Quantitative predictive model for screening optimal processing methods of Polygonati rhizoma.

Polygonati rhizoma (Huangjing in Chinese) is a common clinical tonic with the traditional effects of tonifying Qi, nourishing Yin. However, the lack of precise control of processing parameters has led to the uneven quality of processed Huangjing. A prediction model using the CRITIC method optimizes processing by correlating method, component contents, and biological activity, ensuring consistent quality and efficacy.

Dielectric relaxation parameters combing raw milk compositions to improve the prediction performance of milk somatic cell count.

BACKGROUND: Milk somatic cell count (SCC) is an international standard for identifying mastitis in dairy cows and measuring raw milk quality. Milk SCC can be predicted based on dielectric relaxation parameters (DRPs). We noted a high correlation between DRPs and the milk composition content (MCC), and so we hypothesized that combining DRPs with MCC could improve the prediction accuracy of milk SCC. The present study aimed to analyze the relationship between milk SCC, DRPs and MCC, as well as to investigate the potential of combining DRPs with MCC to improve the prediction accuracy of milk SCC. RESULTS: The dielectric spectra (20-4500 MHz) of 276 milk samples were measured, and their DRPs (εl, εh, Δε, τ and σ) were solved by the modified Debye equation. The SCC prediction models were developed using dielectric full spectra, DRPs and DRPs combined with MCC. The results showed the correlations between DRPs (εl, εh, Δε and σ) and MCC (fat, protein, lactose and total solids) were high, and SCC exhibited a non-linear relationship with DRPs and MCC. The 5DRPs + MCC-generalized regression neural network model had the best prediction, with a standard error of prediction for prediction of 0.143 log SCC mL-1 and residual of the prediction bias of 2.870, which was superior to the models based on full spectra, DRPs and near-infrared or visible/near-infrared. CONCLUSION: The present study has improved the prediction accuracy of milk SCC based on the DRPs combing MCC and provides a new method for dairy farming and milk quality assessment. © 2024 Society of Chemical Industry.

Quantitative prediction of CYP3A induction-mediated drug-drug interactions in clinical practice.

There have been no reports on the quantitative prediction of CYP3A induction-mediated decreases in AUC and Cmax for drug candidates identified as a "victims" of CYP3A induction. Our previous study separately evaluated the fold-induction of hepatic and intestinal CYP3A by known inducers using clinical induction data and revealed that we were able to quantitatively predict the AUC ratio (AUCR) of a few CYP3A substrates in the presence and absence of CYP3A inducers. In the present study, we investigate the predictability of AUCR and also Cmax ratio (CmaxR) in additional 54 clinical studies. The fraction metabolized by CYP3A (fm), the intestinal bioavailability (Fg), and the hepatic intrinsic clearance (CLint) of substrates were determined by the in vitro experiments as well as clinical data used for calculating AUCR and CmaxR. The result showed that 65-69% and 65-67% of predictions were within 2-fold of observed AUCR and CmaxR, respectively. A simulation using multiple parameter combinations suggested that the variability of fm and Fg within a certain range might have a minimal impact on the calculation output. These findings suggest that clinical AUCR and CmaxR of CYP3A substrates can be quantitatively predicted from the preclinical stage.

A deep learning-based quantitative prediction model for the processing potentials of soybeans as soymilk raw materials.

Current technologies as correlation analysis, regression analysis and classification model, exhibited various limitations in the evaluation of soybean possessing potentials, including single, vague evaluation and failure of quantitative prediction, and thereby hindering more efficient and profitable soymilk industry. To solve this problem, 54 soybean cultivars and their corresponding soymilks were subjected to chemical, textural, and sensory analyses to obtain the soybean physicochemical nature (PN) and the soymilk profit and quality attribute (PQA) datasets. A deep-learning based model was established to quantitatively predict PQA data using PN data. Through 45 rounds of training with the stochastic gradient descent optimization, 9 remaining pairs of PN and PQA data were used for model validation. Results suggested that the overall prediction performance of the model showed significant improvements through iterative training, and the trained model eventually reached satisfying predictions (|relative error| ≤ 20%, standard deviation of relative error ≤ 40%) on 78% key soymilk PQAs. Future model training using big data may facilitate better prediction on soymilk odor qualities.

A rapid aroma quantification method: Colorimetric sensor-coupled multidimensional spectroscopy applied to black tea aroma.

