Discriminant Model Research Articles

Elevated SCN11A concentrations associated with lower serum lipid levels in patients with major depressive disorder

The pathogenesis of major depressive disorder (MDD) involves lipid metabolism. Our earlier research also revealed that MDD patients had much lower total cholesterol (TC) concentrations than healthy controls (HCs). However, it is still unclear why TC decreased in MDD. Here, based on the Ingenuity Knowledge Base’s ingenuity pathway analysis, we found that sodium voltage-gated channel alpha subunit 11A (SCN11A) might serve as a link between low lipid levels and MDD. We analyzed the TC levels and used ELISA kits to measure the levels of SCN11A in the serum from 139 MDD patients, and 65 HCs to confirm this theory and explore the potential involvement of SCN11A in MDD. The findings revealed that TC levels were considerably lower and SCN11A levels were remarkably increased in MDD patients than those in HCs, while they were significantly reversed in drug-treatment MDD patients than in drug-naïve MDD patients. There was no significant difference in SCN11A levels among MDD patients who used single or multiple antidepressants, and selective serotonin reuptake inhibitors or other antidepressants. Pearson correlation analysis showed that the levels of TC and SCN11A were linked with the Hamilton Depression Rating Scales score. A substantial association was also found between TC and SCN11A. Moreover, a discriminative model made up of SCN11A was discovered, which produced an area under a curve of 0.9571 in the training set and 0.9357 in the testing set. Taken together, our findings indicated that SCN11A may serve as a link between low lipid levels and MDD, and showed promise as a candidate biomarker for MDD.

Exploring facial cues: automated deception detection using artificial intelligence

Deception detection is an interdisciplinary field attracting researchers from psychology, criminology, computer science, and economics. Automated deception detection presents unique challenges compared to traditional polygraph tests, but also offers novel economic applications. In this spirit, we propose an approach combining deep learning with discriminative models for deception detection. Therefore, we train CNNs for the facial modalities of gaze, head pose, and facial expressions, allowing us to compute facial cues. Due to the very limited availability of training data for deception, we utilize early fusion on the CNN outputs to perform deception classification. We evaluate our approach on five datasets, including four well-known publicly available datasets and a new economically motivated rolling dice experiment. Results reveal performance differences among modalities, with facial expressions outperforming gaze and head pose overall. Combining multiple modalities and feature selection consistently enhances detection performance. The observed variations in expressed features across datasets with different contexts affirm the importance of scenario-specific training data for effective deception detection, further indicating the influence of context on deceptive behavior. Cross-dataset experiments reinforce these findings. Notably, low-stake datasets, including the rolling dice Experiment, present more challenges for deception detection compared to the high-stake Real-Life trials dataset. Nevertheless, various evaluation measures show deception detection performance surpassing chance levels. Our proposed approach and comprehensive evaluation highlight the challenges and potential of automating deception detection from facial cues, offering promise for future research.

Construction of Discrimination Models of Cationic Drugs for Phospholipidosis Induction Potential by Using Interaction Data with Immobilized Artificial Membrane as Well as Physicochemical Properties

Accurate prediction of the phospholipidosis–induction risk of drugs at early stages is important in drug development. So far, discrimination models for predicting the induction risk of cationic drugs have been proposed, but it is still challenging to accurately predict the risk of cationic drugs with intermediate hydrophobicity (logP). In this study, we introduced a parameter (Δlogk40) reflecting not only hydrophobic interaction but also interactions with the polar headgroup between cationic drugs and phospholipids, obtained with liquid chromatography using an immobilized artificial membrane column. The parameter was used along with other physicochemical properties as features to construct discrimination models. Linear discriminant analysis, the modified Mahalanobis discriminant analysis, support vector machine, and random forest were employed for model construction. The results showed that all discrimination models exhibited good predictive performance, with the modified Mahalanobis discriminant analysis and random forest providing the best results for cationic drugs, suggesting that the usefulness of the parameter reflecting complex interactions between cationic drugs and immobilized artificial membrane for constructing discrimination models to predict the induction risk. Furthermore, by applying the parameter as a feature in constructing discrimination models, we demonstrated an improvement in the predictive performance for drugs with intermediate hydrophobicity.

