept" study approach through different chemometric workflows for comprehensive spectral analysis. It may also assist non-targeted authenticity testing, an emerging goal for modern food fraud inspection systems. Hence, FTIR-based methods need to be standardized and validated to be accepted by the olive industry and official regulators. Thus far, several literature reviews evaluated the competence of FTIR standalone or compared with other vibrational techniques only in view of the chemometric methodology, regardless of the inherent characteristics of the product spectra or the application scope. Regarding authenticity testing, every step of the methodology workflow, and not only the post-acquisition steps, need thorough validation. In this context, the present review investigates the progress in the research methodology on FTIR-based detection of virgin olive oil adulteration over a period of more than 25 years with the aim to capture the trends, identify gaps or misuses in the existing literature and highlight intriguing topics for future studies. An extensive search in Scopus, Web of Science and Google Scholar, combined with bibliometric analysis, helped to extract qualitative and quantitative information from publication sources. Our findings verified that intercomparison of literature results is often impossible; sampling design, FTIR spectral acquisition and performance evaluation are critical methodological issues that need more specific guidance and criteria for application to product authenticity testing.

Analysis of Complex Carbohydrate Composition in Plant Cell Wall Using Fourier Transform Mid-Infrared Spectroscopy.

Fourier transform mid-infrared spectroscopy (FTIR) is a powerful tool for compositional analysis of plant cell walls. The infrared spectrum generates a fingerprint of a sample with absorption peaks corresponding to the frequency of vibrations between the bonds of the atoms making up the material. Here we describe a method focused on the use of FTIR in combination with principal component analysis (PCA) to characterize the composition of the plant cell wall. The FTIR method described here facilitates high-throughput identification of the major compositional differences across a large set of samples in a low-cost and non-destructive manner.

Predicting soil carbon in granitic soils using Fourier-transform mid-infrared (FT-MIR) spectroscopy: the value of database disaggregation

Soil carbon (C) is an important component in quality assessments and efficient models are required to estimate C rapidly. Accurate C assessments are valuable in monitoring land-use changes. Fourier-transform mid-infrared (FT-MIR) spectroscopy has proved to be a powerful tool for assessing C. The potential of FT-MIR spectroscopy to estimate C was evaluated using the following techniques: (1) three algorithms [partial least squares (PLS)], principal component regression (PCR), and classical least squares (CLS); and (2) disaggregating the dataset into subgroups based on soil depth and texture. The C contents of samples collected in the Johannesburg Granite Dome were determined by dry combustion for comparison. The soils ranged considerably in C (0.123–2.650%), clay (2.80–41.20%), and silt content (8.56–23.75%). Using standard normal variant (SNV), Savitzky-Golay smoothing and PLS, the best-performing model was the horizons subgroup which provided values of root mean square error for prediction (RMSEP) between 0.079 and 0.095%, root mean square error for calibration (RMSEC) = 0.041 − 0.092, r 2 pre = 0.6174–0.8459, r 2 cal = 0.6599–0.9778, residual prediction variation (RPD) = 2.404–2.753, and ratio of performance to interquartile range (RPIQ) = 2.667–3.454. The pronounced accuracy of FT-MIR spectroscopy coupled with PLS, pre-processing techniques, and textural subgroups confirms the potential of infrared spectroscopy as an efficient tool for estimating C content. Future studies should investigate the combined effects of FT-MIR spectroscopy and subgroups grouped according to soil types and land-uses when predicting C.

Simultaneous Concurrent Assessment of Extra Virgin Olive Oil Adulteration via Fourier Transform Mid-Infrared and UV-Visible Spectroscopy Combined with Partial Least Squares Regression

