JMIR AI. 2025 Mar 20;4:e65729. doi: 10.2196/65729.

ABSTRACT

BACKGROUND: Recent advancements in Generative Adversarial Networks and large language models (LLMs) have significantly advanced the synthesis and augmentation of medical data. These and other deep learning-based methods offer promising potential for generating high-quality, realistic datasets crucial for improving machine learning applications in health care, particularly in contexts where data privacy and availability are limiting factors. However, challenges remain in accurately capturing the complex associations inherent in medical datasets.

OBJECTIVE: This study evaluates the effectiveness of various Synthetic Data Generation (SDG) methods in replicating the correlation structures inherent in real medical datasets. In addition, it examines their performance in downstream tasks using Random Forests (RFs) as the benchmark model. To provide a comprehensive analysis, alternative models such as eXtreme Gradient Boosting and Gated Additive Tree Ensembles are also considered. We compare the following SDG approaches: Synthetic Populations in R (synthpop), copula, copulagan, Conditional Tabular Generative Adversarial Network (ctgan), tabular variational autoencoder (tvae), and tabula for LLMs.

METHODS: We evaluated synthetic data generation methods using both real-world and simulated datasets. Simulated data consist of 10 Gaussian variables and one binary target variable with varying correlation structures, generated via Cholesky decomposition. Real-world datasets include the body performance dataset with 13,393 samples for fitness classification, the Wisconsin Breast Cancer dataset with 569 samples for tumor diagnosis, and the diabetes dataset with 768 samples for diabetes prediction. Data quality is evaluated by comparing correlation matrices, the propensity score mean-squared error (pMSE) for general utility, and F1-scores for downstream tasks as a specific utility metric, using training on synthetic data and testing on real data.

RESULTS: Our simulation study, supplemented with real-world data analyses, shows that the statistical methods copula and synthpop consistently outperform deep learning approaches across various sample sizes and correlation complexities, with synthpop being the most effective. Deep learning methods, including large LLMs, show mixed performance, particularly with smaller datasets or limited training epochs. LLMs often struggle to replicate numerical dependencies effectively. In contrast, methods like tvae with 10,000 epochs perform comparably well. On the body performance dataset, copulagan achieves the best performance in terms of pMSE. The results also highlight that model utility depends more on the relative correlations between features and the target variable than on the absolute magnitude of correlation matrix differences.

CONCLUSIONS: Statistical methods, particularly synthpop, demonstrate superior robustness and utility preservation for synthetic tabular data compared with deep learning approaches. Copula methods show potential but face limitations with integer variables. Deep Learning methods underperform in this context. Overall, these findings underscore the dominance of statistical methods for synthetic data generation for tabular data, while highlighting the niche potential of deep learning approaches for highly complex datasets, provided adequate resources and tuning.

PMID:40112290 | DOI:10.2196/65729

PLoS One. 2025 Mar 20;20(3):e0319859. doi: 10.1371/journal.pone.0319859. eCollection 2025.

ABSTRACT

Deep Neural Networks (DNN) have achieved state-of-the-art performance in medical image classification and are increasingly being used for disease diagnosis. However, these models are quite complex and that necessitates the need to reduce the model complexity for their use in low-power edge applications that are becoming common. The model complexity reduction techniques in most cases comprise of time-consuming operations and are often associated with a loss of model performance in proportion to the model size reduction. In this paper, we propose a simplified model complexity reduction technique based on reducing the number of channels for any DNN and demonstrate the complexity reduction approaches for the ResNet-50 model integration in low-power devices. The model performance of the proposed models was evaluated for multiclass classification of CXR images, as normal, pneumonia, and COVID-19 classes. We demonstrate successive size reductions down to 75%, 87%, and 93% reduction with an acceptable classification performance reduction of 0.5%, 0.5%, and 0.8% respectively. We also provide the results for the model generalization, and visualization with Grad-CAM at an acceptable performance and interpretable level. In addition, a theoretical VLSI architecture for the best performing architecture has been presented.

PMID:40112278 | DOI:10.1371/journal.pone.0319859

Adv Sci (Weinh). 2025 Mar 20:e2413786. doi: 10.1002/advs.202413786. Online ahead of print.