Aroma affects the quality of black tea, and the rapid evaluation of aroma quality is the key to realize the intelligent processing of black tea. A simple colorimetric sensor array coupled with a hyperspectral system was proposed for the rapid quantitative detection of key volatile organic compounds (VOCs) in black tea. Feature variables were screened based on competitive adaptive reweighted sampling (CARS). Furthermore, the performance of the models for VOCs quantitative prediction was compared. For the quantitative prediction of linalool, benzeneacetaldehyde, hexanal, methyl salicylate, and geraniol, the CARS-least-squares support vector machine model's correlation coefficients were 0.89, 0.95, 0.88, 0.80, and 0.78, respectively. The interaction mechanism of array dyes with VOCs was based on density flooding theory. The optimized highest occupied molecular orbital levels, lowest unoccupied molecular orbital energy levels, dipole moments, and intermolecular distances were determined to be strongly correlated with interactions between array dyes and VOCs.

Quantitative prediction of potential areas likely to yield Se-rich and Cd-low rice using fuzzy weights-of-evidence method.

The research of high-quality agricultural products rich in selenium and low in cadmium (Se-rich and Cd-low, respectively) is related directly to the value of agricultural products and people's food safety. Now it is still challenging to carry out development planning for Se-rich rice. By fuzzy weights-of-evidence method, the geochemical soil survey data of Se and Cd from 27,833 surface soil samples and 804 rice samples was used to predict the probability of areas, in Hubei Province, China, that will likely yield (a) Se-rich and Cd-low rice, (b) Se-rich and Cd-normal rice and (c) Se-rich and Cd-high rice. The areas predicted to likely yield Se-rich and Cd-high rice, Se-rich and Cd-normal rice, and high quality (i.e., Se-rich and Cd-low) rice cover 6542.3 km2 (5.9 %), 35,845.9 km2 (32.6 %), 12,379.7 km2 (11.3 %), respectively, of the surveyed region. According to the predictive distribution probability mapping of Se and Cd, this paper gives preliminary suggestions on the use of endogenous and exogenous Se, and Cd-reduction measures in planting Se-rich rice in different regions of Hubei Province. This study provides a new perspective for rational rice planting of Se-rich agricultural products, and it lays a foundation for the effective implementation of a geochemical soil investigation engineering project, which is of great significance for improving the economic value of Se-rich agricultural products and sustainable utilization of Se land resources.

Quantitative prediction of radiographic progression in patients with axial spondyloarthritis using neural network model in a real-world setting.

BACKGROUND: Predicting radiographic progression in axial spondyloarthritis (axSpA) remains limited because of the complex interaction between multiple associated factors and individual variability in real-world settings. Hence, we tested the feasibility of artificial neural network (ANN) models to predict radiographic progression in axSpA. METHODS: In total, 555 patients with axSpA were split into training and testing datasets at a 3:1 ratio. A generalized linear model (GLM) and ANN models were fitted based on the baseline clinical characteristics and treatment-dependent variables for the modified Stoke Ankylosing Spondylitis Spine Score (mSASSS) of the radiographs at follow-up time points. The mSASSS prediction was evaluated, and explainable machine learning methods were used to provide insights into the model outcome or prediction. RESULTS: The R2 values of the fitted models were in the range of 0.90-0.95 and ANN with an input of mSASSS as the number of each score performed better (root mean squared error (RMSE) = 2.83) than GLM or input of mSASSS as a total score (RMSE = 2.99-3.57). The ANN also effectively captured complex interactions among variables and their contributions to the transition of mSASSS over time in the fitted models. Structural changes constituting the mSASSS scoring systems were the most important contributing factors, and no detectable structural abnormalities at baseline were the most significant factors suppressing mSASSS change. CONCLUSIONS: Clinical and radiographic data-driven ANN allows precise mSASSS prediction in real-world settings. Correct evaluation and prediction of spinal structural changes could be beneficial for monitoring patients with axSpA and developing a treatment plan.

Micromagnetic and Robust Evaluation of Surface Hardness in Cr12MoV Steel Considering Repeatability of the Instrument.

The combination of multifunctional micromagnetic testing and neural network-based prediction models is a promising way of nondestructive and quantitative measurement of steel surface hardness. Current studies mainly focused on improving the prediction accuracy of intelligent models, but the unavoidable and random uncertainties related to instruments were seldom explored. The robustness of the prediction model considering the repeatability of instruments was seldom discussed. In this work, a self-developed multifunctional micromagnetic instrument was employed to perform the repeatability test with Cr12MoV steel. The repeatability of the instrument in measuring multiple magnetic features under both static and dynamic conditions was evaluated. The magnetic features for establishing the prediction model were selected based on the consideration of both the repeatability of the instrument and the ability of magnetic features in surface hardness evaluation. To improve the robustness of the model in surface hardness prediction, a modelling strategy considering the repeatability of the instrument was proposed. Through removing partial magnetic features with higher mean impact values from input nodes, robust evaluation of surface hardness in Cr12MoV steel was realized with the multifunctional micromagnetic instrument.