SSC and pH prediction and maturity classification of grapes based on hyperspectral imaging

Soluble solids content (SSC) and pH of red globe grapes are crucial measures of quality. In this paper, we used hyperspectral imaging technology to achieve nondestructive detection and distribution visualization of SSC and pH of red globe grapes. First, the hyperspectral images of samples were collected. Then, CARS, SPA, GA, IRIV were used to extract feature variables from raw spectral (RAW) information. The PLSR prediction models of samples were developed. By comparing the different prediction models, RAW-IRIV-PLSR was selected as the optimal model. Finally, the SSC and pH of the samples were calculated to obtain a grayscale image and perform a pseudo-color transformation to visualize the distribution of SSC and pH. By studying the classification of the maturity of samples, it was concluded that the best discriminant classification model of maturity was RAW-IRIV-ELM. Hyperspectral also provided a new method for maturity stage classification of red globe grapes.

The Influence of the Soil Profile on the Formation of the Elemental Image of Grapes and Wine of the Cabernet Sauvignon Variety.

The features for assessing the authenticity of wines by region of origin are studied, based on the relationship between the mineral composition of the wine, the grapes, and the soil profile (0 to 160 cm) from the place of growth of Cabernet Sauvignon grapes. Soil, grape, and wine samples were taken from the territories of six vineyards in the Anapa district of Krasnodar Territory, Russia. Using the methods of ICP-OES, thermal, and X-ray phase analysis, the soils were differentiated into three groups, differing in mineralogical and mineral compositions. The soil samples of the first group contained up to 31% quartz, the second group up to 25% quartz and 19% mixed calcite, and the third group up to 32% calcite and 15% quartz. The formation of the elemental image of the grapes was studied, taking into account the total content and mobile forms of metals in the soil. The territorial proximity of the vineyards did not affect the extraction of elements from the soil into the grape berry, and the migration of metals for each territory was selective. According to the values of the biological absorption coefficient, the degree of transition of metals from the soil to a berry was estimated. For K, Ti, Zn, Rb, Cu, and Fe in all berries, the coefficient was higher than 1.00, which means that the berry extracts contained not only mobile-form, but also difficult-to-dissolve metal compounds. The migration of macro-components from the soil to the berry was low, and amounted to 6-7% for Ca, 0.8-3.0% for Na, and 25-70% for Mg of the concentration of their mobile forms. For all territories, the maximum correlation between metal concentrations in grapes and soil was observed for samples from a depth of 0-40 cm. The discriminant model based on concentrations of Rb, Al, K, Sr, Co, Na, Pb, Ca, and Ni showed the formation of clusters in the territories of vineyard cultivation. The developed model allow the problems of identifying wines by region to be solved with high accuracy, using their elemental image.

Exogenous curcumin mitigates As stress in spinach plants: A biochemical and metabolomics investigation

The spinach (S. oleracea L.) was used as a model plant to investigate As toxicity on physio-biochemical processes, exploring the potential mitigation effect of curcumin (Cur) applied exogenously at three concentrations (1, 10, and 20 μM Cur). The employment of Cur significantly mitigated As-induced stress in spinach photosynthetic performance (Fv/Fm, Fo/Fm, and Fv/Fo). Moreover, the co-incubation of Cur with As improved physiological processes mainly associated with plant water systems affected by As stress by recovering the leaf's relative water content (RWC) and osmotic potential (ψπ) nearly to the control level and increasing the transpiration rate (E; 39–59%), stomatal conductivity (gs; 86–116%), and carbon assimilation rate (A; 84–121%) compared to As stressed plants. The beneficial effect of Cur in coping with As-induced stress was also assessed at the plant's oxidative level by reducing oxidative stress biomarkers (H2O2 and MDA) and increasing non-enzymatic antioxidant capacity.Untargeted metabolomics analysis was adopted to investigate the main processes affected by As and Cur application. A multifactorial ANOVA discrimination model (AMOPLS-DA) and canonical correlation analysis (rCCA) were employed to identify relevant metabolic changes and biomarkers associated with Cur and As treatments. The results highlighted that Cur significantly determined the accumulation of glucosinolates, phenolic compounds, and an increase in glutathione redox cycle activities, suggesting an overall elicitation of plant secondary metabolisms. Specifically, the correlation analysis reported a strong and positive correlation between (+)-dihydrokaempferol, L-phenylalanine (precursor of phenolic compounds), and serotonin-related metabolites with antioxidant activities (ABTS and DPPH), suggesting the involvement of Cur application in promoting a cross-talk between ROS signaling and phytohormones, especially melatonin and serotonin, working coordinately to alleviate As-induced oxidative stress. The modulation of plant metabolism was also observed at the level of amino acids, fatty acids, and secondary metabolites synthesis, including N-containing compounds, terpenes, and phenylpropanoids to cooperate with As-induced stress response.