ABSTRACT

Mental disorders are a representative type of brain disorder, including anxiety, major depressive depression (MDD), and autism spectrum disorder (ASD), that are caused by multiple etiologies, including genetic heterogeneity, epigenetic dysregulation, and aberrant morphological and biochemical conditions. Psychedelic drugs such as psilocybin and lysergic acid diethylamide (LSD) have been renewed as fascinating treatment options and have gradually demonstrated potential therapeutic effects in mental disorders. However, the multifaceted conditions of psychiatric disorders resulting from individuality, complex genetic interplay, and intricate neural circuits impact the systemic pharmacology of psychedelics, which disturbs the integration of mechanisms that may result in dissimilar medicinal efficiency. The precise prescription of psychedelic drugs remains unclear, and advanced approaches are needed to optimize drug development. Here, recent studies demonstrating the diverse pharmacological effects of psychedelics in mental disorders are reviewed, and emerging perspectives on structural function, the microbiota-gut-brain axis, and the transcriptome are discussed. Moreover, the applicability of deep learning is highlighted for the development of drugs on the basis of big data. These approaches may provide insight into pharmacological mechanisms and interindividual factors to enhance drug discovery and development for advanced precision medicine.

PMID:40112231 | DOI:10.1002/advs.202413786

PLoS One. 2025 Mar 20;20(3):e0319540. doi: 10.1371/journal.pone.0319540. eCollection 2025.

ABSTRACT

Under the increasing pressure of global climate change, water conservation (WC) in semi-arid regions is experiencing unprecedented levels of stress. WC involves complex, nonlinear interactions among ecosystem components like vegetation, soil structure, and topography, complicating research. This study introduces a novel approach combining InVEST modeling, spatiotemporal transfer of Water Conservation Reserves (WCR), and deep learning to uncover regional WC patterns and driving mechanisms. The InVEST model evaluates Xiong'an New Area's WC characteristics from 2000 to 2020, showing a 74% average increase in WC depth with an inverted "V" spatial distribution. Spatiotemporal analysis identifies temporal changes, spatial patterns of WCR and land use, and key protection areas, revealing that the WCR in Xiong'an New Area primarily shifts from the lowest WCR areas to lower WCR areas. The potential enhancement areas of WCR are concentrated in the northern region. Deep learning quantifies data complexity, highlighting critical factors like land use, precipitation, and drought influencing WC. This detailed approach enables the development of personalized WC zones and strategies, offering new insights into managing complex spatial and temporal WC data.

PMID:40112018 | DOI:10.1371/journal.pone.0319540

PLoS One. 2025 Mar 20;20(3):e0316367. doi: 10.1371/journal.pone.0316367. eCollection 2025.

ABSTRACT

Extreme heat waves are causing widespread concern for comprehensive studies on their ecological and societal implications. With the ongoing rise in global temperatures, precise forecasting of heatwaves becomes increasingly crucial for proactive planning and ensuring safety. This study investigates the efficacy of deep learning (DL) models, including Artificial Neural Network (ANN), Conolutional Neural Network (CNN) and Long-Short Term Memory (LSTM), using five years of meteorological data from Pakistan Meteorological Department (PMD), by integrating Explainable AI (XAI) techniques to enhance the interpretability of models. Although Weather forecasting has advanced in predicting sunshine, rain, clouds, and general weather patterns, the study of extreme heat, particularly using advanced computer models, remains largely unexplored, overlooking this gap risks significant disruptions in daily life. Our study addresses this gap by collecting five years of weather dataset and developing a comprehensive framework integrating DL and XAI models for extreme heat prediction. Key variables such as temperature, pressure, humidity, wind, and precipitation are examined. Our findings demonstrate that the LSTM model outperforms others with a lead time of 1-3 days and minimal error metrics, achieving an accuracy of 96.2%. Through the utilization of SHAP and LIME XAI methods, we elucidate the significance of humidity and maximum temperature in accurately predicting extreme heat events. Overall, this study emphasizes how important it is to investigate intricate DL models that integrate XAI for the prediction of extreme heat. Making these models understood allows us to identify important parameters, improving heatwave forecasting accuracy and guiding risk-reduction strategies.

PMID:40111979 | DOI:10.1371/journal.pone.0316367

PLoS One. 2025 Mar 20;20(3):e0313946. doi: 10.1371/journal.pone.0313946. eCollection 2025.

