Recent trends in multi-block data analysis in chemometrics for multi-source data integration

Opportunities offered by latent-based multiblock strategies to integrate biomarkers of chemical exposure and biomarkers of effect in environmental health studies

Modern environmental epidemiology benefits from a new generation of technologies that enable comprehensive profiling of biomarkers, including environmental chemical exposure and omic datasets. The integration and analysis of large and structured datasets to identify functional associations is constrained by computational challenges that cannot be overcome using conventional regression methods. Some extensions of Partial Least Squares (PLS) regression have been developed to efficently integrate multiple datasets, including Multiblock PLS (MB-PLS) and Sequential and Orthogonalized PLS; however, these approaches remain seldom applied in environmental epidemiology. To address that research gap, this study aimed to assess and compare the applicability of PLS-based multiblock models in an observational case study, where biomarkers of exposure to environmental chemicals and endogenous biomarkers of effect were simultaneously integrated to highlight biological links related to a health outcome. The methods were compared with and without sparsity coupling two metrics to support the variable selection: Variable Importance in Projection (VIP) and Selectivity Ratio (SR). The framework was applied to a case-study dataset mimicking the structure of 36 environmental exposure biomarkers (E-block), 61 inflammation biomarkers (M-block), and their relationships with the gestational age at delivery of 161 mother-infant pairs. The results showed an overall consistency in the selected variables across models, although some specific selection patterns were identified. The block-scaled concatenation-based approaches (e.g. MB-PLS) tended to select more variables from the E-block, while these methods were unable to identify certain variables in the M-block. Overall, the number of variables selected using the SR criterion was higher than using the VIP criterion, with lower predictive performances. The multiblock models coupled to VIP, appeared to be the methods of choice for identifying relevant variables with similar statistical performances. Overall, the use of multiblock PLS-based methods appears to be a good strategy to efficiently support the variable selection process in modern environmental epidemiology.

A Novel Data Fusion Strategy of GC-MS and 1H NMR Spectra for the Identification of Different Vintages of Maotai-flavor Baijiu

Counterfeit Baijiu has been emerging because of the price variances of real-aged Chinese Baijiu. Accurate identification of different vintages is of great interest. In this study, the combination of gas chromatography-mass spectrometry (GC-MS) and proton nuclear magnetic resonance (1H NMR) spectroscopy was applied for the comprehensive analysis of chemical constituents for Maotai-flavor Baijiu. Furthermore, a novel data fusion strategy combined with machine learning algorithms has been established. The results showed that the midlevel data fusion combined with the random forest algorithm were the best and successfully applied for classification of different Baijiu vintages. A total of 14 differential compounds (belonging to fatty acid ethyl esters, alcohols, organic acids, and aldehydes) were identified, and used for evaluation of commercial Maotai-flavor Baijiu. Our results indicated that both volatiles and nonvolatiles contributed to the vintage differences. This study demonstrated that GC-MS and 1H NMR spectra combined with a data fusion strategy are practical for the classification of different vintages of Maotai-flavor Baijiu.

Multivariate curve resolution-based data fusion approaches applied in 1H NMR metabolomic analysis of healthy cohorts

BACKGROUND

Metabolomics plays a critical role in deciphering metabolic alterations within individuals, demanding the use of sophisticated analytical methodologies to navigate its intricate complexity. While many studies focus on single biofluid types, simultaneous analysis of multiple matrices enhances understanding of complex biological mechanisms. Consequently, the development of data fusion methods enabling multiblock analysis becomes essential for comprehensive insights into metabolic dynamics.

RESULTS

This study introduces a novel guideline for jointly analyzing diverse metabolomic datasets (serum, urine, metadata) with a focus on metabolic differences between groups within a healthy cohort. The guideline presents two fusion strategies, 'Low-Level data fusion' (LLDF) and 'Mid-Level data fusion' (MLDF), employing a sequential application of Multivariate Curve Resolution with Alternating Least Squares (MCR-ALS), linking the outcomes of successive analyses. MCR-ALS is a versatile method for analyzing mixed data, adaptable at various stages of data processing-encompassing resonance integration, data compression, and exploratory analysis. The LLDF and MLDF strategies were applied to 1H NMR spectral data extracted from urine and serum samples, coupled with biochemical metadata sourced from 145 healthy volunteers.

SIGNIFICANCE

Both methodologies effectively integrated and analysed multiblock datasets, unveiling the inherent data structure and variables associated with discernible factors among healthy cohorts. While both approaches successfully detected sex-related differences, the MLDF strategy uniquely revealed components linked to age. By applying this analysis, we aim to enhance the interpretation of intricate biological mechanisms and uncover variations that may not be easily discernible through individual data analysis.

Improvement of Qualitative Analyses of Aliphatic Alcohols Using Direct Catalytic Fuel Cell and Chemometric Analysis Format

Direct catalytic methanol fuel cells (DCMFCs) have been studied for several years for energy conversion. Less extensive is the investigation of their analytical properties. In this paper, we demonstrate that the behavior of both the discharge and charger curves of DCMFCs depends on the chemical composition of the solution injected in the fuel cell. Their discharge and charge curves, analyzed using a chemometric data fusion method named ComDim, enable the identification of various types of aliphatic alcohols diluted in water. The results also show that the identification of alcohols can be obtained from the first portion of the discharge and charge curves. To this end, the curves have been described by a set of features related to the slope and intercept of the initial portion of the curves. The ComDim analysis of this set of features shows that the identification of alcohols can be obtained in a time that is about thirty times shorter than the time taken to achieve steady-state voltage.