Adulteration of olive oil is a common practice in the industry, where old and commercial oils are mixed with fresh olive oils. Adulteration can negatively affect the quality and authenticity of olive oil, leading to economic fraud and health concerns. Therefore, identifying and quantifying adulteration in olive oil is crucial for ensuring product quality and consumer protection. The objective of this study was to identify and measure the adulteration of fresh olive oils with old oil and commercial oil from the previous harvest year. The study aimed to achieve this goal using spectroscopic techniques in combination with chemometrics. Different spectroscopic techniques, such as FT-MIR and UV-vis spectroscopy, were utilized in this study. Partial least squares (PLS) regression was applied to predict the levels of adulteration in the samples with varying concentrations (0.84 - 52.13 % w/w). Various pre-treatment methods were employed for both FTMIR and UV-Vis spectral data. All the PLS models generated for FT-MIR and UV-Vis spectral data were successful in predicting the levels of adulteration, with high coefficients of determination for both calibration (0.963 - 0.995) and cross validation (0.935 - 0.993) models. The error values for calibration (0.621 % - 2.728 %) and cross validation (0.730 % - 3.314 %) were also low. Based on the results, it was found that the use of second derivative preprocessing for FT-MIR data and SNV preprocessing for UV-Vis data led to the best performance results in quantifying the level of adulteration of olive oil. Spectroscopic techniques in combination with chemometrics can be used to identify and measure the adulteration of olive oil.

Development of fast analytical method for the detection and quantification of Moroccan picholine extra virgin olive oil adulteration using MIR spectroscopy and chemometrics tools

In this study, the adulteration of Moroccan Picholine extra virgin olive oil with Arbequina virgin olive oil was monitored using the Fourier transform mid-infrared (FT-MIR) spectroscopy technique and chemometrics methodologies. To discriminate between olive oil that has been adulterated and unadulterated, principal component analysis (PCA) was utilized for qualitative analysis. We created the best calibration models for quantitative analysis using principal component regression (PCR) and partial least-squares regression (PLS). The first three principal components account for 95% of the overall variability, according to PCA analysis. PCA allows for the classification of the dataset into two groups: adulterated and unadulterated Moroccan Picholine olive oil. The application of the PLS and PCR calibration models for the quantification of adulteration demonstrates high-performance capabilities, as indicated by high values of correlation coefficients R2 greater than 0.999 and 0.995 and lower values of root mean square error (RMSE) less than 0.767 and 2.16 using PLS and PCR, respectively. According to our results, FT-MIR spectroscopy combined with chemometrics approaches can be used successfully as a simple, quick, and non-destructive method for the quantification and discrimination of adulterated olive oil.

Comparison of the genetic characteristics of directly measured and Fourier-transform mid-infrared-predicted bovine milk fatty acids and proteins.

Fourier-transform mid-infrared (FT-MIR) spectroscopy is a high-throughput and inexpensive methodology used to evaluate concentrations of fat and protein in dairy cattle milk samples. The objective of this study was to compare the genetic characteristics of FT-MIR predicted fatty acids and individual milk proteins with those that had been measured directly using gas and liquid chromatography methods. The data used in this study was based on 2,005 milk samples collected from 706 Holstein-Friesian × Jersey animals that were managed in a seasonal, pasture-based dairy system, with milk samples collected across 2 consecutive seasons. Concentrations of fatty acids and protein fractions in milk samples were directly determined by gas chromatography and high-performance liquid chromatography, respectively. Models to predict each directly measured trait based on FT-MIR spectra were developed using partial least squares regression, with spectra from a random selection of half the cows used to train the models, and predictions for the remaining cows used as validation. Variance parameters for each trait and genetic correlations for each pair of measured/predicted traits were estimated from pedigree-based bivariate models using REML procedures. A genome-wide association study was undertaken using imputed whole-genome sequence, and quantitative trait loci (QTL) from directly measured traits were compared with QTL from the corresponding FT-MIR predicted traits. Cross-validation prediction accuracies based on partial least squares for individual and grouped fatty acids ranged from 0.18 to 0.65. Trait prediction accuracies in cross-validation for protein fractions were 0.53, 0.19, and 0.48 for α-casein, β-casein, and κ-casein, 0.31 for α-lactalbumin, 0.68 for β-lactoglobulin, and 0.36 for lactoferrin. Heritability estimates for directly measured traits ranged from 0.07 to 0.55 for fatty acids; and from 0.14 to 0.63 for individual milk proteins. For FT-MIR predicted traits, heritability estimates were mostly higher than for the corresponding measured traits, ranging from 0.14 to 0.46 for fatty acids, and from 0.30 to 0.70 for individual proteins. Genetic correlations between directly measured and FT-MIR predicted protein fractions were consistently above 0.75, with the exceptions of C18:0 and C18:3 cis-3, which had genetic correlations of 0.72 and 0.74, respectively. The GWAS identified trait QTL for fatty acids with likely candidates in the DGAT1, CCDC57, SCD, and GPAT4 genes. Notably, QTL for SCD were largely absent in the FT-MIR predicted traits, and QTL for GPAT4 were absent in directly measured traits. Similarly, for directly measured individual proteins, we identified QTL with likely candidates in the CSN1S1, CSN3, PAEP, and LTF genes, but the QTL for CSN3 and LTF were absent in the FT-MIR predicted traits. Our study indicates that genetic correlations between directly measured and FT-MIR predicted fatty acid and protein fractions are typically high, but that phenotypic variation in these traits may be underpinned by differing genetic architecture.