ABSTRACT

This study aims to explore a data-driven cultural background fusion method to improve the accuracy of environmental art image classification. A novel Dual Kernel Squeeze and Excitation Network (DKSE-Net) model is proposed for the complex cultural background and diverse visual representation in environmental art images. This model combines the advantages of adaptive adjustment of receptive fields using the Selective Kernel Network (SKNet) and the characteristics of enhancing channel features using the Squeeze and Excitation Network (SENet). Constructing a DKSE module can comprehensively extract the global and local features of the image. The DKSE module adopts various techniques such as dilated convolution, L2 regularization, Dropout, etc. in the multi-layer convolution process. Firstly, dilated convolution is introduced into the initial layer of the model to enhance the original art image's feature capture ability. Secondly, the pointwise convolution is constrained by L2 regularization, thus enhancing the accuracy and stability of the convolution. Finally, the Dropout technology randomly discards the feature maps before and after global average pooling to prevent overfitting and improve the model's generalization ability. On this basis, the Rectified Linear Unit activation function and depthwise convolution are introduced after the second layer convolution, and batch normalization is performed to improve the efficiency and robustness of feature extraction. The experimental results indicate that the proposed DKSE-Net model significantly outperforms traditional Convolutional Neural Networks (CNNs) and other existing state-of-the-art models in the task of environmental art image classification. Specifically, the DKSE-Net model achieves a classification accuracy of 92.7%, 3.5 percentage points higher than the comparative models. Moreover, when processing images with complex cultural backgrounds, DKSE-Net can effectively integrate different cultural features, achieving a higher classification accuracy and stability. This enhancement in performance provides an important reference for image classification research based on the fusion of cultural backgrounds and demonstrates the broad potential of deep learning technology in the environmental art field.

PMID:40111961 | DOI:10.1371/journal.pone.0313946

IEEE Trans Neural Netw Learn Syst. 2025 Mar 20;PP. doi: 10.1109/TNNLS.2025.3543926. Online ahead of print.

ABSTRACT

This article presents a unified framework for dynamics modeling and control design using deep learning, focusing on incorporating prior side information on stabilizability. Control theory provides systematic techniques for designing feedback systems while ensuring fundamental properties such as stabilizability, which are crucial for practical control applications. However, conventional data-driven approaches often overlook or struggle to explicitly incorporate such control properties into learned models. To address this, we introduce a novel neural network (NN)-based approach that concurrently learns the system dynamics, a stabilizing feedback controller, and a Lyapunov function for the closed-loop system, thus explicitly guaranteeing stabilizability in the learned model. Our proposed deep learning framework is versatile and applicable across a wide range of control problems, including safety control, -gain control, passivation, and solutions to Hamilton-Jacobi inequalities. By embedding stabilizability as a core property within the learning process, our method allows for the development of learned models that are not only data-driven but also grounded in control-theoretic guarantees, greatly enhancing their utility in real-world control applications. This article includes examples that demonstrate the effectiveness of this approach, showcasing the stability and control performance improvements achieved in various control scenarios. The methods proposed in this article can be easily applied to modeling without control design. The code has been open-sourced and is available at https://github.com/kashctrl/Deep_Stabilizable_Models.

PMID:40111782 | DOI:10.1109/TNNLS.2025.3543926

IEEE J Biomed Health Inform. 2025 Mar 20;PP. doi: 10.1109/JBHI.2025.3553217. Online ahead of print.

ABSTRACT

Deep learning offers efficient solutions for drug-target interaction prediction, but current methods often fail to capture the full complexity of multi-modal data (i.e. sequence, graphs, and three-dimensional structures), limiting both performance and generalization. Here, we present UnitedDTA, a novel explainable deep learning framework capable of integrating multi-modal biomolecule data to improve the binding affinity prediction, especially for novel (unseen) drugs and targets. UnitedDTA enables automatic learning unified discriminative representations from multi-modality data via contrastive learning and cross-attention mechanisms for cross-modality alignment and integration. Comparative results on multiple benchmark datasets show that UnitedDTA significantly outperforms the state-of-the-art drug-target affinity prediction methods and exhibits better generalization ability in predicting unseen drug-target pairs. More importantly, unlike most "black-box" deep learning methods, our well-established model offers better interpretability which enables us to directly infer the important substructures of the drug-target complexes that influence the binding activity, thus providing the insights in unveiling the binding preferences. Moreover, by extending UnitedDTA to other downstream tasks (e.g. molecular property prediction), we showcase the proposed multi-modal representation learning is capable of capturing the latent molecular representations that are closely associated with the molecular property, demonstrating the broad application potential for advancing the drug discovery process.