Research on Discriminant Model of Water Inrush Source By Principal Component-cluster Analysis in Jiaozuo Mining Area

This paper takes Jiaozuo Mining Area as the research object, based on the analysis of the hydrogeological conditions of the mining area, expounds the characteristics of coal strata, aquifers and groundwater recharge, runoff and discharge in the mining area; analyses the water inrush sources and water diversion channels in the mining area, analyses the routine water chemical data of each aquifer in the mining area, draws the piper three-line diagram and confirms it. To determine the hydrochemical type of groundwater in aquifer, six common water chemical ions are used as discriminant factors, a discriminant model of water inrush source is established by combining principal component analysis and cluster analysis, and the principal component of conventional water chemical ions is extracted as cluster variable to discriminate Water Inrush Source in Jiaozuo Mining Area. In order to prove the rationality and validity of the model, another group of inrush sources in Jiaozuo Mining Area is discussed. The water sample data are discriminated and the results obtained by cluster analysis are compared to verify the accuracy of the model. The results show that the model is feasible. To sum up, the identification model of inrush water source by principal component-cluster analysis can accurately and effectively identify the source of inrush water in Jiaozuo Mining Area.

Evaluating precision medicine tools in cystic fibrosis for racial and ethnic fairness.

Patients with cystic fibrosis (CF) experience frequent episodes of acute decline in lung function called pulmonary exacerbations (PEx). An existing clinical and place-based precision medicine algorithm that accurately predicts PEx could include racial and ethnic biases in clinical and geospatial training data, leading to unintentional exacerbation of health inequities. We estimated receiver operating characteristic curves based on predictions from a nonstationary Gaussian stochastic process model for PEx within 3, 6, and 12 months among 26,392 individuals aged 6 years and above (2003-2017) from the US CF Foundation Patient Registry. We screened predictors to identify reasons for discriminatory model performance. The precision medicine algorithm performed worse predicting a PEx among Black patients when compared with White patients or to patients of another race for all three prediction horizons. There was little to no difference in prediction accuracies among Hispanic and non-Hispanic patients for the same prediction horizons. Differences in F508del, smoking households, secondhand smoke exposure, primary and secondary road densities, distance and drive time to the CF center, and average number of clinical evaluations were key factors associated with race. Racial differences in prediction accuracies from our PEx precision medicine algorithm exist. Misclassification of future PEx was attributable to several underlying factors that correspond to race: CF mutation, location where the patient lives, and clinical awareness. Associations of our proxies with race for CF-related health outcomes can lead to systemic racism in data collection and in prediction accuracies from precision medicine algorithms constructed from it.

Analysis of quantum key distribution based on unified model of sequential state discrimination strategy

The quantum key distribution for multiparty is one of the essential subjects of study. Especially, without using entangled states, performing the quantum key distribution for multiparty is a critical area of research. For this purpose, sequential state discrimination, which provides multiparty quantum communication and quantum key distribution for multiple receivers, has recently been introduced. Moreover, the sequential state discrimination is applicable for the security analysis against an eavesdropper’s attack. In this work, we provide the security analysis of quantum key distribution by proposing a unified model of sequential state discrimination including an eavesdropper. In this model, the success probability of eavesdropping is used as a figure of merit for the security analysis. Moreover, we obtain a non-zero secret key rate between the sender and receiver, which implies that the sender and receiver can share a secret key despite the eavesdropper’s scheme that optimizing the success probability of eavesdropping. Further, we propose an experimental methodology for the proposed model, which is implementable with linear optics. We observe that the secret key between the sender and receiver can be non-zero, even with imperfections.

