Recent Developments and Applications of Artificial Intelligence in Solid/Liquid Extraction Studies

Cardoso Rial R.

This article explores the influence and applications of Artificial Intelligence (AI) in analytical chemistry, highlighting its potential to revolutionize the analysis of complex data sets and the development of innovative analytical methods. Additionally, it discusses the role of AI in interpreting large-scale data and optimizing experimental processes. AI has been fundamental in managing heterogeneous data and in advanced analysis of complex spectra in areas such as spectroscopy and chromatography. The article also examines the historical development of AI in chemistry, its current challenges, including the interpretation of AI models and the integration of large volumes of data. Finally, it forecasts future trends and the potential impact of AI on analytical chemistry, emphasizing the need for ethical and secure approaches in the use of AI.

Johnson H., Tipirneni-Sajja A.

Neural networks (NNs) are emerging as a rapid and scalable method for quantifying metabolites directly from nuclear magnetic resonance (NMR) spectra, but the nonlinear nature of NNs precludes understanding of how a model makes predictions. This study implements an explainable artificial intelligence algorithm called integrated gradients (IG) to elucidate which regions of input spectra are the most important for the quantification of specific analytes. The approach is first validated in simulated mixture spectra of eight aqueous metabolites and then investigated in experimentally acquired lipid spectra of a reference standard mixture and a murine hepatic extract. The IG method revealed that, like a human spectroscopist, NNs recognize and quantify analytes based on an analyte’s respective resonance line-shapes, amplitudes, and frequencies. NNs can compensate for peak overlap and prioritize specific resonances most important for concentration determination. Further, we show how modifying a NN training dataset can affect how a model makes decisions, and we provide examples of how this approach can be used to de-bug issues with model performance. Overall, results show that the IG technique facilitates a visual and quantitative understanding of how model inputs relate to model outputs, potentially making NNs a more attractive option for targeted and automated NMR-based metabolomics.

Jia W., Georgouli K., Martinez-Del Rincon J., Koidis A.

Routine, remote, and process analysis for foodstuffs is gaining attention and can provide more confidence for the food supply chain. A new generation of rapid methods is emerging both in the literature and in industry based on spectroscopy coupled with AI-driven modelling methods. Current published studies using these advanced methods are plagued by weaknesses, including sample size, abuse of advanced modelling techniques, and the process of validation for both the acquisition method and modelling. This paper aims to give a comprehensive overview of the analytical challenges faced in research and industrial settings where screening analysis is performed while providing practical solutions in the form of guidelines for a range of scenarios. After extended literature analysis, we conclude that there is no easy way to enhance the accuracy of the methods by using state-of-the-art modelling methods and the key remains that capturing good quality raw data from authentic samples in sufficient volume is very important along with robust validation. A comprehensive methodology involving suitable analytical techniques and interpretive modelling methods needs to be considered under a tailored experimental design whenever conducting rapid food analysis.

Amara-Rekkab A.

The Lanasyn Black is among the most often used in manufacturing and is challenging to take out during wastewater treatment was acquired in the textile industry. Cloud point extraction was used for their elimination in an aqueous solution. The multivariable process parameters have been independently optimized using central composite design and Levenberg-Marquardt algorithm-based artificial neural network for the highest yield of the extraction of Lanasyn Black via cloud point extraction. The CCD forecasts the output maximum of 97.01% under slightly altered process parameters. Still, the ANN-LMA model predicts the extraction yield (99.98%) using an amount of KNO3 =1.04 g, beginning pH of solution=8.99, initial of Lanasyn Black 24.57 ppm, and 0.34 W/W of Triton X-100. With coefficients of determination of 0.997 and 0.9777, the most recent empirical verification of the model mentioned above's predictions using CCD and ANN-LMA is determined to be satisfactory.

Nejabati F., Ebrahimzadeh H.