PMID:40111772 | DOI:10.1109/JBHI.2025.3553217

Waste Manag Res. 2025 Mar 20:734242X241313286. doi: 10.1177/0734242X241313286. Online ahead of print.

ABSTRACT

As the Internet of things (IoT) continues to transform modern technologies, innovative applications in waste management and air pollution monitoring are becoming critical for sustainable development. In this manuscript, a novel smart waste management (SWM) and air pollution forecasting (APF) system is proposed by leveraging IoT sensors and the fully Elman neural network (FENN) model, termed as SWM-APF-IoT-FENN. The system integrates real-time data from waste and air quality sensors including weight, trash level, odour and carbon monoxide (CO) that are collected from smart bins connected to a Google Cloud Server. Here, the MaxAbsScaler is employed for data normalization, ensuring consistent feature representation. Subsequently, the atmospheric contaminants surrounding the waste receptacles were observed using a FENN model. This model is utilized to predict the atmospheric concentration of CO and categorize the bin status as filled, half-filled and unfilled. Moreover, the weight parameter of the FENN model is tuned using the secretary bird optimization algorithm for better prediction results. The implementation of the proposed methodology is done in Python tool, and the performance metrics are analysed. Experimental results demonstrate significant improvements in performance, achieving 15.65%, 18.45% and 21.09% higher accuracy, 18.14%, 20.14% and 24.01% higher F-Measure, 23.64%, 24.29% and 29.34% higher False Acceptance Rate (FAR), 25.00%, 27.09% and 31.74% higher precision, 20.64%, 22.45% and 28.64% higher sensitivity, 26.04%, 28.65% and 32.74% higher specificity, 9.45%, 7.38% and 4.05% reduced computational time than the conventional approaches such as Elman neural network, recurrent artificial neural network and long short-term memory with gated recurrent unit, respectively. Thus, the proposed method offers a streamlined, efficient framework for real-time waste management and pollution forecasting, addressing critical environmental challenges.

PMID:40111379 | DOI:10.1177/0734242X241313286

Med Phys. 2025 Mar 20. doi: 10.1002/mp.17763. Online ahead of print.

ABSTRACT

BACKGROUND: Accurate segmentation of diffuse large B-cell lymphoma (DLBCL) lesions is challenging due to their complex patterns in medical imaging. Traditional methods often struggle to delineate these lesions accurately.

OBJECTIVE: This study aims to develop a precise segmentation method for DLBCL using 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) and computed tomography (CT) images.

METHODS: We propose a 3D segmentation method based on an encoder-decoder architecture. The encoder incorporates a dual-branch design based on the shifted window transformer to extract features from both PET and CT modalities. To enhance feature integration, we introduce a multi-scale information fusion (MSIF) module that performs multi-scale feature fusion using cross-attention mechanisms with a shifted window framework. A gated neural network within the MSIF module dynamically adjusts feature weights to balance the contributions from each modality. The model is optimized using the dice similarity coefficient (DSC) loss function, minimizing discrepancies between the model prediction and ground truth. Additionally, we computed the total metabolic tumor volume (TMTV) and performed statistical analyses on the results.

RESULTS: The model was trained and validated on a private dataset of 165 DLBCL patients and a publicly available dataset (autoPET) containing 145 PET/CT scans of lymphoma patients. Both datasets were analyzed using five-fold cross-validation. On the private dataset, our model achieved a DSC of 0.7512, sensitivity of 0.7548, precision of 0.7611, an average surface distance (ASD) of 3.61 mm, and a Hausdorff distance at the 95th percentile (HD95) of 15.25 mm. On the autoPET dataset, the model achieved a DSC of 0.7441, sensitivity of 0.7573, precision of 0.7427, ASD of 5.83 mm, and HD95 of 21.27 mm, outperforming state-of-the-art methods (p < 0.05, t-test). For TMTV quantification, Pearson correlation coefficients of 0.91 (private dataset) and 0.86 (autoPET) were observed, with R2 values of 0.89 and 0.75, respectively. Extensive ablation studies demonstrated the MSIF module's contribution to enhanced segmentation accuracy.

CONCLUSION: This study presents an effective automatic segmentation method for DLBCL that leverages the complementary strengths of PET and CT imaging. The method demonstrates robust performance on both private and publicly available datasets, ensuring its reliability and generalizability. Our method provides clinicians with more precise tumor delineation, which can improve the accuracy of diagnostic interpretations and assist in treatment planning for DLBCL patients. The code for the proposed method is available at https://github.com/chenzhao2023/lymphoma_seg.