A Dataset for Evaluating Contextualized Representation of Biomedical Concepts in Language Models

Due to the complexity of the biomedical domain, the ability to capture semantically meaningful representations of terms in context is a long-standing challenge. Despite important progress in the past years, no evaluation benchmark has been developed to evaluate how well language models represent biomedical concepts according to their corresponding context. Inspired by the Word-in-Context (WiC) benchmark, in which word sense disambiguation is reformulated as a binary classification task, we propose a novel dataset, BioWiC, to evaluate the ability of language models to encode biomedical terms in context. BioWiC comprises 20’156 instances, covering over 7’400 unique biomedical terms, making it the largest WiC dataset in the biomedical domain. We evaluate BioWiC both intrinsically and extrinsically and show that it could be used as a reliable benchmark for evaluating context-dependent embeddings in biomedical corpora. In addition, we conduct several experiments using a variety of discriminative and generative large language models to establish robust baselines that can serve as a foundation for future research.

Aging of deep venous thrombosis in-vivo using polarization sensitive optical coherence tomography.

Deep venous thrombosis (DVT) is a medical condition with significant post-event morbidity and mortality coupled with limited treatment options. Treatment strategy and efficacy are highly dependent on the structural composition of the thrombus, which evolves over time from initial formation and is currently unevaluable with standard clinical testing. Here, we investigate the use of intravascular polarization-sensitive optical coherence tomography (PS-OCT) to assess thrombus morphology and composition in a rat DVT model in-vivo, including changes that occur over the thrombus aging process. PS-OCT measures tissue birefringence, which provides contrast for collagen and smooth muscle cells that are present in older, chronic clots. Thrombi in the inferior vena cava of two cohorts of rats were imaged in-vivo with intravascular PS-OCT at 24 hours (acute, nrats = 3, 73 cross-sections) or 28 days (chronic, nrats = 4, 41 cross-sections) after thrombus formation. Co-registered histology was labelled by an independent pathologist to establish ground-truth clot composition. Automated analysis of OCT cross-sectional images differentiated acute and chronic thrombi with 97.6% sensitivity and 98.6% specificity using a linear discriminant model comprised of both polarization and conventional OCT metrics. These results support PS-OCT as a highly sensitive imaging modality for the assessment of DVT composition to differentiate acute and chronic thrombi. Intravascular PS-OCT imaging could be integrated with advanced catheter-based treatment strategies and serve to guide therapeutic decision-making and deployment, by offering an accurate assessment of DVT patients in real time.

SketchTrans: Disentangled Prototype Learning With Transformer for Sketch-Photo Recognition.

Matching hand-drawn sketches with photos (a.k.a sketch-photo recognition or re-identification) faces the information asymmetry challenge due to the abstract nature of the sketch modality. Existing works tend to learn shared embedding spaces with CNN models by discarding the appearance cues for photo images or introducing GAN for sketch-photo synthesis. The former unavoidably loses discriminability, while the latter contains ineffaceable generation noise. In this paper, we start the first attempt to design an information-aligned sketch transformer (SketchTrans +) via cross-modal disentangled prototype learning, while the transformer has shown great promise for discriminative visual modelling. Specifically, we design an asymmetric disentanglement scheme with a dynamic updatable auxiliary sketch (A-sketch) to align the modality representations without sacrificing information. The asymmetric disentanglement decomposes the photo representations into sketch-relevant and sketch-irrelevant cues, transferring sketch-irrelevant knowledge into the sketch modality to compensate for the missing information. Moreover, considering the feature discrepancy between the two modalities, we present a modality-aware prototype contrastive learning method that mines representative modality-sharing information using the modality-aware prototypes rather than the original feature representations. Extensive experiments on category- and instance-level sketch-based datasets validate the superiority of our proposed method under various metrics.

