Comput Methods Programs Biomed. 2025 Mar 15;264:108726. doi: 10.1016/j.cmpb.2025.108726. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: Single-cell imaging plays a key role in various fields, including drug development, disease diagnosis, and personalized medicine. To obtain multi-modal information from a single-cell image, especially for label-free cells, this study develops modal expansion cytometry for label-free single-cell analysis.

METHODS: The study utilizes a deep learning-based architecture to expand single-mode light scattering images into multi-modality images, including bright-field (non-fluorescent) and fluorescence images, for label-free single-cell analysis. By combining adversarial loss, L1 distance loss, and VGG perceptual loss, a new network optimization method is proposed. The effectiveness of this method is verified by experiments on simulated images, standard spheres of different sizes, and multiple cell types (such as cervical cancer and leukemia cells). Additionally, the capability of this method in single-cell analysis is assessed through multi-modal cell classification experiments, such as cervical cancer subtypes.

RESULTS: This is demonstrated by using both cervical cancer cells and leukemia cells. The expanded bright-field and fluorescence images derived from the light scattering images align closely with those obtained through conventional microscopy, showing a contour ratio near 1 for both the whole cell and its nucleus. Using machine learning, the subtyping of cervical cancer cells achieved 92.85 % accuracy with the modal expansion images, which represents an improvement of nearly 20 % over single-mode light scattering images.

CONCLUSIONS: This study demonstrates the light scattering imaging modal expansion cytometry with deep learning has the capability to expand the single-mode light scattering image into the artificial multimodal images of label-free single cells, which not only provides the visualization of cells but also helps for the cell classification, showing great potential in the field of single-cell analysis such as cancer cell diagnosis.

PMID:40112688 | DOI:10.1016/j.cmpb.2025.108726

Comput Methods Programs Biomed. 2025 Mar 15;264:108722. doi: 10.1016/j.cmpb.2025.108722. Online ahead of print.

ABSTRACT

BACKGROUND: Atrial fibrillation (AF) is the most common cardiac arrhythmia, affecting up to 2 % of the population. Catheter ablation is a promising treatment for AF, particularly for paroxysmal AF patients, but it often has high recurrence rates. Developing in silico models of patients' atria during the ablation procedure using cardiac MRI data may help reduce these rates.

OBJECTIVE: This study aims to develop an effective automated deep learning-based segmentation pipeline by compiling a specialized dataset and employing standardized labeling protocols to improve segmentation accuracy and efficiency. In doing so, we aim to achieve the highest possible accuracy and generalization ability while minimizing the burden on clinicians involved in manual data segmentation.

METHODS: We collected LGE-MRI data from VMRC and the cDEMRIS database. Two specialists manually labeled the data using standardized protocols to reduce subjective errors. Neural network (nnU-Net and smpU-Net++) performance was evaluated using statistical tests, including sensitivity and specificity analysis. A new database of LGE-MRI images, based on manual segmentation, was created (VMRC).

RESULTS: Our approach with consistent labeling protocols achieved a Dice coefficient of 92.4 % ± 0.8 % for the cavity and 64.5 % ± 1.9 % for LA walls. Using the pre-trained RIFE model, we attained a Dice score of approximately 89.1 % ± 1.6 % for atrial LGE-MRI imputation, outperforming classical methods. Sensitivity and specificity values demonstrated substantial enhancement in the performance of neural networks trained with the new protocol.

CONCLUSION: Standardized labeling and RIFE applications significantly improved machine learning tool efficiency for constructing 3D LA models. This novel approach supports integrating state-of-the-art machine learning methods into broader in silico pipelines for predicting ablation outcomes in AF patients.

PMID:40112687 | DOI:10.1016/j.cmpb.2025.108722

Neural Netw. 2025 Mar 13;187:107368. doi: 10.1016/j.neunet.2025.107368. Online ahead of print.