PMID:40111352 | DOI:10.1002/mp.17763

Med Phys. 2025 Mar 20. doi: 10.1002/mp.17752. Online ahead of print.

ABSTRACT

BACKGROUND: Deep learning (DL)-based systems have not yet been broadly implemented in clinical practice, in part due to unknown robustness across multiple imaging protocols.

PURPOSE: To this end, we aim to evaluate the performance of several previously developed DL-based models, which were trained to distinguish idiopathic pulmonary fibrosis (IPF) from non-IPF among interstitial lung disease (ILD) patients, under standardized reference CT imaging protocols. In this study, we utilized CT scans from non-IPF ILD subjects, acquired using various imaging protocols, to assess the model performance.

METHODS: Three DL-based models, including one 2D and two 3D models, have been previously developed to classify ILD patients into IPF or non-IPF based on chest CT scans. These models were trained on CT image data from 389 IPF and 700 non-IPF ILD patients, retrospectively, obtained from five multicenter studies. For some patients, multiple CT scans were acquired (e.g., one at inhalation and one at exhalation) and/or reconstructed (e.g., thin slice and/or thick slice). Thus, for each patient, one CT image dataset was selected to be used in the construction of the classification model, so the parameters of that data set serve as the reference conditions. In one non-IPF ILD study, due to its specific study protocol, many patients had multiple CT image data sets that were acquired under both prone and supine positions and/or reconstructed under different imaging parameters. Therefore, to assess the robustness of the previously developed models under different (e.g., non-reference) imaging protocols, we identified 343 subjects from this study who had CT data from both the reference condition (used in model construction) and non-reference conditions (e.g., evaluation conditions), which we used in this model evaluation analysis. We reported the specificities from three model under the non-reference conditions. Generalized linear mixed effects model (GLMM) was utilized to identify the significant CT technical and clinical parameters that were associated with getting inconsistent diagnostic results between reference and evaluation conditions. Selected parameters include effective tube current-time product (known as "effective mAs"), reconstruction kernels, slice thickness, patient orientation (prone or supine), CT scanner model, and clinical diagnosis. Limitations include the retrospective nature of this study.

RESULTS: For all three DL models, the overall specificity of the previously trained IPF diagnosis model decreased (p < 0.05 for two out of three models). GLMM further suggests that for at least one out of three models, mean effective mAs across the scan is the key factor that leads to the decrease in model predictive performance (p < 0.001); the difference of mean effective mAs between the reference and evaluation conditions (p = 0.03) and slice thickness (3 mm; p = 0.03) are flagged as significant factors for one out of three models; other factors are not statistically significant (p > 0.05).

CONCLUSION: Preliminary findings demonstrated the lack of robustness of IPF diagnosis model when the DL-based model is applied to CT series collected under different imaging protocols, which indicated that care should be taken as to the acquisition and reconstruction conditions used when developing and deploying DL models into clinical practice.

PMID:40111345 | DOI:10.1002/mp.17752

J Phys Chem Lett. 2025 Mar 20:3165-3176. doi: 10.1021/acs.jpclett.4c03650. Online ahead of print.

ABSTRACT

Interpretability is fundamental in the precise identification of single-molecule charge transport, and its absence in deep learning models is currently the major barrier to the usage of such powerful algorithms in the field. Here, we have pioneered a novel identification method employing fusion attention-based deep learning technologies. Central to our approach is the innovative neural network architecture, SingleFACNN, which integrates convolutional neural networks with a fusion of multihead self-attention and spatial attention mechanisms. Our findings demonstrate that SingleFACNN accurately classifies the three-type and four-type STM-BJ data sets, leveraging the convolutional layers' robust feature extraction and the attention layers' capacity to capture long-range interactions. Through comprehensive gradient-weighted class activation mapping and ablation studies, we identified and analyzed the critical features impacting classification outcomes with remarkable accuracy, thus enhancing the interpretability of our deep learning model. Furthermore, SingleFACNN's application was extended to mixed samples with varying proportions, achieving commendable prediction performance at low computational cost. Our study underscores the potential of SingleFACNN in advancing the interpretability and credibility of deep learning applications in single-molecule charge transport, opening new avenues for single-molecule detection in complex systems.

