Search

[Display omitted] • NIR spectroscopy enabled rapid prediction of characteristic components in continuous counter-current extraction of Angelica dahurica formula granules. • PLSR and BP-ANN prediction models were compared to demonstrate the feasibility of AI for rapid quality monitoring. • Four intelligent optimization algorithms were used to optimize the parameters of the BP-ANN models. • The analytical capability of BP-ANN models were validated by an independent test set. The establishment of near infrared (NIR) spectroscopy model mostly relies on chemometrics, and spectral analysis combined with artificial intelligence (AI) provides a new way of thinking for pharmaceutical quality inspection, new algorithms such as back propagation artificial neural networks (BP-ANN) and swarm intelligence optimization algorithms such as sparrow search algorithm (SSA) provide core technical support. In order to explore the application of AI in the pharmaceutical field, in this study, Angelica dahurica formula granules with a relatively complex system were selected as the research object. Quantitative analysis models were established by using partial least squares regression (PLSR) with a micro-NIR spectrometer, and BP-ANN modeling results were compared. For the best PLSR models of six characteristic components in the continuous counter-current extract of Angelica dahurica , R2 v of imperatorin was lower than 0.90, and the RPD values of imperatorin, phellopterin, and isoimperatorin were even lower than 1. When the prediction model established by SSA-BP-ANN was used for quantitative analysis, R2 v of six components were all higher than 0.92, and the RPD values all higher than 1.5, which proved that the BP-ANN method was better than PLSR. This study confirmed that in the continuous counter-current extraction progress of Angelica dahurica formula granules, the use of micro-NIR spectrometer combined with AI could realize the rapid prediction of the contents of six characteristic components. The comparison results provided a scientific reference for the process analysis and on-line monitoring in the production process of traditional Chinese medicine by micro-NIR spectrometer combined with AI. [ABSTRACT FROM AUTHOR]

[Display omitted] • First study of refrigerant leakage in plasma protein alcohol deposition using NIRS. • A new impurity identification method "background silence" was proposed. • Provided a new perspective on the study of low-level contaminants. Low-temperature ethanol method is the main process for the preparation of blood products. Ethanol is cooled using plate heat exchangers with refrigerant fluid, and the ethylene glycol in the refrigerant is a toxic reagent, so the problem of refrigerant fluid leakage has become a concern for blood product companies. The lack of detection methods of refrigerant impurities in ethanol at this process stage can lead to serious safety issues and losses in the event of a refrigerant leak. In this study, a pattern recognition method based on near-infrared spectroscopy (NIRS), the "background silence" method, was developed for the detection of refrigerant impurities in ethanol. The method considered normal impurity-free ethanol solution samples as the background and impurity samples as the interference, made the background "silent" through linear regression, highlighted the changes brought by the interference factor, and then established a "background silence" pattern recognition system by calculating the RSD value at the characteristic data points, which realised the detection of trace refrigerant impurities in ethanol solution. The specificity and sensitivity of the method reached 100 %, and the detection limit can reach 0.25 ‰. The NIRS "background silence" method enables the detection of trace refrigerant impurities in ethanol solutions with reduced computational complexity compared with the widely used PLS-DA discrimination method. This study provides new methodological guidance for the detection of impurities in low content components, and lays the foundation for the application of the "background silence" method in practical production. [ABSTRACT FROM AUTHOR]

[Display omitted] • The first time using CBAM-CNN to predict particle size distribution during fluidized bed granulation. • The CBAM-CNN model was optimized by introducing Bayesian optimization and C-Mixup algorithms. • The performance of CBAM-CNN was compared to other classic models. • The modeling convenience of CBAM-CNN was evaluated. Monitoring the particle size distribution (PSD) is crucial for controlling product quality during fluidized bed granulation. This paper proposed a rapid analytical method that quantifies the D10, D50, and D90 values using a Convolutional Block Attention Module-Convolutional Neural Network (CBAM-CNN) framework tailored for deep learning with near-infrared (NIR) spectroscopy. This innovative framework, which fuses CBAM with CNN, excels at extracting intricate features while prioritizing crucial ones, thereby facilitating the creation of a robust multi-output regression model. To expand the training dataset, we incorporated the C-Mixup algorithm, ensuring that the deep learning model was trained comprehensively. Additionally, the Bayesian optimization algorithm was introduced to optimize the hyperparameters, improving the prediction performance of the deep learning model. Compared with the commonly used Partial Least Squares (PLS), Support Vector Machine (SVM), and Artificial Neural Network (ANN) models, the CBAM-CNN model yielded higher prediction accuracy. Furthermore, the CBAM-CNN model avoided spectral preprocessing, preserved the spectral information to the maximum extent, and returned multiple predicted values at one time without degrading the prediction accuracy. Therefore, the CBAM-CNN model showed better prediction performance and modeling convenience for analyzing PSD values in fluidized bed granulation. [ABSTRACT FROM AUTHOR]