ABSTRACT

In this paper, we propose a novel neural architecture search (NAS) method called MAPOCNN, which leverages an enhanced version of the Artificial Protozoa Optimizer (APO) to optimize the architecture of Convolutional Neural Networks (CNNs). The APO is known for its rapid convergence, high stability, and minimal parameter involvement. To further improve its performance, we introduce MAPO (Modified Artificial Protozoa Optimizer), which incorporates the phototaxis behavior of protozoa. This addition helps mitigate the risk of premature convergence, allowing the algorithm to explore a broader range of possible CNN architectures and ultimately identify more optimal solutions. Through rigorous experimentation on benchmark datasets, including Rectangle and Mnist-random, we demonstrate that MAPOCNN not only achieves faster convergence times but also performs competitively when compared to other state-of-the-art NAS algorithms. The results highlight the effectiveness of MAPOCNN in efficiently discovering CNN architectures that outperform existing methods in terms of both speed and accuracy. This work presents a promising direction for optimizing deep learning architectures using biologically inspired optimization techniques.

PMID:40112636 | DOI:10.1016/j.neunet.2025.107368

Thorax. 2025 Mar 20:thorax-2023-221063. doi: 10.1136/thorax-2023-221063. Online ahead of print.

ABSTRACT

BACKGROUND: Long-term oxygen therapy (LTOT) improves survival in patients with chronic severe resting hypoxaemia, but effects on hospitalisation are unknown. This study evaluated the potential impact of starting LTOT on acute exacerbation and hospital burden in patients with chronic obstructive pulmonary disease (COPD), interstitial lung disease (ILD) and pulmonary hypertension (PH).

METHODS: Longitudinal analysis of consecutive patients in the population-based Swedish DISCOVERY cohort who started LTOT between 2000 and 2018 with a follow-up duration≥3 months. Total and hospitalised acute exacerbations of the underlying disease, all-cause hospitalisations, and all-cause outpatient visits were annualised and compared between the year before and after LTOT initiation for each disease cohort, and by hypercapnic status in patients with COPD.

RESULTS: Patients with COPD (n=10 134) had significant reduction in annualised rates of total and hospitalised acute exacerbations, as well as all-cause hospitalisations, following LTOT initiation, with increment in those with ILD (n=2507) and PH (n=850). All-cause outpatient visits increased across all cohorts following LTOT initiation. Similar findings were observed in patients with hypercapnic and non-hypercapnic COPD. Sensitivity analyses of patients with 12 months of follow-up showed reduced acute exacerbations and all-cause hospitalisations in the ILD and PH cohorts.

CONCLUSION: LTOT is associated with reduced rates of both total and hospitalised acute exacerbations and all-cause hospitalisations in patients with COPD, as well as patients with ILD and PH with 12 months of follow-up. There is increased all-cause outpatient visits in all disease groups following LTOT initiation.

PMID:40113248 | DOI:10.1136/thorax-2023-221063

Bioorg Chem. 2025 Mar 11;159:108360. doi: 10.1016/j.bioorg.2025.108360. Online ahead of print.

ABSTRACT

Idiopathic pulmonary fibrosis (IPF) is a progressive, irreversible, and fatal pulmonary disease. Owing to its complex pathogenesis and lack of effective treatment, patients have a short survival time after diagnosis. Although pirfenidone and nintedanib can mitigate declines in lung function, neither has stopped the progression of IPF nor significantly improved long-term survival in patients. HDAC6 inhibitors have been reported to inhibit TGF-β1-induced collagen expression to protect mice from pulmonary fibrosis, and this pharmacological mechanism has been supported by immunohistochemical studies of HDAC6 overexpression in IPF lung tissue. In this study, a series of novel derivatives were obtained based on the reported active compounds through the ring closure strategy in scaffold hopping theory. Compound W28 was selected from in vitro screening for better HDAC6 selectivity, and it was used for in-depth pharmacokinetic and pharmacodynamic studies. Detailed molecular docking studies, molecular dynamics (MD) simulations and the structure-activity relationship (SAR) discussion will contribute to guiding the design of new molecules. In further studies, the ability of W28 to inhibit the IPF phenotype was confirmed, and the corresponding pharmacological mechanism was also demonstrated. Moreover, the pharmacokinetic characteristics of W28 were also tested to guide pharmacodynamic studies in vivo, and the therapeutic effect of W28 on bleomycin-induced pulmonary fibrosis in mice was found to be satisfactory. The results reported in this paper may provide a reference for promoting the discovery of new selective HDAC6 inhibitors as drug molecules for the treatment of IPF.