Although NSAIDs possess notable therapeutic and pharmaceutical qualities, it's essential to acknowledge that excessive doses can result in toxicity within the human body. Moreover, the importance lies in identifying and measuring their trace amounts. Due to their existence within intricate matrices, the creation of novel electrospun nanofibers as sorbents for electrically-assisted solid-phase microextraction (EA-SPME) becomes vital. This innovation caters to the requirement for the effective pre-treatment of NSAID samples, providing a strategic approach to managing the complexities associated with trace quantities found in various matrices. First, polyvinylalcohol/casein/tannic acid/polyaniline/titanium dioxide nanoparticles (PVA/CAS/TA/PANI/TiO2 NPs) electrospun nanofibers were prepared for EA-SPME on pewter rode and then, trace amounts of six NSAIDs (Acetaminophen, Caffeine, Naproxen, Celecoxib, Ibuprofen and mefenamic acid) were adsorbed chemically on these nanofibers. In the next step, the desorption of six NSAIDs was electrochemically done from prepared electrospun nanofibers on a pewter rod which was as working electrode at three electrodes system. Finally, these drugs were quantified from different human plasma samples with HPLC-UV. The synthesis of electrospun nanofibers was confirmed through a series of analytical techniques including field emission-scanning electron microscopy (FE-SEM), energy-dispersive X-ray spectroscopy with elemental mapping analysis (EDX-Mapping), X-ray diffraction (XRD), and Fourier transform-infrared (FT-IR). The optimal percentage of additive compounds to PVA/CAS for electrospinning, as well as the factors influencing adsorption and desorption processes, were determined through both of Design Expert software and MATLAB programming language. Under optimum conditions, the wide linear range was 27–8000 ng mL−1 with R2 ≥ 0.9897, low detection limits were ranged from 8 to 27.3 ng mL−1 based on S/N = 3 and significant enrichment factors were acquired. The intra-day and inter-day RSDs% were obtained within the 4.51% - 5.68% and 4.28%–5.45%, respectively. Finally, The effectiveness of the EA-SPME-HPLC-UV method was assessed for determining NSAIDs in plasma samples, demonstrating good recoveries ranging from 90.2% to 105.2%.

Kumar N., Thorat S.T., Gite A., Patole P.B.

Aquatic animals are prone to extinction due to metal pollution and global climate change. Even though the fish and their products are also unsafe for human consumption, their exports have been rejected due to inorganic and organic contaminants. Nickel (Ni) is a metal that induces toxicity and accumulates in the aquatic ecosystem, posing health threats to humans, animals, and fish. In light of the above, our present investigation aimed to determine the median lethal concentration (96 h-LC50) of nickel alone and concurrent with high temperature (34 °C) (Ni + T) using static non-renewable bioassay toxicity test in Pangasianodon hypophthalmus. The groups treated under exposure to Ni reared under control condition (25–28.9 °C) and Ni + T exposure group reread under 34 °C. In this study, chose the definitive dose of Ni and Ni + T as 17, 18, 19, and 20 mg L−1 after the range finding test. The median lethal concentration of Ni and Ni + T was determined as 19.38 and 18.75 mg L−1, respectively at 96 h. Oxidative stress viz. catalase (CAT), superoxide dismutase (SOD), glutathione-s-transferase (GST), and glutathione peroxidase (GPx) in the liver, gill, and kidney were noticeably elevated with Ni and Ni + T during 96 h. Whereas, the CAT, GPx, and SOD gene expressions were significantly upregulated with Ni and Ni + T. Trilox equivalent anti-oxidant capacity (TEAC), cupric reducing anti-oxidant capacity (CUPRIC), ferric reducing ability of plasma (FRAP), ethoxy resorufin-O-deethylase (EROD), and acetylcholine esterase (AChE) were reduced due to exposure to Ni and Ni + T. Cellular metabolic stress and lipid peroxidation were highly affected due to Ni and Ni + T exposure. The immunological status, as indicated by total protein, albumin, globulin, A:G ratio, and nitro blue tetrazolium chloride (NBT), was severely affected by the toxicity of Ni and Ni + T. Moreover, the gene expression of interleukin (IL), tumor necrosis factor (TNFα), toll-like receptor (TLR), and total immunoglobulin (Ig) was remarkably downregulated following exposure to Ni and Ni + T. HSP 70, iNOS expression, ATPase, Na + /K + -ATPase, cortisol, and blood glucose was significantly elevated with Ni and Ni + T in P. hypophthalmus. The bioaccumulation of Ni in fish tissues and experimental water was determined. The kidney and liver tissues were highly accumulated with Ni, whereas DNA damage was reported in gill tissue. Interestingly, depuration study revealed that at the 28th day, the Ni bioaccumulation was below the maximum residue limit (MRL) level. Therefore, the present study revealed that Ni and Ni + T led to dysfunctional gene and metabolic regulation affecting physiology and genotoxicity. The bioaccumulation and depuration results also indicate higher residual occurrence of Ni in water and aquatic organisms for longer periods.