Prediction of cyanidin 3-rutinoside content in Michelia crassipes based on near-infrared spectroscopic techniques

Currently the determination of cyanidin 3-rutinoside content in plant petals usually requires chemical assays or high performance liquid chromatography (HPLC), which are time-consuming and laborious. In this study, we aimed to develop a low-cost, high-throughput method to predict cyanidin 3-rutinoside content, and developed a cyanidin 3-rutinoside prediction model using near-infrared (NIR) spectroscopy combined with partial least squares regression (PLSR). We collected spectral data from Michelia crassipes (Magnoliaceae) tepals and used five different preprocessing methods and four variable selection algorithms to calibrate the PLSR model to determine the best prediction model. The results showed that (1) the PLSR model built by combining the blockScale (BS) preprocessing method and the Significance multivariate correlation (sMC) algorithm performed the best; (2) The model has a reliable prediction ability, with a coefficient of determination (R2) of 0.72, a root mean square error (RMSE) of 1.04%, and a residual prediction deviation (RPD) of 2.06. The model can be effectively used to predict the cyanidin 3-rutinoside content of the perianth slices of M. crassipes, providing an efficient method for the rapid determination of cyanidin 3-rutinoside content.

Characterization of CBD oils, seized on the Belgian market, using infrared spectroscopy: Matrix identification and CBD determination, a proof of concept

The availability of cannabidiol (CBD) oil products has increased in recent years. No analytical controls are mandatory for these products leading to uncertainties about composition and quality. In this paper, a methodology was developed to identify the oil matrix and to estimate the CBD content in such samples, using mid-infrared and near-infrared spectroscopy. Different oils were selected based on the information labeled on products and were bought in food stores in order to create a sample set with a variety of matrices. These oils were spiked with CBD to obtain samples with CBD levels from 0% to 20%. The first part of the study was focused on the qualitative analysis of the oil matrix. A classification model, based on Soft Independent Modeling of Class Analogy, was build using the spiked oils to distinguish between the different oil matrices. For both spectroscopic techniques, the sensitivity, the specificity, the accuracy and the precision were equal to 100%. These models were applied to determine the oil matrix of seized samples. The second part of the study was focused on the quantitative estimation of CBD. After determination of CBD in seized samples using gas chromatography-tandem mass spectrometry, partial least square regression (PLS-R) models were built, one for each matrix in the sample set. Both techniques were able to classify unknown oily samples according to their matrix, and although only few samples were available to evaluate the PLS-R models, the approach clearly showed promising results for the estimation of the CBD content in oil samples.

Bi-directional hyperspectral reconstruction of cherry tomato: diagnosis of internal tissues maturation stage and composition

Introduction

Precision monitoring maturity in climacteric fruits like tomato is crucial for minimising losses within the food supply chain and enhancing pre- and post-harvest production and utilisation.

Objectives

This paper introduces an approach to analyse the precision maturation of tomato using hyperspectral tomography-like.

Methods

A novel bi-directional spectral reconstruction method is presented, leveraging visible to near-infrared (Vis-NIR) information gathered from tomato spectra and their internal tissues (skin, pulp, and seeds). The study, encompassing 118 tomatoes at various maturation stages, employs a multi-block hierarchical principal component analysis combined with partial least squares for bi-directional reconstruction. The approach involves predicting internal tissue spectra by decomposing the overall tomato spectral information, creating a superset with eight latent variables for each tissue. The reverse process also utilises eight latent variables for reconstructing skin, pulp, and seed spectral data.

Results

The reconstruction of the tomato spectra presents a mean absolute percentage error of 30.44 % and 5.37 %, 5.25 % and 6.42 % and Pearson's correlation coefficient of 0.85, 0.98, 0.99 and 0.99 for the skin, pulp and seed, respectively. Quality parameters, including soluble solid content (%), chlorophyll (a.u.), lycopene (a.u.), and puncture force (N), were assessed and modelled with PLS with the original and reconstructed datasets, presenting a range of R2 higher than 0.84 in the reconstructed dataset. An empirical demonstration of the tomato maturation in the internal tissues revealed the dynamic of the chlorophyll and lycopene in the different tissues during the maturation process.

Conclusion

The proposed approach for inner tomato tissue spectral inference is highly reliable, provides early indications and is easy to operate. This study highlights the potential of Vis-NIR devices in precision fruit maturation assessment, surpassing conventional labour-intensive techniques in cost-effectiveness and efficiency. The implications of this advancement extend to various agronomic and food chain applications, promising substantial improvements in monitoring and enhancing fruit quality.

Brown adipose tissue evaluation using water and triglyceride as indices by diffuse reflectance spectroscopy

Brown adipose tissue (BAT) is related to lipid and glucose metabolism, and BAT evaluation is expected to contribute to disease prevention and treatment. We aimed to establish a BAT evaluation method using simple and non-invasive diffuse reflectance spectroscopy (DRS). We acquired diffuse reflectance spectra of BAT using DRS from rats with cold stimulation and analyzed the second-derivative spectra. To predict the amount of triglyceride in BAT from the second-derivative spectra, partial least-squares regression analysis was performed, and we examined whether BAT weight can be predicted from the amount of triglyceride by single regression analysis. By focusing on changes in the amount of triglyceride in BAT with cold stimulation, it was suggested that this amount could be predicted spectroscopically, and the predicted amount of triglyceride could be used to estimate the BAT weight with cold stimulation. If these results can be translated into humans, they may contribute to preventing metabolic disorders.