PMID:40111072 | DOI:10.1021/acs.jpclett.4c03650

J Chem Inf Model. 2025 Mar 20. doi: 10.1021/acs.jcim.5c00130. Online ahead of print.

ABSTRACT

Accurately predicting the effect of mutations on protein-protein interactions (PPIs) is essential for understanding the protein structure and function, as well as providing insights into disease-causing mechanisms. Many recent popular approaches based on the three-dimensional structure of proteins have been proposed to predict the changes in binding affinity caused by mutations, i.e. ΔΔG. However, how to effectively use the structural information to comprehensively exploit complex interactions within proteins and integrate multisource features remains a significant challenge. In this study, we propose SFM-Net, a powerful deep learning model constructed with GNN-based multiway feature extractors and a new context-aware selective fusion module that jointly leverages the sequence, structural, and evolutionary information. Such design enables SFM-Net to effectively and selectively use features from different sources to facilitate binding affinity change prediction. Benchmarking experiments and targeted ablation studies illustrate the effectiveness and robustness of our method for improving the binding affinity change prediction.

PMID:40111004 | DOI:10.1021/acs.jcim.5c00130

Aust J Rural Health. 2025 Apr;33(2):e70031. doi: 10.1111/ajr.70031.

ABSTRACT

OBJECTIVE: Diabetic retinopathy (DR) screening rates are poor in remote Western Australia where communities rely on outdated primary care-based retinal cameras. Deep learning systems (DLS) may improve access to screening, however, require validation in real-world settings. This study describes and evaluates the implementation of a new, mobile DR screening model that incorporates artificial intelligence (AI) into routine care.

DESIGN: Prospective, population-based study.

SETTING: The model was co-designed with local Aboriginal communities and implemented in the remote, Pilbara region of Western Australia. A research officer without formal healthcare qualification performed retinal screening aboard a Mercedes Sprinter Van using an automated retinal camera with integrated AI diagnostics. Patients received their diagnosis on-the-spot and completed an evaluation survey. A remote clinician provided supervision and on-the-spot telehealth consultation for referable disease.

PARTICIPANTS: People with diabetes from the Pilbara region.

MAIN OUTCOME MEASURE(S): Number of people screened, acceptability of AI to patients.

RESULTS: From February to August 2024, DR screening was provided to 9 communities across the Pilbara region. 78 patients provided research consent, of which 56.4% were Aboriginal or Torres Strait Islanders. 10.3% of retinal photos had referable DR and 8.4% of photos were ungradable. 96% of patients were 'Happy with the use of AI'.

CONCLUSION: Our new model for AI-assisted DR screening was culturally safe, acceptable to patients and effective, demonstrating an 11-fold increase in screening rates compared to 2023 Pilbara data. In remote Australian settings, AI-assisted DR screening may overcome historical barriers to service provision and improve minimisation of preventable blindness.

PMID:40110918 | DOI:10.1111/ajr.70031

SAR QSAR Environ Res. 2025 Mar 20:1-26. doi: 10.1080/1062936X.2025.2475407. Online ahead of print.

ABSTRACT

P38α has been identified as a key target for drug design to treat a wide range of diseases. In this study, multiple independent Gaussian accelerated molecular dynamics (GaMD) simulations, deep learning (DL), and the molecular mechanics generalized Born surface area (MM-GBSA) method were used to investigate the binding mechanism of inhibitors (SB2, SK8, and BMU) to DFG-in and DFG-out P38α and clarify the effect of conformational differences in P38α on inhibitor binding. GaMD trajectory-based DL effectively identified important functional domains, such as the A-loop and N-sheet. Post-processing analysis on GaMD trajectories showed that binding of the three inhibitors profoundly affected the structural flexibility and dynamical behaviour of P38α situated at the DFG-in and DFG-out states. The MM-GBSA calculations not only revealed that differences in the binding ability of inhibitors are affected by DFG-in and DFG-out conformations of P38α, but also confirmed that van der Waals interactions are the primary force driving inhibitor-P38α binding. Residue-based free energy estimation identifies hot spots of inhibitor-P38α binding across DFG-in and DFG-out conformations, providing potential target sites for drug design towards P38α. This work is expected to offer valuable theoretical support for the development of selective inhibitors of P38α family members.

PMID:40110797 | DOI:10.1080/1062936X.2025.2475407

Oncologist. 2025 Mar 10;30(3):oyaf013. doi: 10.1093/oncolo/oyaf013.