PMID:40112668 | DOI:10.1016/j.bioorg.2025.108360

FEMS Microbiol Ecol. 2025 Mar 20:fiaf028. doi: 10.1093/femsec/fiaf028. Online ahead of print.

ABSTRACT

Environmental factors like diet and antibiotics modulate the gut microbiota in early life. During weaning, gut microbiota progressively diversifies through exposure to non-digestible carbohydrates (NDCs) from diet, while antibiotic perturbations might disrupt this process. Supplementing an infant's diet with prebiotic NDCs may mitigate the adverse effects of antibiotics on gut microbiota development. This study evaluated the influence of supplementation with 2-fucosyllactose (2'-FL), galacto-oligosaccharides (GOS), or isomalto/malto-polysaccharides containing 87% of α(1→6) linkages (IMMP-87), on the recovery of antibiotic-perturbed microbiota. The TIM-2 in vitro colon model inoculated with fecal microbiota of nine-month-old infants was used to simulate the colon of weaning infants exposed to the antibiotics amoxicillin/clavulanate or azithromycin. Both antibiotics induced changes in microbiota composition, with no signs of recovery in azithromycin-treated microbiota within 72 h. Moreover, antibiotic exposure affected microbiota activity, indicated by a low valerate production, and azithromycin treatment was associated with increased succinate production. The IMMP-87 supplementation promoted the compositional recovery of amoxicillin/clavulanate-perturbed microbiota, associated with the recovery of Ruminococcus, Ruminococcus gauvreauii group, and Holdemanella. NDC supplementation did not influence compositional recovery of azithromycin-treated microbiota. Irrespective of antibiotic exposure, supplementation with 2'-FL, GOS, or IMMP-87 enhanced microbiota activity by increasing short-chain fatty acids production (acetate, propionate, and butyrate).

PMID:40113239 | DOI:10.1093/femsec/fiaf028

Lett Appl Microbiol. 2025 Mar 20:ovaf043. doi: 10.1093/lambio/ovaf043. Online ahead of print.

ABSTRACT

Sleep is an essential homeostatic process that undergoes dynamic changes throughout the lifespan, with distinct life stages predisposed to specific sleep pathologies. Similarly, the gut microbiome also varies with age, with different signatures associated with health and disease in the latest decades of life. Emerging research has shown significant cross-talk between the gut microbiota and the brain through several pathways, suggesting the microbiota may influence sleep, though the specific mechanisms remain to be elucidated. Here, we critically examine the existing literature on the potential impacts of the gut microbiome on sleep and how this relationship varies across adulthood. We suggest that age-related shifts in gut microbiome composition and immune function may, in part, drive age-related changes in sleep. We conclude with an outlook on the therapeutic potential of microbiome-targeted interventions aimed at improving sleep across adulthood, particularly for individuals experiencing high stress or with sleep complaints.

PMID:40113228 | DOI:10.1093/lambio/ovaf043

Plant Physiol. 2025 Mar 21:kiaf112. doi: 10.1093/plphys/kiaf112. Online ahead of print.