Identification and analysis of hoisting safety risk factors for IBS construction based on the AcciMap and cases study

Hoisting is an essential aspect of Industrial Building System (IBS) construction. Although research on hoisting safety in China has made strides to focus on "worker," "data," "task," "site," and "accident," there still needs to be more approaches based on multi-dimensional social system thinking. Therefore, the paper aims to fill this gap. We investigated 105 hoisting accidents in China and found that hoisting accidents occurred most frequently in China's southeast coastal region; truck-mounted cranes and tower cranes were the most common types of machinery involved in accidents; hoisting load off, capsizing of crane machinery, and workers falling from height are the three most common accident types; the average impact of a single hoisting accident is approximately RMB 2.43 million direct economic loss, 1.543 deaths and 0.829 injured. This study used three algorithms (Rindge regression, Lasson regression, and partial least squares regression) to explore the impact of deaths and injuries on direct economic losses. By combining Rasmussen's risk framework with the characteristics of hoisting construction, six risk domains and thirty-six safety risk factors were identified. Finally, we used AcciMap technology to construct a qualitative IBS hoisting management model, which exhaustively presents the systematic levels and propagation paths of the influencing factors by the PDCA method. The research helps academics explore strategies to improve the safety of hoisting construction in IBS. Moreover, the study outcomes can inform the policy-making process towards promoting healthy and sustainable construction development.

Recent trends of machine learning applied to multi-source data of medicinal plants

In traditional medicine and ethnomedicine, medicinal plants have long been recognized as the basis for materials in therapeutic applications worldwide. In particular, the remarkable curative effect of traditional Chinese medicine during corona virus disease 2019 (COVID-19) pandemic has attracted extensive attention globally. Medicinal plants have, therefore, become increasingly popular among the public. However, with increasing demand for and profit with medicinal plants, commercial fraudulent events such as adulteration or counterfeits sometimes occur, which poses a serious threat to the clinical outcomes and interests of consumers. With rapid advances in artificial intelligence, machine learning can be used to mine information on various medicinal plants to establish an ideal resource database. We herein present a review that mainly introduces common machine learning algorithms and discusses their application in multi-source data analysis of medicinal plants. The combination of machine learning algorithms and multi-source data analysis facilitates a comprehensive analysis and aids in the effective evaluation of the quality of medicinal plants. The findings of this review provide new possibilities for promoting the development and utilization of medicinal plants.

Exploring new dimensions: Single and multi-block analysis of essential oils using DBDI-MS and FT-IR for enhanced authenticity control

BACKGROUND

Essential oils (EOs) are complex mixtures of volatile hydrocarbons with a wide range of applications in the pharmaceutical, fragrance and food industry. The composition of EOs is highly variable and can affect their quality and pharmaceutical efficacy. Moreover, the high economic value of EOs, such as those obtained from Rosa damascena, make falsification and misclassification a lucrative business. Consequently, adulterations can lead to serious health consequences for consumers. While current quality control methods for EOs involve analysing their chromatographic profile or comparing their Fourier transform infrared (FT-IR) spectra, these methods can be time-consuming or lack sensitivity. To address these issues, we compared state-of-the-art quality control methods, including gas chromatography flame ionization detection (GC-FID) quantification and enantiomeric ratio determination, FT-IR spectrometry with dielectric barrier discharge ionization coupled to triple quadrupole mass spectrometer (DBDI-MS), in a chemometric single- and multi-block approach.

RESULTS

Our results show that the best classification accuracy of 94.7% for R. damascena samples was obtained using GC-FID combined with partial least square discriminant analysis (PLS-DA). Comparatively, the enantiomeric ratios did not improve classification accuracy. In contrast, fragmentation data from DBDI-MS (Q3), which was acquired in a fraction of the analysis time and without extensive sample preparation, achieved a classification accuracy of 84.2%. We also found that combining FT-IR with parent ion DBDI-MS (Q1) data in a multi-block sequentially orthogonalized partial least squares linear discriminant analysis (SO-PLS-LDA) model improved classification accuracy, compared to their respective single-block PLS-DA models.

SIGNIFICANCE

Overall, our study demonstrates that DBDI, as an ambient ionization method, has significant potential for high-throughput screening. When combined with MS, it can produce comparable classification accuracies to conventional methods, while offering the added benefits of speed and convenience. As such, DBDI-MS is a promising tool for EO quality control.

Crude Oil Density Prediction Improved by Multiblock Analysis of Fourier Transform Ion Cyclotron Resonance Mass Spectrometry, Fourier Transform Infrared, and Near-Infrared Spectroscopy Data

Crude oils are among the world's most complex organic mixtures containing a large number of unique components and many analytical techniques lack resolving power to characterize. Fourier transform ion cyclotron resonance mass spectrometry offers a high mass accuracy, making a detailed analysis of crude oils possible. Infrared (IR) spectroscopic methods such as Fourier transform IR spectroscopy (FT-IR) and near-IR, can also be used for crude oil characterization. The three methods measure different properties of the samples, and different data sources can often be combined to improve the prediction accuracy of models. In this study, partial least squares regression (PLSR) models for each of the three methods (single-block PLSR) were compared to multiblock PLSR and sequential and orthogonalized PLSR (SO-PLSR), with the aim of predicting the density of crude oils. Variable importance in projection was used to identify the important variables for each method, as spectroscopic data often contain irrelevant variation. The variables were interpreted to evaluate their underlying chemistry and to check whether consistency could be found between the variables selected from the spectroscopic data for the single-block and multiblock methods. Combining the different blocks of data increased the prediction abilities of the models both before and after variable selection, and SO-PLSR using a reduced data set resulted in the best-performing prediction model.

Network pharmacology and fingerprint for the integrated analysis of mechanism, identification and prediction in Panax notoginseng

INTRODUCTION

Panax notoginseng (Burkill) F. H. Chen ex C. H. Chow, is a well-known herb with multitudinous efficacy. In this study, a series of overall analyses on the action mechanism, component content, origin identification, and content prediction of P. notoginseng are conducted.