Wei Q., Lv M., Wang B., Sun J., Wang D.

The present study sought to improve the QuEChERS (quick, easy, cheap, effective, rugged, safe) method to determine the pesticide residues in Lycium barbarum. The QuEChERS conditions were optimized by coupling an artificial neural network (ANN) technique with the genetic algorithm (GA) method, and the response surface methodology (RSM). The results revealed that GA-ANN was more accurate than RSM. Meanwhile, the limit of detection and the limit of quantitation of the QuEChERS method which was optimized by GA-ANN were 0.023–0. 0644 mg·kg−1 and 0.0077–0. 2149 mg·kg−1, respectively. The recoveries of the three levels were 92.36–108. 79% with the Relative Standard Deviation ranging from 0.43% to 6. 69%. The regression coefficient for all calibration curves were greater than 0.9960. Overall, the improved QuEChERS method exhibited high accuracy and good recovery toward determining the pesticide residues in Lycium barbarum.

Duran C., Ozeken S.T., Camoglu A.Y., Ozdes D.

Abstract Natural mulberry leaves and carboxylic acid-modified mulberry (Morus alba L.) leaves were used for the first time to scrutinize the effects of modification on the retention efficiency of an anionic dye (Remazol Brilliant Blue R (RBBR)) from aqueous solutions to suggest an economical and promising adsorbent for the treatment of dye-contaminated water. The characterization of the adsorbents was accomplished through common techniques including SEM, FTIR, and pHpzc determination. Several parameters studied in batch experiments pointed out that the initial pH of 2.0 and the contact time of 240 min were optimum conditions for all the developed RBBR uptake processes. An artificial neural network (ANN) model was applied to formulate a forecast model for the uptake efficiency of RBBR. The experimental data were assessed by different kinetic and isotherm models to explain the mechanism of the developed processes in more detail. Maximum monolayer adsorption capacities of natural mulberry leaves and acetic acid-, citric acid-, and oxalic acid-modified mulberry leaves were determined as 64.5, 95.2, 84.8, and 91.7 mg g−1, respectively, by the Langmuir isotherm model. These results demonstrated that the modification with carboxylic acids significantly increases the anionic dye adsorption capacity of the mulberry leaves.

Geramizadegan A., Niknam L., Pournamdari E.

In this article, a molecularly imprinted polymer-solid phase extraction (SPE)-liquid chromatography method was developed to isolate toxic bentazon in surface water. The molecularly imprinted polymer (MIP) consisted of methacrylic acid as a functional monomer, ethylene glycol dimethacrylate as a crosslinking monomer, and α,α′-azoisobutyronitrile as an initiator for polymer preparation. To evaluate the applicability of the imprinted polymer as a selective sorbent, general parameters, such as pH, amount of loading solvents, washing solution, eluent, and time, were optimized following a step-by-step approach. Under the optimum conditions, the linear range was between 0.05 and 1.0 µg/L. The standard deviation of 2.2% and the method detection limit of 0.05 µg/L were obtained. The recoveries up to approximately 97.0% from spiked surface water samples could be obtained. The observed outcomes confirmed the suitability of the artificial neural network model as a tool for mean square error of bentazon on MIP-SPE (0.018) and non-imprinted polymer-SPE (0.029) selectivity and permeability. The proposed molecularly imprinted polymer-solid phase extraction-liquid chromatography method could be applied to the direct determination of toxic bentazon in water samples.

dos Santos D.P., Sena M.M., Almeida M.R., Mazali I.O., Olivieri A.C., Villa J.E.