Annual and seasonal trends in cow's milk quality determined by FT-MIR spectroscopy in Hungary between 2011 and 2020.

We analysed and monitored the major chemical composition of cow's bulk milk by Fourier transform mid-infrared (FT-MIR) spectroscopy over a 10-year period in the whole territory of Hungary. In addition, the two most important key parameters for milk quality assessment, total bacterial count (TBC) and somatic cell count (SCC) were also followed. Production parameters showed significant seasonal and yearly changes. The overall mean fat, protein, lactose and solids-non-fat (SNF) contents of cow's milk were 3.81%, 3.32%, 4.74% and 8.76%, respectively. A circannual variation was observed in the chemical composition and yield of milk components of samples examined between 2011 and 2020. Concerning milk fat, milk protein and SNF, the values were the lowest in summer and the highest in winter. In the case of lactose, the minimum values were measured in autumn and the maximum values in spring. An obvious trend of long-term elevation of lactose and SNF was found in the raw cow milk samples over the observed period. The overall mean TBC and SCC of cow's milk were 52 × 103 CFU ml-1 and 270 × 103 cells/ml, respectively. Although there were differences in the monthly average values, no seasonal cyclicality was observed.

Prediction of Indirect Indicators of a Grass-Based Diet by Milk Fourier Transform Mid-Infrared Spectroscopy to Assess the Feeding Typologies of Dairy Farms.

Simple SummaryThe dairy industry is interested in developing a detection tool for milk produced from pasture to certify the protected designation of origin of certain dairy products. As the cattle’s grazing influences the milk composition, the milk mid-infrared (MIR) spectra will be modified. Therefore, this study aims to develop a predictive model allowing one to use milk MIR spectrometry to classify milk as produced from a cattle diet either based on grass or not. To achieve this objective, the collection of grazing calendars from farms is needed. Unfortunately, this is hardly possible, as this information is rarely recorded. Therefore, the innovation of this research consists of using the usual farming practices developed in the southern part of Belgium combined with a large-scale milk database containing 48 milk composition-related traits. Indeed, in this geographical area, the cows are mainly on pasture between April and September. Therefore, the month of testing can be considered indirect information about their feeding. The developed models were able to distinguish with a precision of around 90% the supposed grass-based diet. Therefore, the probability of belonging to the GRASS class could be used in a tool counting the number of grazing days to confirm the labeling of dairy products.This research aims to develop a predictive model to discriminate milk produced from a cattle diet either based on grass or not using milk mid-infrared spectrometry and the month of testing (an indirect indicator of the feeding ration). The dataset contained 3,377,715 spectra collected between 2011 and 2021 from 2449 farms and 3 grazing traits defined following the month of testing. Records from 30% of the randomly selected farms were kept in the calibration set, and the remaining records were used to validate the models. Around 90% of the records were correctly discriminated. This accuracy is very good, as some records could be erroneously assigned. The probability of belonging to the GRASS modality allowed confirmation of the model’s ability to detect the transition period even if the model was not trained on this data. Indeed, the probability increased from the spring to the summer and then decreased. The discrimination was mainly explained by the changes in the milk fat, mineral, and protein compositions. A hierarchical clustering from the averaged probability per farm and year highlighted 12 groups illustrating different management practices. The probability of belonging to the GRASS class could be used in a tool counting the number of grazing days.