OBJECTIVES

The purpose was to analyse the mechanism of pharmacological efficacy, differences between contents and groups of P. notoginseng from different origins, and to identify the origin and predict the content.

MATERIALS AND METHODS

The P. notoginseng samples from four different origins were used for analysis by the database, network pharmacology (Q-marker) and fingerprint analysis [high-performance liquid chromatography (HPLC), attenuated total reflectance Fourier-transform infrared (ATR-FTIR) and near-infrared (NIR)] combined with data fusion strategy (low- and feature-level).

RESULTS

Four saponins were identified as Q-markers, and exerted pharmacological effects on signalling pathways through 24 core targets. The qualitative and quantitative analysis of HPLC showed that there were differences among groups and different origins. Therefore, considering the need to treat diseases, combined with network database and network pharmacology, the suitable producing areas were determined through the mechanism of action and the required saponin content. The low-level data fusion successfully identified the origin and predicted the content of P. notoginseng from different origins. The accuracy rate of each evaluation index of the partial least squares discriminant analysis (PLS-DA) model was 1, and the t-SNE (t-distributed stochastic neighbor embedding) visualisation results were good. The coefficient of determination (R2 ) of the partial least squares regression (PLSR) model ranged from 0.9235-0.9996, and the root mean square error of cross-validation (RMSECV) and root mean square error of prediction (RMSEP) range is 0.301-1.519.

CONCLUSION

This study was designed to provide a sufficient theoretical basis for the quality control of P. notoginseng.

Interfacial Self-Assembly of Surfactant-Free Au Nanoparticles as a Clean Surface-Enhanced Raman Scattering Substrate for Quantitative Detection of As5+ in Combination with Convolutional Neural Networks

Surface-enhanced Raman scattering (SERS) is a highly sensitive tool in the field of environmental testing. However, the detection and accurate quantification of weakly adsorbed molecules (such as heavy metal ions) remain a challenge. Herein, we combine clean SERS substrates capable of capturing heavy metal ions with convolutional neural network (CNN) algorithm models for quantitative detection of heavy metal ions in solution. The SERS substrate consists of surfactant-free Au nanoparticles (NPs) and l-cysteine molecules. As plasmonic nanobuilt blocks, surfactant-free Au NPs without physical or chemical barriers are more accessible to target molecules. The amino and carboxyl groups in the l-cysteine molecule can chelate As5+ ions. The CNN algorithm model is applied to quantify and predict the concentration of As5+ ions in samples. The results demonstrated that this strategy allows for fast and accurate prediction of As5+ ion concentrations, and the determination coefficient between the predicted and actual values is as high as 0.991.

Multi-block DD-SIMCA as a high-level data fusion tool

Multi-block classification method based on the Data Driven Soft Independent Modeling of Class Analogy (DD-SIMCA) is presented. A high-level data fusion approach is used for the joint analysis of data collected with the help of different analytical instruments. The proposed fusion technique is very simple and straightforward. It uses a Cumulative Analytical Signal which is a combination of outcomes of the individual classification models. Any number of blocks can be combined. Although the high-level fusion eventually leads to a rather complex model, the analysis of partial distances makes it possible to establish a meaningful relationship between the classification results and the influence of individual samples and specific tools. Two real world examples are used to demonstrate the applicability of the multi-block algorithm and the consistency of the multi-block method with its predecessor, a conventional DD-SIMCA.

Tracing the origin of Taiping Houkui green tea using 1H NMR and HS-SPME-GC-MS chemical fingerprints, data fusion and chemometrics

The narrow geographical traceability of green tea is both important and challenging. This study aimed to establish multi-technology metabolomic and chemometric approaches to finely discriminate the geographic origins of green teas. Taiping Houkui green tea samples were analyzed by headspace solid-phase microextraction coupled with gas chromatography-mass spectrometry and ¹H NMR of polar (D₂O) and non-polar (CDCl₃). Common dimension, low-level and mid-level data fusion approaches were tested to verify if the combination of several analytical sources can improve the classification ability of samples from different origins. In assessments of tea from six origins, the single instrument data test set results in 40.00% to 80.00% accuracy. Data fusion improved single-instrument performance classification with mid-level data fusion to obtain 93.33% accuracy in the test set. These results provide comprehensive metabolomic insights into the origin of TPHK fingerprinting and open up new metabolomic approaches for quality control in the tea industry.

Sequentially orthogonalized canonical partial least squares for improved multiple responses modeling in multiblock data sets

Multiblock data sets and modeling techniques are widely encountered in the chemometric community. Although the currently available techniques, such as sequential orthogonalized partial least squares (SO-PLS) regression are mainly focused on the prediction of a single response and deal with the multiple response(s) case using PLS2 type approach. Recently, a new approach called canonical PLS (CPLS) was proposed for extracting the subspaces efficiently for multiple response(s) cases, supporting both regression and classification. 'Efficiently' here means more information in fewer latent variables. This work suggests a combination of SO-PLS and CPLS, sequential orthogonalized canonical partial least squares (SO-CPLS), to model multiple response(s) for multiblock data sets. The cases of SO-CPLS for modeling multiple response(s) regression and classification were demonstrated on several data sets. Also, the capability of SO-CPLS to incorporate meta-information related to samples for efficient subspace extraction is demonstrated. Furthermore, a comparison with the commonly used sequential modeling technique, called sequential orthogonalized partial least squares (SO-PLS), is also presented. The SO-CPLS approach can benefit both the multiple response(s) regression and classification modeling and can be of high importance when meta-information such as experimental design or sample classes is available.