Surface-enhanced Raman spectroscopy (SERS) has gained increasing attention because it provides rich chemical information and high sensitivity, being applicable in many scientific fields including medical diagnosis, forensic analysis, food control, and microbiology. Although SERS is often limited by the lack of selectivity in the analysis of samples with complex matrices, the use of multivariate statistics and mathematical tools has been demonstrated to be an efficient strategy to circumvent this issue. Importantly, since the rapid development of artificial intelligence has been promoting the implementation of a wide variety of advanced multivariate methods in SERS, a discussion about the extent of their synergy and possible standardization becomes necessary. This critical review comprises the principles, advantages, and limitations of coupling SERS with chemometrics and machine learning for both qualitative and quantitative analytical applications. Recent advances and trends in combining SERS with uncommonly used but powerful data analysis tools are also discussed. Finally, a section on benchmarking and tips for selecting the suitable chemometric/machine learning method is included. We believe this will help to move SERS from an alternative detection strategy to a general analytical technique for real-life applications.

Islam A., Rais S.

• New MWCNT based magnetic IIP synthesized for SPE coupled FAAS method development. • Serves twin objective of determination and removal in food, water, wastewater. • Analytical method validation; SRM, recovery, accuracy, precision, robustness. • Cd(II) loaded IIP was exploited for removal of toxic anionic dyes. A 3D Fe 3 O 4 @MWCNT-CdIIP was synthesized by the oxidizing surface of multi-walled carbon nanotubes with carboxylic acid end groups and its subsequent termination with an ion imprinted polymer. An artificial neural network manifests better predictability than the central composite design methodology for optimising the adsorption procedure. The adsorption capacity was 109 mg g -1 (2.5 times more than non-imprinted polymer) under optimized conditions (pH; 5.6, time; 15 min, concentration; 800 μg mL −1 temperature; 25°C), which was in accord with Toth isotherm. Fractal-like pseudo-second-order kinetics was found reasonably fast, with 66% adsorption in 5 minutes. Solid phase extraction coupled Flame atomic absorption spectrometry method provides selective recognition towards Cd(II), with limit of detection; 1.13 µg L −1 , limit of quantification; 3.21 µg L −1 after preconcentration (preconcentration factor; 50) and good robustness. The developed method was applied for Cd(II) determination in food (tea, coffee, bread, tobacco, radish, spinach), water and wastewater (> 99% removal as well). Cd(II) loaded IIP was further utilized to remove anionic dyes with > 95% removal.

Hemmati A., Asadollahzadeh M., Derafshi M., Salimi M., Mahabadi Mahabad M., Torkaman R.

This paper aimed to predict the solvent extraction conditions to maximize indium recovery from discarded LCD screens. Two approaches, including the response surface methodology (RSM) and the artificial neural network (ANN), were utilized to predict the efficiency of indium recovery. The main parameters, such as aqueous phase acidity (A), indium concentration (B), ionic liquid concentration (C), and aqueous to organic phase ratio (D), were investigated by using CyphosIL 101 diluted in kerosene as the organic phase. The experimental results were used to train a multilayer perceptron for creating an ANN model with the structure of one, eight, and three for input, hidden, and output layers, respectively. The optimum conditions by the RSM approach to provide the maximum efficiency of indium recovery were. 4 mol/L A, 197.79 ppm of B, 0.009 mol/L of C, and 1.58 mol/L of D. By contrast, the ANN approaches illustrated the optimal A, B, C and D equal to 4.2, 194.32, 0.0085, and 1.52 %, respectively. Two statistical approaches described the satisfactory data, and the superior data was obtained with the ANN approaches. The use of two ionic liquids verified the indium recovery from the discarded LCD screen, and 99.7 % of indium ions were separated and extracted into the stripping solution.