ABSTRACT

Late blight caused by Phytophthora infestans is a major threat to global potato and tomato production. Sustainable management of late blight requires the development of resistant crop cultivars. This process can be facilitated by high-throughput identification of functional genes involved in late blight pathogenesis. In this study, we generated a high-quality transcriptomic time-course dataset focusing on the initial twenty-four hours of contact between P. infestans and three solanaceous plant species, tobacco(Nicotiana benthamiana), tomato (Solanum lycopersicum), and potato (Solanum tuberosum). Our results demonstrate species-specific transcriptional regulation in early stages of the infection. Transient silencing of putative RIBOSE-5-PHOSPHATE ISOMERASE and HMG-CoA REDUCTASE genes in N. benthamiana lowered plant resistance against P. infestans. Furthermore, heterologous expression of a putative tomato Golgi-localized nucleosugar transporter-encoding gene exacerbated P. infestans infection of N. benthamiana. In comparison, bioassays using transgenic tomato lines showed that the quantitative disease resistance genes were required but insufficient for late blight resistance; genetic knock-out of the susceptibility gene enhanced resistance. The same RNA-seq dataset was exploited to examine the transcriptional landscape of P. infestans and revealed host-specific gene expression patterns in the pathogen. This temporal transcriptomic diversity, in combination with genomic distribution features, identified the P. infestans IPI-B family GLYCINE-RICH PROTEINs as putative virulence factors that promoted disease severity or induced plant tissue necrosis when transiently expressed in N. benthamiana. These functional genes underline the effectiveness of functional gene-mining through a time-course dual RNA-seq approach and provide insight into the molecular interactions between solanaceous plants and P. infestans.

PMID:40112880 | DOI:10.1093/plphys/kiaf112

Cell. 2025 Mar 18:S0092-8674(25)00202-8. doi: 10.1016/j.cell.2025.02.017. Online ahead of print.

ABSTRACT

The relationships of human diversity with biomedical phenotypes are pervasive yet remain understudied, particularly in a single-cell genomics context. Here, we present the Asian Immune Diversity Atlas (AIDA), a multi-national single-cell RNA sequencing (scRNA-seq) healthy reference atlas of human immune cells. AIDA comprises 1,265,624 circulating immune cells from 619 donors, spanning 7 population groups across 5 Asian countries, and 6 controls. Though population groups are frequently compared at the continental level, we found that sub-continental diversity, age, and sex pervasively impacted cellular and molecular properties of immune cells. These included differential abundance of cell neighborhoods as well as cell populations and genes relevant to disease risk, pathogenesis, and diagnostics. We discovered functional genetic variants influencing cell-type-specific gene expression, which were under-represented in non-Asian populations, and helped contextualize disease-associated variants. AIDA enables analyses of multi-ancestry disease datasets and facilitates the development of precision medicine efforts in Asia and beyond.

PMID:40112801 | DOI:10.1016/j.cell.2025.02.017

Zhonghua Yi Xue Za Zhi. 2025 Mar 25;105(12):867-871. doi: 10.3760/cma.j.cn112137-20241024-02396.

ABSTRACT

Type 2 diabetes mellitus and chronic kidney disease (T2DM-CKD) is common in the Chinese population and seriously threatens human health. With the development and application of new drugs, the outcome of T2DM-CKD has been improved in recent years. However, how to combine those drugs effectively and reduce side effects deserves further attention. "Renal triple therapy " (RTT) refers to combined and sequential use of three key medications in treatment of T2DM-CKD, namely renin-angiotensin system inhibitor (RASi), sodium-glucose cotransporter 2 inhibitor (SGLT-2i) and non-steroidal mineralocorticoid receptor antagonist (finerenone), targeting various pathogenic factors in T2DM-CKD. Clinical studies have demonstrated that RTT is superior for protecting the kidney and heart compared with single or dual therapy, and thus improves outcomes of patients with T2DM-CKD. Moreover, RTT can reduce the risk of drug-induced hyperkalemia. Based on research progress at home and abroad and personal clinical experience, this article discusses the origin, theoretical basis, benefits and precautions of RTT in treating T2DM-CKD, aiming to provide a good treatment strategy for primary care physicians and improve the overall level of disease prevention and control.

PMID:40113409 | DOI:10.3760/cma.j.cn112137-20241024-02396

Brief Bioinform. 2025 Mar 4;26(2):bbaf117. doi: 10.1093/bib/bbaf117.