Variable selection by permutation applied in support vector regression models

AbstractSupport vector regression (SVR) can be considered as a black box machine‐learning method. Thus, identifying the cause/effect relationship and the synergism between the most important variables is a difficult task. This study demonstrates the potential of two variable selection methods by permutation—subwindow permutation analysis (SPA) and noise incorporated subwindow permutation analysis (NISPA)—to overcome this limitation. The application of these two variable selections in SVR is poorly explored in literature, mainly for regression problems. The algorithms were applied in FTIR (Fourier transform mid infrared spectroscopy) data of crude oil samples to estimate API gravity, kinematic viscosity at 50°C, saturates, aromatics, resins, and asphaltene content. The results were compared to other variable selection methods. SPA and NISPA provided the most accurate models for kinematic viscosity, saturates, and aromatic content. The root‐mean‐squared percentage error of prediction (RMSPEP) of the SPA and NISPA were, respectively, 14.26% and 14.62% for kinematic viscosity, 4.7 wt% and 4.4 wt% for saturates content, and 3.4 wt% and 3.1 wt% for aromatic content. Regarding API prediction, despite obtaining similar accuracy to the other selection methods, SPA produced a more simplified model, using only 3.5% of the 3351 total variables, with RMSEP equal to 1.0 and R2p to 0.981. Therefore, SPA and NISPA, besides obtaining, in general, faster and more accurate and parsimonious models, revealed the most important variables for building the SVR models.

Antimicrobial evaluation of the Cynara cardunculus extract in Helicobacter pylori cells using mid-infrared spectroscopy and chemometric methods

A preliminary assay, using both therapeutic-based antibiotics (clarithromycin and metronidazole), was conducted to optimize experimental conditions in terms of the sensibility of the Fourier-transform mid-infrared (MIR-FTIR) spectroscopy associated with chemometric methods. Principal component analysis was applied to understand how the Cynara extract concentration acts differentially against H. pylori bacteria. The partial least squares model, characterized by R2 =0.98, and root mean square error cross-validation, 0.011, was developed for the spectral regions (3600-2500 cm-1 and 2000-698 cm-1 ). MIR-FTIR spectroscopy associated with chemometric methods can be considered a suitable approach to discover and analyse the promissory antimicrobial agents based on the biomolecular changes observed according to the Cynara extract. MIR-FTIR spectroscopy and chemometric methods allowed to register the biomolecular changes due to the potential antimicrobial drugs at reduced concentrations comparatively to the conventional assay based on an agar-dilution method, being considered a useful approach to develop a platform to discover new bioactive molecules, allowing to reduce time and costs related to the exploratory step.

Data fusion of multiple‐information strategy based on Fourier transform near infrared spectroscopy and Fourier‐transform mid infrared for geographical traceability of Wolfiporia cocos combined with chemometrics

AbstractOwing to the widespread concern relating to herb safety and quality, there is a momentum to discriminate the geographical traceability of fungus with multiple‐information technologies. In this study, we attempted to evaluate the fusion strategy of multiple‐information for the geographical traceability of this fungus based on Fourier transform near infrared spectroscopy (FT‐NIR) and Fourier‐transform mid infrared spectroscopy (FT‐MIR) with chemometrics. From all results, (1) comparative visualization of t‐distributed stochastic neighbor embedding (t‐SNE) emerged that the superior effect of FT‐NIR spectroscopy was better than FT‐MIR, which were separated according to the samples of different regions; (2) in view of optimized spectrum, the geographical traceability of extreme learning machine (ELM) model was better than the partial least squares discriminant analysis (PLS‐DA) and support vector machine (SVM) models that the accuracy of training set for all models was 100%; (3) the accuracy of train and test for ELM model were 100% with single spectrum, low‐level, and mid‐level fusion of FT‐NIR and FT‐MIR based on principal components (PCs) and competitive adaptive weighting algorithm (CARS), which was suitable for geographical traceability and evaluation of this fungus. (4) The three models based on successive projection algorithm (SPA) were not dissatisfied for the geographical traceability of this fungus. (5) The result of hierarchical cluster analysis (HCA) was consistent with the above results, which could distinguish samples according to different regions. All results showed that models could be developed as superior model on the foundation of single spectrum based on FT‐NIR, low‐level or mid‐level (except SPA) fusion of ELM, which could be employed in geographical traceability of Wolfiporia cocos, effectively.