ABSTRACT

BACKGROUND: Accurate prediction of early recurrence (ER) is essential to improve the prognosis of patients with hepatocellular carcinoma (HCC) underwent thermal ablation (TA). Therefore, a deep learning model system using longitudinal magnetic resonance imaging (MRI) was developed to predict ER of patients with HCC.

METHODS: From 2014, April to 2017, May, a total of 289 eligible patients with HCC underwent TA were retrospectively enrolled from 3 hospitals and assigned into one training cohort (n = 254) and one external testing cohort (n = 35). Two deep learning models (Pre and PrePost) were developed using the pre-operative MRI and longitudinal MRI (pre- and post-operative) to predict ER for the patients with HCC after TA, respectively. Then, an integrated model (DL_Clinical) incorporating PrePost model signature and clinical variables was built for post-ablation ER risk stratification for the patients with HCC.

RESULTS: In the external testing cohort, the area under the receiver operating characteristic curve (AUC) of the DL_Clinical model was better than that of the Clinical (0.740 vs 0.571), Pre (0.740 vs 0.648), and PrePost model (0.740 vs 0.689). Additionally, there was a significant difference in RFS between the high- and low-risk groups which were divided by the DL_Clinical model (P = .04).

CONCLUSIONS: The PrePost model developed using longitudinal MRI showed outstanding performance for predicting post-ablation ER of HCC. The DL_Clinical model could stratify the patients into high- and low-risk groups, which may help physicians in treatment and surveillance strategy selection in clinical practice.

PMID:40110765 | DOI:10.1093/oncolo/oyaf013

ACS Appl Mater Interfaces. 2025 Mar 20. doi: 10.1021/acsami.4c19494. Online ahead of print.

ABSTRACT

The emergence of inverse design approaches leveraging generative models offers a promising avenue for thermoelectric material design. However, these models heavily depend on diverse training data, and current thermoelectric data sets are limited, primarily encompassing group IV-VI materials operating within moderate temperature ranges. This constraint poses a significant challenge in the pursuit of materials with high thermoelectric figure of merit (zT) through generative modeling. Our study introduces an inverse design model tailored for the constrained thermoelectric materials data set. By augmenting the data with 2000 entries from the experimental literature and incorporating a generative model featuring a diversity loss function and residual network (ResNet) architecture to enhance complexity, our approach has been trained to systematically generate high-zT thermoelectric materials across various temperature ranges. Under predefined high-zT criteria, our deep generative model successfully predicted 100 doped materials with zT values exceeding 1.0. Furthermore, this research analyzes density of states (DOS) plots for the generated materials, identifying 25 unreported previously potential thermoelectric candidates in the material database. Notably, we experimentally validated the synthesis of Mg3.1Sb0.5Bi1.497Te0.003, a representative thermoelectric material from the Mg3(Sb, Bi)2 family suitable for room temperature applications. This validation underscores the efficacy of our model in exploring and discovering novel thermoelectric materials.

PMID:40110715 | DOI:10.1021/acsami.4c19494

Technol Health Care. 2024 Dec 16:9287329241291334. doi: 10.1177/09287329241291334. Online ahead of print.

ABSTRACT

BackgroundThe complexity and diversity of brain activity patterns make it difficult to accurately diagnose neurological disorders such epilepsy, Parkinson's disease, schizophrenia, stroke, and Alzheimer's disease. Integrated and effective analysis of multiple data sources is often beyond the scope of traditional diagnostic procedures. With the use of multi-modal data, recent developments in neural network approaches present encouraging opportunities for raising diagnostic accuracy.ObjectivesA novel approach has been proposed toward the integration of different Nondestructive Evaluation data with EEG signals for improving the diagnosis of neurological disorders such as stroke, epilepsy, Parkinson's disease, and schizophrenia, by leveraging advanced neural network techniques in order to improve the identification and correlation of shared latent features across heterogeneous NDE datasets.MethodsWe determined the 2D scalogram images using a specific encoder-decoder neural network after transforming the EEG signals using wavelet signal processing. Several NDE data types can be easily integrated for thorough analysis due to this network's ability to extract and correlate important aspects from each form of data. Aiming to uncover common patterns indicating of neurological disorders, the technique was evaluated on datasets containing EEG signals and corresponding NDE data.ResultsOur method demonstrated a significant improvement in diagnostic accuracy and efficiency. The encoder-decoder network effectively identified shared latent features across the heterogeneous NDE datasets, leading to more precise and reliable diagnoses. The fusion of multi-modality NDE data with EEG signals provided a robust framework for the automatic identification of multiple neurological disorders.ConclusionsThis innovative approach represents a substantial advancement in the field of neurological disorder diagnosis. By integrating diverse NDE data with EEG signals through advanced neural network techniques, we have developed a method that enhances the accuracy and efficiency of diagnosing multiple neurological conditions. This fusion of multi-modality data has the potential to revolutionize current diagnostic practices in neurology, paving the way for more precise and automated identification of neurological disorders.