Prediction of the freshness of horse mackerel (Trachurus japonicus) using E-nose, E-tongue, and colorimeter based on biochemical indexes analyzed during frozen storage of whole fish.

Electronic nose (E-nose), electronic tongue (E-tongue) and colorimeter combined with data fusion strategy and different machine learning algorithms (artificial neural network, ANN; extreme gradient boosting, XGBoost; random forest regression, RFR; support vector regression, SVR) were applied to quantitatively assess and predict the freshness of horse mackerel (Trachurus japonicus) during the 90-day frozen storage. The results showed that the fusion data of the E-nose, E-tongue and colorimeter could contain more information (with a total variance contribution rate of 94.734 %) than that of the independent one. ANN, RFR and XGBoost showed good performance in predicting biochemical indexes with the RP2 (the square correlation coefficient of the Test set) ≥ 0.929, 0.936, 0.888, respectively, while SVR models showed a bad performance (RP2 ≤ 0.835). In addition, among the established quantitative models, the RFR model had the best prediction effect on K value (freshness index) with Rp2 of 0.936, ANN model had the highest fitting degree in predicting carbonyl content (protein oxidation degree) with Rp2 of 0.978, XGBoost model had the best performance in predicting the TBA value (lipid oxidation degree) with Rp2 of 0.994, RFR model was the best strategy for predicting Ca2+-ATPase activity (protein denaturation degree) with Rp2 of 0.969. The results demonstrated that the freshness of frozen fish can be effectively evaluated and predicted by the combination of electronic sensor fusion signals.

Quantitative characterization of the diffusion behavior of sucrose in marinated beef by HSI and FEA.

The quality of marinated meat could be assessed by the uniformity of marinade distribution within it. In this study, the diffusion behavior of sucrose inside the marinated beef was quantitatively characterized from 2D plane and 3D space using hyperspectral imaging (HSI) and finite element analysis (FEA), respectively. Visualization of sucrose content based on HSI showed that the distribution state of sucrose on marinated beef was not uniform. Subsequently, the diffusion behavior of sucrose in the 3D beef geometric model was simulated using FEA. Results revealed that the diffusion rate of sucrose on muscle tissues is significantly higher than other tissues, and the difference in diffusion behavior is the main reason for the inhomogeneous distribution of sucrose. The quantitative characterization of marinade diffusion behavior makes it possible to predict the marinade's transient distribution state, thereby determining the optimal marinade conditions for the meat. Therefore, the method proposed has practical significance for evaluating and regulating the quality of marinated meat products.

Adulteration discrimination and analysis of fresh and frozen-thawed minced adulterated mutton using hyperspectral images combined with recurrence plot and convolutional neural network.

This paper presented a method to detect adulterated mutton using recurrence plot transformed by spectrum combined with convolutional neural network (RP-CNN). For this, 100 adulterated samples of mutton mixed with different proportions (0.5-1-2-5-10% (w/w)) of pork and 20 pure mutton samples were prepared. The results of the classification model of adulterated mutton and the quantitative prediction model of pork content established by this method were comparable for fresh, frozen-thawed and mixed datasets. It shows that the classification accuracies of adulteration mutton on three datasets were 100.00%, 100.00% and 99.95% respectively. Moreover, for the pork content prediction of adulterated mutton, the R2 on three datasets of fresh, frozen-thawed and mixed samples were 0.9762, 0.9807 and 0.9479, respectively. Therefore, the hyperspectral combined with RP-CNN proposed in this paper shows great potential in the classification of adulterated mutton and the pork content prediction of adulterated mutton.

Detection of adulteration in mutton using digital images in time domain combined with deep learning algorithm.

A novel method based on digital images in time domain combined with convolutional neural network (CNN) is proposed for discrimination and analysis of the adulterated mutton. For this, 195 sample images during the constant temperature heating process (about 10 min) were combined with CNN for qualitative discrimination and quantitative prediction of adulterated mutton. Furthermore, the hypothesis that temperature disturbance can improve the detection ability of adulterated mutton was confirmed by comparing the model performance of the initial heating stage and the entire heating process. The experimental results show that the performance of the latter was superior to that of the former. The accuracy of the qualitative discriminant model was increased by 7.33%, the R2 and RPD of the quantitative prediction model of the duck/pork in adulterated mutton were increased by 0.08/0.07 and 0.85/0.87 respectively, while the RMSE decreased by 0.01/0.01. Consequently, the proposed method can be used for detecting adulterated mutton effectively and accurately.