Joshi P.B.

Chemometrics and machine learning are artificial intelligence-based methods stirring a transformative change in chemistry. Organic synthesis, drug discovery and analytical techniques are incorporating machine learning techniques at an accelerated pace. However, machine-assisted chemistry faces challenges while solving critical problems in chemistry due to complex relationships in data sets. Even with increasing publishing volumes on machine learning, its application in areas of chemistry is not a straightforward endeavour. A particular concern in applying machine learning in chemistry is data availability and reproducibility. The present review article discusses the various chemometric methods, expert systems, and machine learning techniques developed for solving problems of organic synthesis and drug discovery with selected examples. Further, a concise discussion on chemometrics and ML deployed in analytical techniques such as, spectroscopy, microscopy and chromatography are presented. Finally, the review reflects the challenges, opportunities and future perspectives on machine learning and automation in chemistry. The review concludes by pondering on some tough questions on applying machine learning and their possibility of navigation in the different terrains of chemistry.

Alardhi S.M., Fiyadh S.S., Salman A.D., Adelikhah M.

In this study, methyl orange (MO) dye removal by adsorption utilizing activated carbon made from date seeds (DPAC) was modeled using an artificial neural network (ANN) technique. Instrumental investigations such as X-ray diffraction (XRD), scanning electron microscopy (SEM), and Brunauer-Emmett-Teller (BET) analysis were used to assess the physicochemical parameters of adsorbent. By changing operational parameters including adsorbent dosage (0.01-0.03 g), solution pH 3-8, initial dye concentration (5-20 mg/L), and contact time (2-60 min), the viability of date seeds for the adsorptive removal of methyl orange dye from aqueous solution was assessed in a batch procedure. The system followed the pseudo 2nd order kinetic model for DPAC adsorbent, according to the kinetic study (R2 = 0.9973). The mean square error (MSE), relative root mean square error (RRMSE), root mean square error (RMSE), mean absolute percentage error (MAPE), relative error (RE), and correlation coefficient (R2) were used to measure the ANN model performance. The maximum RE was 8.24% for the ANN model. Two isotherm models, Langmuir and Freundlich, were studied to fit the equilibrium data. Compared with the Freundlich isotherm model (R2 = 0.72), the Langmuir model functioned better as an adsorption isotherm with R2 of 0.9902. Thus, this study demonstrates that the dye removal process can be predicted using an ANN technique, and it also suggests that adsorption onto DPAC may be employed as a main treatment for dye removal from wastewater.

Ozdes D., Tilki N., Seker S., Duran C.

AbstractIn the present research, brewed tea waste (BTW) was utilized as a green, low-priced, and abundant adsorbent for separation/preconcentration of Cd(II) ions through solid-phase extraction method from water and foods for the first time. BTW was applied as a natural adsorbent, without using any chelating agent to bind Cd(II) ions or any chemical reagent for its modification. A three-layer artificial neural network model using backpropagation algorithm was utilized to explicate a prediction model for the extraction performance of Cd(II) ions by selecting the input parameters as solution pH, quantity of BTW, sample volume, eluent concentration and volume, and equilibrium time for desorption. The preconcentration factor, relative standard deviation, and detection limit were attained as 100, 3.03%, and 0.56 µg L−1, respectively. It was decided that the Langmuir isotherm model is acceptable to characterize the retention of Cd(II) ions on BTW. This result pointed out that the active binding sites on the BTW surface are homogeneously distributed. Adsorption capacity of BTW was achieved as 41.5 mg g−1 which is higher than several expensive and difficult-to-prepare adsorbents. Adsorption kinetics was elucidated by pseudo-second order kinetic model. After confirmed the accuracy of the method with spike/recovery studies, it was employed for Cd(II) determination in water (stream and sea water) and food (eggplant, lettuce, parsley, apple, and apricot) samples with high accuracy. The inferences of the study proved that the BTW offers a magnificent application prospect in the extraction of Cd(II) ions.

Javar K., Foroozandeh A., Souri M., Amoli H.S., Hasanzadeh M.