Internal reflectance cell fluorescence measurement combined with multi-way analysis to detect fluorescence signatures of undiluted honeys and a fusion of fluorescence and NIR to enhance predictability

Honey is a complex food matrix that contains diverse polyphenolic compounds. Some phenolics exhibit fluorescence signatures which can be used to evaluate honey quality, and authenticity and to determine botanical origin. Mānuka honey contains two unique fluorescence markers: Leptosperin (MM1) and Lepteridine^TM (MM2) that are derived from Leptospermum scoparium nectar. Fluorescence measurement of supersaturated solutions such as undiluted honeys can be challenged by complex inner filter effects. The current study shows the ability of internal reflectance cell fluorescence measurement and multi-way analysis to detect fluorophores in undiluted honeys. This study scanned honeys from different geographic districts generating excitation emission matrices (250-400/300-600 nm), and by near infrared (NIR) hyperspectral camera (547-1701 nm). PARAFAC and tri-PLS could track two fluorescence markers: MM1 (R² = 0.82 & RMSEP = 138.65) and MM2 (R² = 0.82 & RMSEP = 2.75) from undiluted honey fluorescence data with > 80 % accuracy. Classification of mono-floral, multi-floral and non-mānuka honeys achieved 90 % overall accuracy. Fusion of fluorescence data at ƛ_ex 270 & 330 nm and NIR hyperspectral data combined with multi-block PLS analysis enhances predictability of fluorescence markers further. The study revealed the potential of internal reflectance cell fluorescence measurement combined with chemometrics and data fusion for rapid evaluation of honey quality and botanical origin.

Quality assessment of traditional Chinese medicine based on data fusion combined with machine learning: A review

The authenticity and quality of traditional Chinese medicine (TCM) directly impact clinical efficacy and safety. Quality assessment of traditional Chinese medicine (QATCM) is a global concern due to increased demand and shortage of resources. Recently, modern analytical technologies have been extensively investigated and utilized to analyze the chemical composition of TCM. However, a single analytical technique has some limitations, and judging the quality of TCM only from the characteristics of the components is not enough to reflect the overall view of TCM. Thus, the development of multi-source information fusion technology and machine learning (ML) has further improved QATCM. Data information from different analytical instruments can better understand the connection between herbal samples from multiple aspects. This review focuses on the use of data fusion (DF) and ML in QATCM, including chromatography, spectroscopy, and other electronic sensors. The common data structures and DF strategies are introduced, followed by ML methods, including fast-growing deep learning. Finally, DF strategies combined with ML methods are discussed and illustrated for research on applications such as source identification, species identification, and content prediction in TCM. This review demonstrates the validity and accuracy of QATCM-based DF and ML strategies and provides a reference for developing and applying QATCM methods.

Discrimination of Robusta Amazônico coffee farmed by indigenous and non-indigenous people in Amazon: comparing benchtop and portable NIR using ComDim and duplex

Robusta Amazônico is the name given to the Amazonian coffee that has been becoming popular and has recently been registered as a geographical indication in Brazil. It is produced by indigenous and non-indigenous coffee producers in regions that are geographically very close to one another. There is a need to authenticate whether coffee is truly produced by indigenous people and near-infrared (NIR) spectroscopy is an excellent technique for this. To meet the substantial trend towards NIR spectroscopy miniaturization, this work compared benchtop and portable NIR instruments to discriminate Robusta Amazônico samples using partial least squares discriminant analysis (PLS-DA). To ensure the results to be fairly comparable and, at the same time, to guarantee representative selection of both training and test set for the discriminant analysis, a sample selection strategy based on coupling ComDim multi-block analysis and the duplex algorithm was applied. Different pre-processing techniques were tested to create multiple matrices to be used in ComDim, as well as to build the discriminant models. The best PLS-DA model for benchtop NIR provided an accuracy of 96% for the test samples, while for the portable NIR the correct classification rate was 92%. It was demonstrated that portable NIR provides similar results to benchtop NIR for coffee origin classification by performing an unbiased sample selection strategy.

Spectroscopic technologies and data fusion: Applications for the dairy industry

Increasing consumer awareness, scale of manufacture, and demand to ensure safety, quality and sustainability have accelerated the need for rapid, reliable, and accurate analytical techniques for food products. Spectroscopy, coupled with Artificial Intelligence-enabled sensors and chemometric techniques, has led to the fusion of data sources for dairy analytical applications. This article provides an overview of the current spectroscopic technologies used in the dairy industry, with an introduction to data fusion and the associated methodologies used in spectroscopy-based data fusion. The relevance of data fusion in the dairy industry is considered, focusing on its potential to improve predictions for processing traits by chemometric techniques, such as principal component analysis (PCA), partial least squares regression (PLS), and other machine learning algorithms.

Raman spectroscopy for on-line monitoring of botanical extraction process using convolutional neural network with background subtraction

Aqueous extraction is the most common and cost-effective means of obtaining active ingredients from medicinal plants. However, botanical extracts generally contain high pigment content and complex chemical composition posing a challenge for the process analysis of aqueous extraction. Here, we employed Raman spectroscopy to monitor the physical and chemical properties during the extraction process using convolution neural network (CNN) with background subtraction. Real-time spectra were first preprocessed to eliminate fluorescence background interference. Next, two types of CNN models, the one-dimensional CNN (1D-CNN) based on one preprocessing method, and two-dimensional CNN (2D-CNN) based on a concatenation of differentially pretreated data blocks, were used to receive the preprocessed spectra data. Two case studies were conducted for 1D- and 2D-CNN: the extraction of Aurantii fructus, and the co-extraction of Radix Salvia miltiorrhiza and Rhizoma Ligusticum chuanxiong. Furthermore, partial least squares (PLS) models and sequential preprocessing through orthogonalization (SPORT) models were developed and compared with 1D-CNN and 2D-CNN, respectively. CNN-based methods were superior to other models in terms of prediction accuracy, with 2D-CNN yielding the best results. These results indicated that preprocessing and CNN methods were highly complementary, and could effectively remove the fluorescence effect and artefacts introduced by pretreatment in spectral profile. To the best of our knowledge, this is the first study to demonstrate that a combination of preprocessing and CNN leads to improved prediction performance of analytes when using Raman spectroscopy for online monitoring high-pigmented samples.