An Investigation of a New Parameter Based on the Plastic Strain Gradient to Characterize Composite Constraint around the Crack Front at a Low Temperature.

Stress corrosion cracking (SCC) is an important destruction form of materials such as stainless steel, nickel-based alloy and their welded components in nuclear reactor pressure vessels and pipes. The existing popular quantitative prediction models of SCC crack growth rate are mainly influenced by fracture toughness values KJc or Jc. In particular, the composite constraint, containing the in-plane constraints and out-of-plane constraints around the crack front, has a significant influence on the fracture toughness of structures in nuclear power plants. Since the plastic strain gradient is a characterization parameter of the quantitative prediction model for crack growth rate, it may be a characterization parameter of composite constraint. On the basis of the experimental data at a low temperature of alloy steel 22NiMoCr3-7 used in nuclear pressure vessels, the gradient of equivalent plastic strain DPEEQ around the crack fronts at different constraint levels was calculated using the finite element method, which introduces a new non-dimensional constraint parameter Dp, to uniformly characterize the in-plane and out-of-plane constraint effects. Compared with constraint parameters APEEQ or Ap, the process of obtaining parameters DPEEQ or Dp is much simpler and easier. In a wide range, a single correlation curve was drawn between parameter Dp and normalized fracture toughness values KJc/Kref or Jc/Jref of specimens at a low or high constraint level. Therefore, regardless of whether the constraint levels of the structures or standard specimens are low or high, constraint parameter Dp can be used to measure their fracture toughness. To build an evaluation method that has structural integrity and safety while containing the composite constraint effects, in addition to accurate theoretical interpretation, further verification experiments, numerical simulations and detailed discussions are still needed.

Association between Predicted Effects of TP53 Missense Variants on Protein Conformation and Their Phenotypic Presentation as Li-Fraumeni Syndrome or Hereditary Breast Cancer.

Rare germline pathogenic TP53 missense variants often predispose to a wide spectrum of tumors characterized by Li-Fraumeni syndrome (LFS) but a subset of variants is also seen in families with exclusively hereditary breast cancer (HBC) outcomes. We have developed a logistic regression model with the aim of predicting LFS and HBC outcomes, based on the predicted effects of individual TP53 variants on aspects of protein conformation. A total of 48 missense variants either unique for LFS (n = 24) or exclusively reported in HBC (n = 24) were included. LFS-variants were over-represented in residues tending to be buried in the core of the tertiary structure of TP53 (p = 0.0014). The favored logistic regression model describes disease outcome in terms of explanatory variables related to the surface or buried status of residues as well as their propensity to contribute to protein compactness or protein-protein interactions. Reduced, internally validated models discriminated well between LFS and HBC (C-statistic = 0.78-0.84; equivalent to the area under the ROC (receiver operating characteristic) curve), had a low risk for over-fitting and were well calibrated in relation to the known outcome risk. In conclusion, this study presents a phenotypic prediction model of LFS and HBC risk for germline TP53 missense variants, in an attempt to provide a complementary tool for future decision making and clinical handling.

Structure and Microwave Dielectric Properties of Gillespite-Type ACuSi4O10 (A = Ca, Sr, Ba) Ceramics and Quantitative Prediction of the Q × f Value via Machine Learning.

Structure and dielectric properties of gillespite-type ceramics ACuSi4O10 (A = Ca, Sr, Ba) were investigated by crystal structure refinement, far-infrared reflectivity spectroscopy, and microwave dielectric measurements. A series of (CaxSr1-x)CuSi4O10 (0 < x < 1) ceramics with relative permittivities of 5.70-5.82, Q × f values of 20391-48794 GHz (@ ∼ 13.5 GHz), and τf of -46.3 to -38.9 ppm/°C were synthesized. By Ca2+ substitution for Sr2+ at the A-site, the rigid double-layered copper silicate framework remains stable, resulting in the nearly unchanged relative permittivity, while the [(Ca,Sr)O8] dodecahedron undergoes shrinkage and distortion, which is correlated to the changes in the Q × f and τf values. The normalized bond valence sums indicate that almost all ions are rattling, weakening the bond strengths and enlarging the molecular dielectric polarizability. The fitting of far-infrared reflectivity spectra reveals that the local structure changes suppress the intermediate and low-frequency vibrational modes significantly and improves the contribution from electronic polarization to permittivity. Symmetry breaking of the [(Ca,Sr)O8] dodecahedron conforms to the elevated restoring forces acting on the ions and improves the τf value. The large span in Q × f value may have intricate correlations to local structure changes and defects. Machine learning methods were introduced to explore the decisive structural factors for the Q × f value. A Q × f value prediction model correlated with the A-O2 bond length and the variance of A-O bond lengths was established. The Q × f values of isostructural (BaySr1-y)CuSi4O10 ceramics were predicted and verified by experiments.