Virtual biopsies for breast cancer using MCR-ALS perfusion-based biomarkers and double cross-validation PLS-DA

Functional MRI is, currently, the most sensitive technique in breast cancer for detecting early tumors, and perfusion (DCE-MRI) has become the most important sequence to depict and characterize angiogenesis and neovascularization. In this work, we propose the use of new biomarkers that are related to clear physiological phenomena, obtained from MCR-ALS as an alternative to curve-based pseudo-biomarkers and pharmacokinetics models. In order to provide a discrimination and prediction model between healthy tissue and cancer, we propose using PLS-DA with double cross-validation (2CV) and variable selection, repeated several times and obtaining excellent average results for the performance indexes (f-score: 0.9149, MCC: 0.8538, AUROC: 0.8794). After selecting the optimal prediction model, a unique probabilistic map called “virtual biopsy” that shows in different colors the probability that each pixel of the image has a tumor behavior is obtained, helping the specialist with the identification and characterization of breast tumors with only one easy-to-interpret biomarker map.

A novel RCACycleGAN model is proposed for the high-precision reconstruction of sparse TFM images

The sparse total focusing method (TFM) has been shown to enhance the computational efficacy of ultrasound imaging but the image quality of ultrasound regrettably deteriorates with an increase in the sparsity rate of array elements. Deep learning has made remarkable advancements in image processing and cycle-consistent generative adversarial networks (CycleGANs) have been extensively employed to reconstruct diverse image categories. However, due to the incomplete extraction of image feature information by the generator and discriminator in a CycleGAN, high-quality sparse TFM images cannot be directly reconstructed using CycleGANs. There is also a risk of losing crucial feature information related to minor defects. As a result, this paper modifies the generator and discriminator in the CycleGAN to construct a new relativistic discriminator and coordinate attention CycleGAN (RCACycleGAN) model, which enables high-precision reconstruction of sparse TFM images. The addition of the coordinate attention module to the CycleGAN enhances the defective feature representation by fully considering the channel and spatial correlation between regions and using the fusion of spatially perceived feature maps in different directions. It solves the problem of easy loss of defective key feature information. The relativistic discriminator replaces the PatchGAN discriminator in the CycleGAN and evaluates the quality of both real and sparse TFM reconstructed images to ensure a relative image quality evaluation. This process solves the problem of unstable image quality of the sparse TFM reconstructed image. Experimental results demonstrate that RCACycleGAN can stably reconstruct sparse TFM images even in small sample dataset scenarios. The proposed network model reconstructs images with better accuracy, including in terms of structural similarity, defect roundness and area, and has a shorter training time than several existing network models.

Analysis of metabolic syndrome in bilateral upper urinary tract stones: A retrospective study of 3905 cases

Bilateral upper urinary tract stones are significantly related to renal function damage. However, few studies characterized the risk factors of bilateral upper urinary tract stones. We retrospectively enrolled 3905 patients with urinary tract stones from March 2019 to March 2022 at the Second Hospital of Tianjin Medical University. Patients were divided into two groups according to the location of the stones, and the related data were evaluated. In this study, 2485 unilateral and 1420 bilateral stone patients were included. Multivariate logistic regression analysis showed that BMI, gout, hyperparathyroidism, uric acid stone, urine PH, 24-h urinary calcium, blood uric acid, and metabolic syndrome (Mets) were independent risk factors for bilateral stone formation(P < 0.05). Based on these results, we construct a discrimination model. This model revealed good discrimination with an area under the receiver operating characteristic curves of 0.617, and the sensitivity and specificity were 0.592 and 0.586, respectively. Furthermore, the number of Mets components increased the risk of bilateral upper urinary tract stones. Hypertension, hyperglycemia, and low HDL level were strongly associated with bilateral upper urinary tract stones (P < 0.05). Patients with 5 components Mets had 1.89-fold higher risk of bilateral upper urinary tract stones than those with 1 component Mets (OR 3.381; 95 % CI 1.221–9.360; P = 0.013). Additionally, male patients with Mets had higher risk of bilateral upper urinary tract stones than female patients. Our analysis revealed that eight clinical factors were associated with the formation of bilateral upper urinary tract stones, namely BMI, gout, hyperparathyroidism, uric acid stone, urine PH, 24-h urinary calcium, blood uric acid, and Mets. This study could help clinicians adjust treatment strategies for high-risk patients with bilateral upper urinary tract stones.