Towards Automated Classification of Zooplankton Using Combination of Laser Spectral Techniques and Advanced Chemometrics

Zooplankton identification has been the subject of many studies. They are mainly based on the analysis of photographs (computer vision). However, spectroscopic techniques can be a good alternative due to the valuable additional information that they provide. We tested the performance of several chemometric techniques (principal component analysis (PCA), non-negative matrix factorisation (NMF), and common dimensions and specific weights analysis (CCSWA of ComDim)) for the unsupervised classification of zooplankton species based on their spectra. The spectra were obtained using laser-induced breakdown spectroscopy (LIBS) and Raman spectroscopy. It was convenient to assess the discriminative power in terms of silhouette metrics (Sil). The LIBS data were substantially more useful for the task than the Raman spectra, although the best results were achieved for the combined LIBS + Raman dataset (best Sil = 0.67). Although NMF (Sil = 0.63) and ComDim (Sil = 0.39) gave interesting information in the loadings, PCA was generally enough for the discrimination based on the score graphs. The distinguishing between Calanoida and Euphausiacea crustaceans and Limacina helicina sea snails has proved possible, probably because of their different mineral compositions. Conversely, arrow worms (Parasagitta elegans) usually fell into the same class with Calanoida despite the differences in their Raman spectra.

Daphnia as a Sentinel Species for Environmental Health Protection: A Perspective on Biomonitoring and Bioremediation of Chemical Pollution

Despite available technology and the knowledge that chemical pollution damages human and ecosystem health, chemical pollution remains rampant, ineffectively monitored, rarely prevented, and only occasionally mitigated. We present a framework that helps address current major challenges in the monitoring and assessment of chemical pollution by broadening the use of the sentinel species Daphnia as a diagnostic agent of water pollution. And where prevention has failed, we propose the application of Daphnia as a bioremediation agent to help reduce hazards from chemical mixtures in the environment. By applying "omics" technologies to Daphnia exposed to real-world ambient chemical mixtures, we show improvements at detecting bioactive components of chemical mixtures, determining the potential effects of untested chemicals within mixtures, and identifying targets of toxicity. We also show that using Daphnia strains that naturally adapted to chemical pollution as removal agents of ambient chemical mixtures can sustainably improve environmental health protection. Expanding the use of Daphnia beyond its current applications in regulatory toxicology has the potential to improve both the assessment and the remediation of environmental pollution.

Correlation between the Quality of Talent Training and Regional Economic Development Based on Multivariate Statistical Analysis Model

Entering the era of knowledge economy, the economic value of talent education is more and more emphasized, and it contributes more and more to the local economy and injects new vitality into local economic development. However, there are still some difficulties in the synergistic development of talent education and local economy, such as the low degree of integration of "industry, profession, and employment" and the lack of synergy between schools and enterprises, which affects the high-quality development of talent education and restricts the long-term development of regional economy. This paper incorporates machine learning algorithms to construct a multivariate statistics analysis model based on the correlation analysis model between talent training quality and regional economic development. Based on the multi-variate statistical analysis theory and method, the qualitative analysis and quantitative analysis are closely combined to scientifically pick up the main indicators affecting the comprehensive quality of talent cultivation and overcome the drawbacks of artificial subjective assignment of values. Through the judicious selection of evaluation indexes, a scientific and fair evaluation model is established, and the targets of talent cultivation are combined with regional economic development, in a comprehensive analysis, which provides a new means for the development of the regional economy.

Challenges and Opportunities of Implementing Data Fusion in Process Analytical Technology—A Review

The release of the FDA’s guidance on Process Analytical Technology has motivated and supported the pharmaceutical industry to deliver consistent quality medicine by acquiring a deeper understanding of the product performance and process interplay. The technical opportunities to reach this high-level control have considerably evolved since 2004 due to the development of advanced analytical sensors and chemometric tools. However, their transfer to the highly regulated pharmaceutical sector has been limited. To this respect, data fusion strategies have been extensively applied in different sectors, such as food or chemical, to provide a more robust performance of the analytical platforms. This survey evaluates the challenges and opportunities of implementing data fusion within the PAT concept by identifying transfer opportunities from other sectors. Special attention is given to the data types available from pharmaceutical manufacturing and their compatibility with data fusion strategies. Furthermore, the integration into Pharma 4.0 is discussed.

Metabolomics with multi-block modelling of mass spectrometry and nuclear magnetic resonance in order to discriminate Haplosclerida marine sponges

A comprehensive metabolomic strategy, integrating ¹H NMR and MS-based multi-block modelling in conjunction with multi-informational molecular networking, has been developed to discriminate sponges of the order Haplosclerida, well known for being taxonomically contentious. An in-house collection of 33 marine sponge samples belonging to three families (Callyspongiidae, Chalinidae, Petrosiidae) and four different genera (Callyspongia, Haliclona, Petrosia, Xestospongia) was investigated using LC-MS/MS, molecular networking, and the annotations processes combined with NMR data and multivariate statistical modelling. The combination of MS and NMR data into supervised multivariate models led to the discrimination of, out of the four genera, three groups based on the presence of metabolites, not necessarily previously described in the Haplosclerida order. Although these metabolomic methods have already been applied separately, it is the first time that a multi-block untargeted approach using MS and NMR has been combined with molecular networking and statistically analyzed, pointing out the pros and cons of this strategy.