Production, Composition, and Ecological Function of Sweet-Basil-Seed Mucilage during Hydration

The sweet-basil (Ocimum basilicum L.) fruit/pericarp produces mucilage that engulfs the fruit and seed within minutes of hydration. Seed mucilage is produced by plant species that have adapted to arid, sandy soils. This study was conducted to determine how basil-seed mucilage improves ecological fitness. A second objective was to find ways to remove mucilage, which may interfere with commercial planting. Basil fruit/seeds were examined using light and environmental scanning electron microscopy. Columnar structures of basil mucilage rapidly unfolded from the pericarp upon initial hydration. Dilute hydrochloric acid removed the mucilage, which decreased the water content four-fold but did not inhibit seed germination in a laboratory test. Nondestructive Fourier-transform mid-infrared (FTIR) spectroscopy confirmed that the mucilage was primarily composed of hemicellulose that anchored the basil seed to resist movement. The fully hydrated seeds approached zero water potential, so the mucilage did not interfere with hydration. The seeds that were planted in growing media with mucilage had from 12 to 28% higher seedling emergence and survival percentages after 10 days than seeds without mucilage. Basil-fruit/seed mucilage provides a reservoir of loosely bound water at high water potential for seed germination and early seedling development, thus improving survivability under low moisture.

Quality control of spectroscopic data in non-targeted analysis – Development of a multivariate control chart

In the presented study, an easy to implement workflow based on the evaluation of a quality control sample in non-targeted analysis (outlier detection and time related trend) is proposed for the first time. The novel concept was developed and demonstrated with Fourier transform-midinfrared spectroscopy using a rapeseed oil as quality control sample. Different data evaluation strategies for outlier detection were tested and compared: (i) principal component analysis (PCA), (ii) PCA combined with Hotelling's T-squared distribution and Q-residuals for data assessment as well as (iii) various outlier score-based methods. The build models were challenged by varying measurement and storage conditions to verify the applicability of the three evaluation types (i-iii) to identify these artificially induced variations as outliers. Analogous to a control chart in targeted analysis warning and action limits (numerical decision criteria) were calculated using outlier score-based methods. The best results were achieved by the four outlier score-based methods (pre-period n = 25), where 100 % of the deliberately generated outliers were identified as such. • A multivariate control chart is proposed in non-targeted spectroscopic analysis. • Proposal using FT-MIR spectroscopy and edible seed oil samples. • Comparison of PCA and outlier scores-based approaches for quality assurance. • Study showed best results applying outlier score-based algorithms.

Uses of FT-MIR Spectroscopy and Multivariate Analysis in Quality Control of Coffee, Cocoa, and Commercially Important Spices.

Nowadays, coffee, cocoa, and spices have broad applications in the food and pharmaceutical industries due to their organoleptic and nutraceutical properties, which have turned them into products of great commercial demand. Consequently, these products are susceptible to fraud and adulteration, especially those sold at high prices, such as saffron, vanilla, and turmeric. This situation represents a major problem for industries and consumers’ health. Implementing analytical techniques, i.e., Fourier transform mid-infrared (FT-MIR) spectroscopy coupled with multivariate analysis, can ensure the authenticity and quality of these products since these provide unique information on food matrices. The present review addresses FT-MIR spectroscopy and multivariate analysis application on coffee, cocoa, and spices authentication and quality control, revealing their potential use and elucidating areas of opportunity for future research.