PMID:40110612 | DOI:10.1177/09287329241291334

Front Behav Neurosci. 2025 Mar 5;19:1549666. doi: 10.3389/fnbeh.2025.1549666. eCollection 2025.

ABSTRACT

Social hierarchy refers to the set of social ranks in a group of animals where individuals can gain priority access to resources through repeated social interactions. Key mechanisms involved in this process include conflict, social negotiation, prior experience, and physical advantages. The establishment and maintenance of social hierarchies not only promote group stability and well-being but also shape individual social behaviors by fostering cooperation and reducing conflict. Existing research indicates that social hierarchy is closely associated with immune responses, neural regulation, metabolic processes, and endocrine functions. These physiological systems collectively modulate an individual's sensitivity to stress and influence adaptive responses, thereby playing a critical role in the development of psychiatric disorders such as depression and anxiety. This review summarizes the primary behavioral methods used to assess social dominance in mice, evaluates their applicability and limitations, and discusses potential improvements. Additionally, it explores the underlying neural mechanisms associated with these methods to deepen our understanding of their biological basis. By critically assessing existing methodologies and proposing refinements, this study aims to provide a systematic reference framework and methodological guidance for future research, facilitating a more comprehensive exploration of the neural mechanisms underlying social behavior. The role of sex differences in social hierarchy formation remains underexplored. Most studies focus predominantly on males, while the distinct social strategies and physiological mechanisms of females are currently overlooked. Future studies should place greater emphasis on evaluating social hierarchy in female mice to achieve a more comprehensive understanding of sex-specific social behaviors and their impact on group structure and individual health. Advances in automated tracking technologies may help address this gap by improving behavioral assessments in female mice. Future research may also benefit from integrating physiological data (e.g., hormone levels) to gain deeper insights into the relationships between social status, stress regulation, and mental health. Additionally, developments in artificial intelligence and deep learning could enhance individual recognition and behavioral analysis, potentially reducing reliance on chemical markers or implanted devices.

PMID:40110389 | PMC:PMC11920152 | DOI:10.3389/fnbeh.2025.1549666

Front Plant Sci. 2025 Mar 5;16:1538051. doi: 10.3389/fpls.2025.1538051. eCollection 2025.

ABSTRACT

The removal of non-tobacco related materials (NTRMs) is crucial for improving tobacco product quality and consumer safety. Traditional NTRM detection methods are labor-intensive and inefficient. This study proposes a novel approach for real-time NTRM detection using hyperspectral imaging (HSI) and an enhanced YOLOv8 model, named Dual-branch-YOLO-Tobacco (DBY-Tobacco). We created a dataset of 1,000 images containing 4,203 NTRMs by using a hyperspectral camera, SpectraEye (SEL-24), with a spectral range of 400-900 nm. To improve processing efficiency of HSIs data, three characteristic wavelengths (580nm, 680nm, and 850nm) were extracted by analyzing the weighted coefficients of the principal components. Then the pseudo color image fusion and decorrelation contrast stretch methods were applied for image enhancement. The DBY-Tobacco model features a dual-branch backbone network and a BiFPN-Efficient-Lighting-Feature-Pyramid-Network (BELFPN) module for effective feature fusion. Experimental results demonstrate that the DBY-Tobacco model achieves high performance metrics, including an F1 score of 89.7%, mAP@50 of 92.8%, mAP@50-95 of 73.7%, and a processing speed of 151 FPS, making it suitable for real-time applications in dynamic production environments. The study highlights the potential of combining HSI with advanced deep learning techniques for improving tobacco product quality and safety. Future work will focus on addressing limitations such as stripe noise in HSI and expanding the detection to other types of NTRMs. The dataset and code are available at: https://github.com/Ikaros-sc/DBY-Tobacco.

PMID:40110354 | PMC:PMC11921890 | DOI:10.3389/fpls.2025.1538051