A Portable Spectrometric System for Quantitative Prediction of the Soluble Solids Content of Apples with a Pre-calibrated Multispectral Sensor Chipset.

A portable spectrometric system for nondestructive assessment of the soluble solids content (SSC) of fruits for practical applications has been proposed and its performance has been examined by an experiment on quantitative prediction of the SSC of apples. Although the spectroscopic technique is a powerful tool for predicting the internal qualities of fruits, its practical applications are limited due to its high cost and complexity. In the proposed system, the spectra of apples were collected by a simple optical setup with a cheap pre-calibrated multispectral chipset. An optimal multiple linear regression model with five wavebands at 900, 760, 730, 680, and 535 nm revealed the best performance with the coefficient of determination of prediction and the root mean square error of prediction of 0.861 and 0.403 °Brix, respectively, which was comparable to that of the previous studies using dispersive spectrometers. Compared with previously reported systems using discrete filters or light emitting diodes, the proposed system was superior in terms of manufacturability and reproducibility. The experimental results confirmed that the proposed system had a considerable potential for practical, cost-effective applications of the SSC prediction, not only for apples but also for other fruits.

Quantitative prediction of the bitterness of atomoxetine hydrochloride and taste-masked using hydroxypropyl-ß-cyclodextrin: A biosensor evaluation and interaction study.

The bitterness of a drug is a major challenge for patient acceptability and compliance, especially for children. Due to the toxicity of medication, a human taste panel test has certain limitations. Atomoxetine hydrochloride (HCl), which is used for the treatment of attention deficit/hyperactivity disorder (ADHD), has an extremely bitter taste. The aim of this work is to quantitatively predict the bitterness of atomoxetine HCl by a biosensor system. Based on the mechanism of detection of the electronic tongue (E-tongue), the bitterness of atomoxetine HCl was evaluated, and it was found that its bitterness was similar to that of quinine HCl. The bitterness threshold of atomoxetine HCl was 8.61 µg/ml based on the Change of membrane Potential caused by Adsorption (CPA) value of the BT0 sensor. In this study, the taste-masking efficiency of 2-hydroxypropyl-ß-cyclodextrin (HP-ß-CyD) was assessed by Euclidean distances on a principle component analysis (PCA) map with the SA402B Taste Sensing System, and the host-guest interactions were investigated by differential scanning calorimetry (DSC), powder X-ray diffraction (XRD), nuclear magnetic resonance (NMR) spectroscopy and scanning electron microscopy (SEM). Biosensor evaluation and characterization of the inclusion complex indicated that atomoxetine HCl could actively react with 2-hydroxypropyl-ß-cyclodextrin.

The qualitative and quantitative assessment of tea quality based on E-nose, E-tongue and E-eye combined with chemometrics.

Electronic nose (E-nose), electronic tongue (E-tongue) and electronic eye (E-eye) combined with chemometrics methods were applied for qualitative identification and quantitative prediction of tea quality. Main chemical components, such as amino acids, catechins, polyphenols and caffeine were measured by traditional methods. Feature-level fusion strategy for the integration of the signals was introduced to integrate the E-nose, E-tongue and E-eye signals, aiming at improving the performances of identification and prediction models. Perfect results with an accuracy of 100% were obtained for qualitative identification of tea quality grades, based on fusion signals by support vector machine and random forest. Quantitative models were established for predicting the contents of the chemical components based on independent electronic signals and fusion signals by partial least squares regression, support vector machine and random forest. Random forest based on the fusion signals achieved the best performance in predicting the concentration of those chemical components.

The problem of racemization in drug discovery and tools to predict it.

INTRODUCTION: Racemization has long been an ignored risk in drug development, probably because of a lack of convenient access to good tools for its detection and an absence of methods to predict racemization risk. As a result, the potential effects of racemization have been systematically underestimated. Areas covered: Herein, the potential effects of racemization are discussed through a review of drugs for which activity and side effects for both enantiomers are known. Subsequently, drugs known to racemize are discussed and the authors review methods to predict racemization risk. Application of a method quantitatively predicting racemization risk to databases of compounds from the medicinal chemistry literature shows that success in clinical trials is negatively correlated with racemization risk. Expert opinion: It is envisioned that a quantitative method of predicting racemization risk will remove a blind spot from the drug development pipeline. Removal of the blind spot will make drug development more efficient and result in less late-stage attrition of the drug pipeline.