GAN‐Based Multi‐Decomposition Photo Cartoonization

AbstractBackgroundCartoon images play a vital role in film production, scientific and educational animation, video games, and other fields, and are one of the key visual expressions of artistic creation. However, since hand‐crafted cartoon images often require a great deal of time and effort on the part of professional artists, it is necessary to be able to automatically transform real‐world images into different styles of cartoon images. Although cartoon images vary from artist to artist, cartoon images generally have the unique characteristics of being highly simplified and abstract, with clear edges, smooth color shading, and relatively simple textures. However, existing image cartoonization methods tend to create a number of problems when performing style transfer, which mainly include: (1) the resulting generated images do not have obvious cartoon‐style textures; and (2) the generated images are prone to structural confusion, color artifacts, and loss of the original image content. Therefore, it is also a great challenge in the field of image cartoonization to be able to make a good balance between style transfer and content keeping.MethodsIn this paper, we propose a GAN‐based multi‐attention mechanism for image cartoonization to address the above issues. The method combines the residual block used to extract deep network features in the generator with the attention mechanism, and further strengthens the perceptual ability of the generative model to cartoon images through the adaptive feature correction of the attention module to improve the cartoon features of the generated images. At the same time, we also introduce the attention mechanism in the convolution block of the discriminator, which is used to further reduce the image visual quality problem caused by the style transfer process. By introducing the attention mechanism into the generator and discriminator models of the generative adversarial network, our method enables the generated images to have obvious cartoon‐style features while effectively improving the image's visual quality.ResultsA large number of quantitative, qualitative, and ablation experiments are conducted to demonstrate the advantages of our method in the field of image cartoonization and the role of each module in the method.

Vis-NIR spectroscopic discriminant analysis of aflatoxin B1 excessive standard in peanut meal as feedstuff materials

A fast, simple and reagent-free detection method for aflatoxin B1 (AFB1) is of great significance to food safety and human health. Visible and near-infrared (Vis-NIR) spectroscopy was applied to the discriminant analysis of AFB1 excessive standard of peanut meal as feedstuff materials. Two types of excessive standard discriminant models based on spectral quantitative analysis with partial least squares (PLS) and direct pattern recognition with partial least squares-discrimination analysis (PLS-DA) were established, respectively. Multi-parameter optimization of Norris derivative filtering (NDF) was used for spectral preprocessing; the two-stage wavelength screening method based on equidistant combination-wavelength step-by-step phase-out (EC-WSP) was used for wavelength optimization. A rigorous sample experimental design of calibration-prediction-validation was utilized. The calibration and prediction samples were used for modeling and parameter optimization, and the selected model was validated using the independent validation samples. For quantitative analysis-based, the positive, negative and total recognition-accuracy rates in validation (RARV+, RARV-, and RARV) were 84.8 %, 74.6 % and 79.8 %, respectively; but, the relative root mean square error of prediction was as high as 51.0 %. For pattern recognition-based, the RARV+, RARV-, and RARV were 93.3 %, 90.5 % and 91.9 %, respectively. Moreover, the number of wavelengths N was drastically reduced to 17, and the discrete wavelength combination was in NIR overtone frequency region. The results indicated that, the EC-WSP-PLS-DA model achieved significantly better discrimination effect. Thus demonstrated that Vis-NIR spectroscopy has feasibility for the excessive standard discrimination of aflatoxin B1 in feedstuff materials.