High-throughput plant phenotyping: a role for metabolomics?

High-throughput (HTP) plant phenotyping approaches are developing rapidly and are already helping to bridge the genotype-phenotype gap. However, technologies should be developed beyond current physico-spectral evaluations to extend our analytical capacities to the subcellular level. Metabolites define and determine many key physiological and agronomic features in plants and an ability to integrate a metabolomics approach within current HTP phenotyping platforms has huge potential for added value. While key challenges remain on several fronts, novel technological innovations are upcoming yet under-exploited in a phenotyping context. In this review, we present an overview of the state of the art and how current limitations might be overcome to enable full integration of metabolomics approaches into a generic phenotyping pipeline in the near future.

Spectra Fusion of Mid-Infrared (MIR) and X-ray Fluorescence (XRF) Spectroscopy for Estimation of Selected Soil Fertility Attributes

Previous works indicate that data fusion, compared to single data modelling can improve the assessment of soil attributes using spectroscopy. In this work, two different kinds of proximal soil sensing techniques i.e., mid-infrared (MIR) and X-ray fluorescence (XRF) spectroscopy were evaluated, for assessment of seven fertility attributes. These soil attributes include pH, organic carbon (OC), phosphorous (P), potassium (K), magnesium (Mg), calcium (Ca) and moisture contents (MC). Three kinds of spectra fusion (SF) (spectra concatenation) approaches of MIR and XRF spectra were compared, namely, spectra fusion-Partial least square (SF-PLS), spectra fusion-Sequential Orthogonalized Partial least square (SF-SOPLS) and spectra fusion-Variable Importance Projection-Sequential Orthogonalized Partial least square (SF-VIP-SOPLS). Furthermore, the performance of SF models was compared with the developed single sensor model (based on individual spectra of MIR and XRF). Compared with the results obtained from single sensor model, SF models showed improvement in the prediction performance for all studied attributes, except for OC, Mg, and K prediction. More specifically, the highest improvement was observed with SF-SOPLS model for pH [R2p = 0.90, root mean square error prediction (RMSEP) = 0.15, residual prediction deviation (RPD) = 3.30, and ratio of performance inter-quantile (RPIQ) = 3.59], successively followed by P (R2p = 0.91, RMSEP = 4.45 mg/100 g, RPD = 3.53, and RPIQ = 4.90), Ca (R2p = 0.92, RMSEP = 177.11 mg/100 g, RPD = 3.66, and RPIQ = 3.22) and MC (R2p = 0.80, RMSEP = 1.91%, RPD = 2.31, RPIQ = 2.62). Overall the study concluded that SF approach with SOPLS attained better performance over the traditional model developed with the single sensor spectra, hence, SF is recommended as the best SF method for improving the prediction accuracy of studied soil attributes. Moreover, the multi-sensor spectra fusion approach is not limited for only MIR and XRF data but in general can be extended for complementary information fusion in order to improve the model performance in precision agriculture (PA) applications.

Prediction of clinical trial enrollment rates

Clinical trials represent a critical milestone of translational and clinical sciences. However, poor recruitment to clinical trials has been a long standing problem affecting institutions all over the world. One way to reduce the cost incurred by insufficient enrollment is to minimize initiating trials that are most likely to fall short of their enrollment goal. Hence, the ability to predict which proposed trials will meet enrollment goals prior to the start of the trial is highly beneficial. In the current study, we leveraged a data set extracted from ClinicalTrials.gov that consists of 46,724 U.S. based clinical trials from 1990 to 2020. We constructed 4,636 candidate predictors based on data collected by ClinicalTrials.gov and external sources for enrollment rate prediction using various state-of-the-art machine learning methods. Taking advantage of a nested time series cross-validation design, our models resulted in good predictive performance that is generalizable to future data and stable over time. Moreover, information content analysis revealed the study design related features to be the most informative feature type regarding enrollment. Compared to the performance of models built with all features, the performance of models built with study design related features is only marginally worse (AUC = 0.78 ± 0.03 vs. AUC = 0.76 ± 0.02). The results presented can form the basis for data-driven decision support systems to assess whether proposed clinical trials would likely meet their enrollment goal.

A Multiblock Approach to Fuse Process and Near-Infrared Sensors for On-Line Prediction of Polymer Properties

Petrochemical companies aim at assessing final product quality in real time, in order to rapidly deal with possible plant faults and to reduce chemical wastes and staff effort resulting from the many laboratory analyses performed every day. In order to answer these needs, the main purpose of the current work is to explore the feasibility of multiblock regression methods to build real-time monitoring models for the prediction of two quality properties of Acrylonitrile-Butadiene-Styrene (ABS) by fusing near-infrared (NIR) and process sensors data. Data come from a production plant, which operates continuously, and where four NIR probes are installed on-line, in addition to standard process sensors. Multiblock-PLS (MB-PLS) and Response-Oriented Sequential Alternation (ROSA) methods were here utilized to assess which of such sensors and plant areas were the most relevant for the quality parameters prediction. Several prediction models were constructed exploiting measurements provided by sensors active at different ABS production process stages. Both methods provided good prediction performances and permitted identification of the most relevant data blocks for the quality parameters’ prediction. Moreover, models built without considering recordings from the final stage of the process yielded prediction errors comparable to those involving all available data blocks. Thus, in principle, allowing final ABS quality to be estimated in real-time before the end of the process itself.