Pregnancy status predicted using milk mid-infrared spectra from dairy cattle

Accurate and timely pregnancy diagnosis is an important component of effective herd management in dairy cattle. Predicting pregnancy from Fourier-transform mid-infrared (FT-MIR) spectroscopy data is of particular interest because the data are often already available from routine milk testing. The purpose of this study was to evaluate how well pregnancy status could be predicted in a large data set of 1,161,436 FT-MIR milk spectra records from 863,982 mixed-breed pasture-based New Zealand dairy cattle managed within seasonal calving systems. Three strategies were assessed for defining the nonpregnant cows when partitioning the records according to pregnancy status in the training population. Two of these used records for cows with a subsequent calving only, whereas the third also included records for cows without a subsequent calving. For each partitioning strategy, partial least squares discriminant analysis models were developed, whereby spectra from all the cows in 80% of herds were used to train the models, and predictions on cows in the remaining herds were used for validation. A separate data set was also used as a secondary validation, whereby pregnancy diagnosis had been assigned according to the presence of pregnancy-associated glycoproteins (PAG) in the milk samples. We examined different ways of accounting for stage of lactation in the prediction models, either by including it as an effect in the prediction model, or by pre-adjusting spectra before fitting the model. For a subset of strategies, we also assessed prediction accuracies from deep learning approaches, utilizing either the raw spectra or images of spectra. Across all strategies, prediction accuracies were highest for models using the unadjusted spectra as model predictors. Strategies for cows with a subsequent calving performed well in herd-independent validation with sensitivities above 0.79, specificities above 0.91 and area under the receiver operating characteristic curve (AUC) values over 0.91. However, for these strategies, the specificity to predict nonpregnant cows in the external PAG data set was poor (0.002-0.04). The best performing models were those that included records for cows without a subsequent calving, and used unadjusted spectra and days in milk as predictors, with consistent results observed across the training, herd-independent validation and PAG data sets. For the partial least squares discriminant analysis model, sensitivity was 0.71, specificity was 0.54 and AUC values were 0.68 in the PAG data set; and for an image-based deep learning model, the sensitivity was 0.74, specificity was 0.52 and the AUC value was 0.69. Our results demonstrate that in pasture-based seasonal calving herds, confounding between pregnancy status and spectral changes associated with stage of lactation can inflate prediction accuracies. When the effect of this confounding was reduced, prediction accuracies were not sufficiently high enough to use as a sole indicator of pregnancy status.

The use of milk Fourier-transform mid-infrared spectroscopy to diagnose pregnancy and determine spectral regional associations with pregnancy in US dairy cows

Accurate early diagnosis of pregnancy is important for timely reproductive management of dairy farms. Fourier-transform mid-infrared (FT-MIR) milk spectral data are routinely used for determining milk components such as fat and protein, whereas milk composition is known to change with advancing stages of pregnancy. The objectives of this study were to compare partial least squares discriminant analysis (PLS-DA) and a Bayesian variable selection regression model (BayesC) for the diagnosis of pregnancy status (PS) from milk FT-MIR data and to infer any spectral regions that might be highly associated with PS at various stages of pregnancy. Conception dates on confirmed pregnant cows were obtained from Holstein cows within 123 herds in Michigan, Ohio, and Indiana during 2018 and 2019. Milk samples from these pregnant cows at 7 different stages of pregnancy were case-control matched to open contemporary herd mates to be within the same stage (±10 d for days in milk) of lactation for the same milk sample test date. The FT-MIR data were obtained for all of these milk samples. Ten-fold herd-independent cross-validation was used to compare PLS-DA versus BayesC using the area under the receiver operating characteristic curve (AUC). The BayesC model demonstrated higher mean AUC compared with PLS-DA at all stages exceeding 60 d of pregnancy. The mean BayesC AUC at stage 1 (1-30 d) was 0.58 ± 0.02, which was superior to a random guess (AUC = 0.50) yet too low to be of practical use. The mean BayesC AUC at stage 7 (≥180 d) was 0.13 greater compared with that of stage 1 (1-30 d) and 0.07 to 0.10 greater compared with stages 2, 3, 4, 5, and 6 (31-180 d in 30-d increments). The mean AUC of stages 2 to 6 were 0.03 to 0.06 greater compared with stage 1 yet again too low to be of practical use. Because of high multicollinearity between many adjacent wavenumbers, a spatially constrained clustering algorithm was used to adaptively partition wavenumbers into 68 windows before inferring associations of spectral regions with pregnancy. Pregnancy status was highly associated with wavenumber windows 1,063 to 1,134 cm-1, 1,201 to 1,257 cm-1, and 1,260 to 1,432 cm-1 based on an estimated BayesC posterior probability of association (PPA) approaching 100% for each of these windows at all pregnancy stages. Other windows ranging from 1,730 to 1,764 cm-1, 1,775 to 1,992 cm-1, 1,995 to 2,163 cm-1, and 2,167 to 2,316 cm-1 had varying medium to high PPA (30% to 100%) across stages. The estimated PPA in wavenumber regions from 1,477 to 1,507 cm-1, and 1,510 to 1,574 cm-1 was weaker in stages 1 and 2 compared with later stages, whereas for the regions 2,984 to 3,077 cm-1 and 3,081 to 3,133 cm-1 the effect of pregnancy was greater for stage 1 compared with other stages. Despite our conclusion that milk FT-MIR data poorly diagnose PS, our study provides new insights into spectral regions that are strongly associated with PS and warrant greater attention.