An optimal framework for natural English translate processing: On the application of artificial neural network and Adam optimization algorithm

Traditional rule-based and statistical methods have limitations when dealing with complex language structures and semantics. In neural network machine translation algorithms, the objective function is usually to improve the accuracy of n-ary words. However, this does not guarantee a more natural and accurate translation. To overcome these challenges, this paper proposes an optimization algorithm for English natural translation processing based on neural networks, which combines Generative Adversarial Network (GAN) and Transformer models. In GAN, the generative model uses the Transformer model to generate false samples, while the discriminative model uses a binary classifier based on convolutional neural networks and attention mechanisms to distinguish between true and false samples. During the training process, reinforcement learning algorithms are added to evaluate and adjust the generated sentences, and the parameters of the generated model are updated. The classification results of the discriminative model are used together with the Bilingual Evaluation Basis Value (BLEU) objective function to evaluate false samples, and the results are fed back to the generating model to guide parameter updates and optimization. Extensive experiments were conducted on a standard English-Chinese machine translation dataset to evaluate our method. Compared with the benchmark model that only uses supervised learning methods, our neural network-based optimization algorithm for English natural translation processing has achieved significant improvements in translation quality. According to statistical comparison, compared with the Transformer model (BLUE = 33.63 and AP = 90%) and the deep learning model based on long-term and short-term memory (BLUE = 30.26 and AP = 83%), the GAN and Transformer models proposed as the best framework exhibit better performance in bilingual evaluation deficiency (BLEU) (34.35) and accuracy (AP = 95%).

The ice recrystallization inhibition activity of wheat glutenin hydrolysates and effect of salt on their activity

This study aimed to investigate the antifreeze activity of wheat glutenin hydrolysates produced by Alcalase and trypsin at varying degrees of hydrolysis. The influence of salt concentrations in two dispersing media, phosphate-buffered saline (PBS) and NaCl solution, and the types of cations, NaCl and CaCl2, on hydrolysates was further analyzed. The results revealed a consistently higher ice recrystallization inhibition (IRI) activity for all hydrolysates dispersed in 0.1 x PBS than in 1 x PBS. Interestingly, glutenin hydrolysates exhibited better IRI activity in CaCl2 than in NaCl solution under the same ionic strength. Furthermore, trypsin-derived hydrolysates (with a molar mass about 10 kDa) consistently had better IRI activity than those produced by Alcalase (with a molar mass less than 1 kDa), regardless of the dispersing media. The observed increase in IRI activity was associated with alterations in the secondary structure, characterized by a higher α-helix and lower β-turns content. This suggests that structural rigidity of the molecules plays a significant role in enhancing the antifreeze activity of peptides. Additionally, the scores plot of the partial least-squares discriminant analysis model indicates that salt concentration had a more significant impact than salt type on the IRI activity of glutenin hydrolysates. In conclusion, our findings provide insights into the factors influencing the IRI activity of protein hydrolysates.

Deep learning-based modeling of the cyclic behavior of replaceable fuse buckling-restrained braces (BRBs)

This paper presents a novel approach for predicting the behavior of buckling restrained braces (BRBs) using long short-term memory (LSTM) and residual neural network (ResNet) models. Nonlinear finite element analysis (NLFEA) usually requires 3D modeling of complex parts and assigning various material and simulation properties before conducting the analysis, which can be time-consuming and computationally costly. LSTM networks are particularly well-suited for modeling sequential data, such as time series, and ResNet is a discriminative deep learning-based model that can handle deeper architectures without the issue of vanishing gradient. Developing a general LSTM model requires a comprehensive database for training, cross-validation, and blind testing. Even if such a database were available, concatenating data from different BRB specimens would not be feasible when modeling a data series. Such a method would intertwine the features of the individual specimens, rendering the data useless for machine-learning purposes. On the other hand, a well-trained LSTM can predict cyclic behavior for specimens that resemble the training data. As such, a group of well-trained models can produce superior predictions when used on individually familiar data. Hence, there is a need for a prescreening classification stage. The framework presented herein utilizes an AI classifier (ResNet) that automatically recognizes the BRB specimen type of the input data and directs it to the appropriate LSTM model for prediction. The presented framework demonstrates excellent predictions with an accuracy greater than 99%. It is customizable, adaptable, and scalable to include different BRB specimens. The input data consisted of the displacement of the BRB specimens based on the AISC 341–10 qualification recommendations, while the output was the corresponding force (hysteretic response to cyclic loading). The proposed framework can be valuable in earthquake engineering applications as it demonstrates superior predictions.