A novel approach for discovering correlations between elemental and molecular composition using laser-based spectroscopic techniques

LIBS and Raman spectra of marine zooplankton processed together to study trends in anomalous lithium enrichment.

Optical deciphering of multinary chiral compound mixtures through organic reaction based chemometric chirality sensing

The advances of high-throughput experimentation technology and chemometrics have revolutionized the pace of scientific progress and enabled previously inconceivable discoveries, in particular when used in tandem. Here we show that the combination of chirality sensing based on small-molecule optical probes that bind to amines and amino alcohols via dynamic covalent or click chemistries and powerful chemometric tools that achieve orthogonal data fusion and spectral deconvolution yields a streamlined multi-modal sensing protocol that allows analysis of the absolute configuration, enantiomeric composition and concentration of structurally analogous—and therefore particularly challenging—chiral target compounds without laborious and time-consuming physical separation. The practicality, high accuracy, and speed of this approach are demonstrated with complicated quaternary and octonary mixtures of varying chemical and chiral compositions. The advantages over chiral chromatography and other classical methods include operational simplicity, increased speed, reduced waste production, low cost, and compatibility with multiwell plate technology if high-throughput analysis of hundreds of samples is desired.

The stereoselective analysis of mixtures of chiral compounds typically requires time-consuming chromatography. Here, the authors combine reaction based chiroptical sensing and chemometric tools to directly determine the absolute configuration, enantiomeric composition and concentration of convoluted samples without physical separation.

Deep multiblock predictive modelling using parallel input convolutional neural networks

In the domain of chemometrics, multiblock data analysis is widely performed for exploring or fusing data from multiple sources. Commonly used methods for multiblock predictive analysis are the extensions of latent space modelling approaches. However, recently, deep learning (DL) approaches such as convolutional neural networks (CNNs) have outperformed the single block traditional latent space modelling chemometric approaches such as partial least-square (PLS) regression. The CNNs based DL modelling can also be performed to simultaneously deal with the multiblock data but was never explored until this study. Hence, this study for the first time presents the concept of parallel input CNNs based DL modelling for multiblock predictive chemometric analysis. The parallel input CNNs based DL modelling utilizes individual convolutional layers for each data block to extract key features that are later combined and passed to a regression module composed of fully connected layers. The method was tested on a real visible and near-infrared (Vis-NIR) large data set related to dry matter prediction in mango fruit. To have the multiblock data, the visible (Vis) and near-infrared (NIR) parts were treated as two separate blocks. The performance of the parallel input CNN was compared with the traditional single block CNNs based DL modelling, as well as with a commonly used multiblock chemometric approach called sequentially orthogonalized partial least-square (SO-PLS) regression. The results showed that the proposed parallel input CNNs based deep multiblock analysis outperformed the single block CNNs based DL modelling and the SO-PLS regression analysis. The root means squared errors of prediction obtained with deep multiblock analysis was 0.818%, relatively lower by 4 and 20% than single block CNNs and SO-PLS regression, respectively. Furthermore, the deep multiblock approach attained ∼3% lower RMSE compared to the best known on the mango data set used for this study. The deep multiblock analysis approach based on parallel input CNNs could be considered as a useful tool for fusing data from multiple sources.

Approaches to Integrating Metabolomics and Multi-Omics Data: A Primer

Metabolomics deals with multiple and complex chemical reactions within living organisms and how these are influenced by external or internal perturbations. It lies at the heart of omics profiling technologies not only as the underlying biochemical layer that reflects information expressed by the genome, the transcriptome and the proteome, but also as the closest layer to the phenome. The combination of metabolomics data with the information available from genomics, transcriptomics, and proteomics offers unprecedented possibilities to enhance current understanding of biological functions, elucidate their underlying mechanisms and uncover hidden associations between omics variables. As a result, a vast array of computational tools have been developed to assist with integrative analysis of metabolomics data with different omics. Here, we review and propose five criteria-hypothesis, data types, strategies, study design and study focus- to classify statistical multi-omics data integration approaches into state-of-the-art classes under which all existing statistical methods fall. The purpose of this review is to look at various aspects that lead the choice of the statistical integrative analysis pipeline in terms of the different classes. We will draw particular attention to metabolomics and genomics data to assist those new to this field in the choice of the integrative analysis pipeline.

Prediction and Utilization of Malondialdehyde in Exotic Pine Under Drought Stress Using Near-Infrared Spectroscopy

Drought is a major abiotic stress that adversely affects the growth and productivity of plants. Malondialdehyde (MDA), a substance produced by membrane lipids in response to reactive oxygen species (ROS), can be used as a drought indicator to evaluate the degree of plasma membrane damage and the ability of plants to drought stress tolerance. Still measuring MDA is usually a labor- and time-consuming task. In this study, near-infrared (NIR) spectroscopy combined with partial least squares (PLS) was used to obtain rapid and high-throughput measurements of MDA, and the application of this technique to plant drought stress experiments was also investigated. Two exotic conifer tree species, namely, slash pine (Pinus elliottii) and loblolly pine (Pinus taeda), were used as plant material exposed to drought stress; different types of spectral preprocessing methods and important feature-selection algorithms were applied to the PLS model to calibrate it and obtain the best MDA-predicting model. The results show that the best PLS model is established via the combined treatment of detrended variable-significant multivariate correlation algorithm (DET-sMC), where latent variables (LVs) were 6. This model has a respectable predictive capability, with a correlation coefficient (R ²) of 0.66, a root mean square error (RMSE) of 2.28%, and a residual prediction deviation (RPD) of 1.51, and it was successfully implemented in drought stress experiments as a reliable and non-destructive method to detect the MDA content in real time.