ABSTRACT

The prediction of virus-drug associations (VDAs) is crucial for drug repositioning, contributing to the identification of latent antiviral drugs. In this study, we developed a graph-based integrated Gaussian kernel similarity (GiGs) method for predicting potential VDAs in drug repositioning. The GiGs model comprises three components: (i) collection of experimentally validated VDA information and calculation virus sequence, drug chemical structure, and drug side effect similarity; (ii) integration of viruses and drugs similarity based on the above information and Gaussian interaction profile kernel (GIPK); and (iii) utilization of similarity-constrained weight graph normalization matrix factorization to predict antiviral drugs. The GiGs model enhances correlation matrix quality through the integration of multiple biological data, improves performance via similarity constraints, and prevents overfitting and predicts missing data more accurately through graph regularization. Extensive experimental results indicated that the GiGs model outperforms five other advanced association prediction methods. A case study identified broad-spectrum drugs for treating highly pathogenic human coronavirus infections, with molecular docking experiments confirming the model's accuracy.

PMID:40112339 | DOI:10.1093/bib/bbaf117

Obstet Gynecol. 2025 Apr 1;145(4):e141-e142. doi: 10.1097/AOG.0000000000005865.

NO ABSTRACT

PMID:40112310 | DOI:10.1097/AOG.0000000000005865

Brief Bioinform. 2025 Mar 4;26(2):bbaf107. doi: 10.1093/bib/bbaf107.

ABSTRACT

A-to-I ribonucleic acid (RNA) editing detection is still a challenging task. Current bioinformatics tools rely on empirical filters and whole genome sequencing or whole exome sequencing data to remove background noise, sequencing errors, and artifacts. Sometimes they make use of cumbersome and time-consuming computational procedures. Here, we present REDInet, a temporal convolutional network-based deep learning algorithm, to profile RNA editing in human RNA sequencing (RNAseq) data. It has been trained on REDIportal RNA editing sites, the largest collection of human A-to-I changes from >8000 RNAseq data of the genotype-tissue expression project. REDInet can classify editing events with high accuracy harnessing RNAseq nucleotide frequencies of 101-base windows without the need for coupled genomic data.

PMID:40112338 | DOI:10.1093/bib/bbaf107

Hepatology. 2025 Mar 20. doi: 10.1097/HEP.0000000000001314. Online ahead of print.

ABSTRACT

BACKGROUND AND AIMS: Among those with primary sclerosing cholangitis (PSC), perihilar CCA (pCCA) is often diagnosed at a late-stage and is a leading source of mortality. Detection of pCCA in PSC when curative action can be taken is challenging. Our aim was to create a deep learning model that analyzed magnetic resonance imaging (MRI) to detect early-stage pCCA and compare its diagnostic performance with expert radiologists.

APPROACH AND RESULTS: We conducted a multicenter, international, retrospective cohort study involving adults with large duct PSC who underwent contrast-enhanced MRI. Senior abdominal radiologists reviewed the images. All patients with pCCA had early-stage cancer and were registered for liver transplantation. We trained a 3D DenseNet-121 model, a form of deep learning, using MRI images and assessed its performance in a separate test cohort. The study included 398 patients (training cohort n=150; test cohort n=248). pCCA was present in 230 individuals (training cohort n=64; test cohort n=166). In the test cohort, the respective performances of the model compared to the radiologists were: sensitivity 87.9% versus 50.0%, p<0.001; specificity 84.1% versus 100.0%, p<0.001; area under receiving operating curve 86.0% versus 75.0%, p<0.001. Even when a mass was absent, the model had a higher sensitivity for pCCA than radiologists (91.6% vs. 50.6%, p<0.001) and maintained good specificity (84.1%).

CONCLUSION: The 3D DenseNet-121 MRI model effectively detects early-stage pCCA in PSC patients. Compared to expert radiologists, the model missed fewer cases of cancer.

PMID:40112296 | DOI:10.1097/HEP.0000000000001314

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