[Display omitted] • Real-time in-line prediction of drug loading of diclofenac sodium during the coating process of sugar spheres was realized by NIRS. • Real-time in-line prediction of release rate during the coating process of diclofenac sodium spheres was realized by NIRS. • The real-time in-line prediction research on drug loading and release rate were carried out with the CQAs of coating process in the fluidized bed. • The analytical ability of the real-time in-line NIRS models of drug loading and release rate was verified by independent external validation set. The preparation of diclofenac sodium spheres by fluidized bed is a common production mode for the pharmaceutical preparations at present, but the critical material attributes in the production process is mostly analyzed off-line, which is time-consuming and laborious, and the analysis results lag behind. In this paper, the real-time in-line prediction of drug loading of diclofenac sodium and the release rate during the coating process was realized by using near infrared spectroscopy. For the best near infrared spectroscopy (NIRS) model of drug loading, R2 cv , R2 p , RMSECV, RMSEP were 0.9874, 0.9973, 0.002549 mg/g, 0.001515 mg/g respectively. For the best NIRS model of three release time points, the R2 cv , R2 p , RMSECV and RMSEP were 0.9755, 0.9823, 3.233%, 4.500%; 0.9358, 0.9965, 2.598%, 0.7939% and 0.9867, 0.9927, 0.4085%, 0.4726% respectively. And the analytical ability of these model was verified. The organic combination of these two parts of work constituted an important basis for ensuring the safety and effectiveness of diclofenac sodium spheres from the perspective of production process. [ABSTRACT FROM AUTHOR]

• A new perspective in understanding the processing of TCM by Aquaphotomics. • The component of SSZ promoted the blood system to be in a relatively active state. • The component of TSZ formed a stable hydrogen-bonded network structure in TSZ. • A loose and porous structure was formed after processing through SEM observation. • The content of different chemical compositions changed after processing. The processing of traditional Chinese medicine (TCM) is a critical pharmaceutical technology that enhances the efficacy and safety of TCM. However, the underlying scientific principles of processing have remained largely unknown, hindering the development of TCM. This study examined Crataegi Fructus , which has four processed products (raw, fried, charred, and carbonized), as an example to investigate the processing mechanisms that cause differences in their clinical use. The differences between the four processed products were analyzed in terms of physical properties and chemical compositions using a metallographic microscope, scanning electron microscope, and high-performance liquid chromatography. The study also proposed a new method for investigating processing mechanisms using near-infrared spectroscopy with Aquaphotomics. The results showed that there were significant differences after processing, with a loose and porous structure formed, and the 5-hydroxymethylfurfural content increased. Additionally, raw Crataegi Fructus was found to promote an active hydrogen-bonded network, which may account for the circulation-promoting effect, while carbonized Crataegi Fructus formed a stable hydrogen-bonded network structure, thus exerting its hemostatic effect. The scientific principle of "Carbonized-processing promoting hemostatic effect" in the processing of TCM was first revealed by Aquaphotomics in this study, providing a valuable reference for future studies on the processing mechanisms of TCM. [Display omitted] [ABSTRACT FROM AUTHOR]

Protein is the basis of life substance and the main undertaker of life activities. The study of protein structure and the interaction between protein and other molecules is the basis of studying the origin of life and new drugs. Near-infrared spectroscopy (NIRS) has been widely used in various fields due to its advantages of rapid, accurate, non-destructive, and cost-effective. In this paper, the recent advances and application of NIRS in study on protein structure and molecular interactions are reviewed. At the same time, NIRS combined with other techniques for protein structure research is also introduced. This review demonstrates the feasibility of using NIRS for protein structure characterization and molecular interaction analysis, which not only provides a good theoretical support, but also lay the foundation for the study of protein molecular behavior, and effectively broadens the application field of NIRS. [ABSTRACT FROM AUTHOR]