PLoS One. 2025 May 22;20(5):e0324621. doi: 10.1371/journal.pone.0324621. eCollection 2025.

ABSTRACT

As the fashion e-commerce markets rapidly develop, tens of thousands of products are registered daily on e-commerce platforms. Individual sellers register products after setting up a product category directly on a fashion e-commerce platform. However, many sellers fail to find a suitable category and mistakenly register their products under incorrect ones. Precise category matching is important for increasing sales through search optimization and accurate product exposure. However, manually correcting registered categories is time-consuming and costly for platform managers. To resolve this problem, this study proposes a methodology for fashion e-commerce product classification based on multi-modal deep learning and transfer learning. Through the proposed methodology, three challenges in classifying fashion e-commerce products are addressed. First, the issue of extremely biased e-commerce data is addressed through under-sampling. Second, multi-modal deep learning enables the model to simultaneously use input data in different formats, which helps mitigate the impact of noisy and low-quality e-commerce data by providing richer information.Finally, the high computational cost and long training times involved in training deep learning models with both image and text data are mitigated by leveraging transfer learning. In this study, three strategies for transfer learning to fine-tune the image and text modules are presented. In addition, five methods for fusing feature vectors extracted from a single modal into one and six strategies for fine-tuning multi-modal models are presented, featuring a total of 14 strategies. The study shows that multi-modal models outperform unimodal models based solely on text or image. It also suggests the optimal conditions for classifying e-commerce products, helping fashion e-commerce practitioners construct models tailored to their respective business environments more efficiently.

PMID:40403022 | DOI:10.1371/journal.pone.0324621

Database (Oxford). 2025 Apr 22;2025:baaf031. doi: 10.1093/database/baaf031.

ABSTRACT

As the importance of precision agriculture grows, scalable and efficient methods for real-time data collection and analysis have become essential. In this study, we developed a system to collect real-time crop images, focusing on physiological disorders in tomatoes. This system systematically collects crop images and related data, with the potential to evolve into a valuable tool for researchers and agricultural practitioners. A total of 58 479 images were produced under stress conditions, including bacterial wilt (BW), Tomato Yellow Leaf Curl Virus (TYLCV), Tomato Spotted Wilt Virus (TSWV), drought, and salinity, across seven tomato varieties. The images include front views at 0 degrees, 120 degrees, 240 degrees, and top views and petiole images. Of these, 43 894 images were suitable for labeling. Based on this, 24 000 images were used for AI model training, and 13 037 images for model testing. By training a deep learning model, we achieved a mean Average Precision (mAP) of 0.46 and a recall rate of 0.60. Additionally, we discussed data augmentation and hyperparameter tuning strategies to improve AI model performance and explored the potential for generalizing the system across various agricultural environments. The database constructed in this study will serve as a crucial resource for the future development of agricultural AI. Database URL: https://crops.phyzen.com/.

PMID:40402767 | DOI:10.1093/database/baaf031

IEEE J Biomed Health Inform. 2025 May 22;PP. doi: 10.1109/JBHI.2025.3558170. Online ahead of print.

ABSTRACT

Non-suicidal self-injury (NSSI) is a serious threat to the physical and mental health of adolescents, significantly increasing the risk of suicide and attracting widespread public concern. Electroencephalography (EEG), as an objective tool for identifying brain disorders, holds great promise. However, extracting meaningful and reliable features from high-dimensional EEG data, especially by integrating spatiotemporal brain dynamics into informative representations, remains a major challenge. In this study, we introduce an advanced semi-supervised adversarial network, NSSI-Net, to effectively model EEG features related to NSSI. NSSI-Net consists of two key modules: a spatial-temporal feature extraction module and a multi-concept discriminator. In the spatial-temporal feature extraction module, an integrated 2D convolutional neural network (2D-CNN) and a bi-directional Gated Recurrent Unit (BiGRU) are used to capture both spatial and temporal dynamics in EEG data. In the multi-concept discriminator, signal, gender, domain, and disease levels are fully explored to extract meaningful EEG features, considering individual, demographic, disease variations across a diverse population. Based on self-collected NSSI data (n=114), the model's effectiveness and reliability are demonstrated, with a 5.44% improvement in performance compared to existing machine learning and deep learning methods. This study advances the understanding and early diagnosis of NSSI in adolescents with depression, enabling timely intervention.

PMID:40402701 | DOI:10.1109/JBHI.2025.3558170

IEEE J Biomed Health Inform. 2025 May 22;PP. doi: 10.1109/JBHI.2025.3572376. Online ahead of print.

ABSTRACT

This study presents a real-time implementation of an accelerated Hurst Contour Projection from Multiscale Multifractal Analysis (HCP-MMA) for deep learning-based ECG arrhythmia classification. Traditional heart rate variability analyses rely on fixed time scales and predefined parameters, limiting their ability to capture intricate scaling patterns and leading to diagnostic inconsistencies. HCP-MMA converts complex multifractal properties into a contour-based representation, enhancing interpretability for automated classification. However, the high computational cost of MMA hinders real-time processing. To address this, a runtime-optimized parallel computing pipeline is introduced, incorporating singular value decomposition (SVD) and vectorized processing, achieving a $730\times$ speedup over the baseline implementation on an Intel-based system. The proposed HCP-MMA framework, integrated with AlexNet, achieved over 98% classification accuracy across three benchmark datasets (PhysioNet, MIT-BIH, CU), with an F1-score of up to 99.3%. Runtime optimizations enabled real-time deployment on Raspberry Pi 5, demonstrating a $\sim 199\times$ speedup over baseline MMA computation on embedded hardware, with an average inference time of 0.0668 seconds per image, a memory footprint of approximately 220 MB, and a model size of $\sim 122$ MB. Statistical validation using ANOVA and Tukey's HSD tests (p $< 0.05$) confirmed the approach's robustness and generalizability. By bridging computational efficiency with real-time adaptability, this method not only advances automated ECG diagnostics but also paves the way for scalable deployment in wearable monitoring, telemedicine, and multifractal analysis of complex physiological time-series.

PMID:40402700 | DOI:10.1109/JBHI.2025.3572376

IEEE J Biomed Health Inform. 2025 May 22;PP. doi: 10.1109/JBHI.2025.3572458. Online ahead of print.

ABSTRACT

Osteoporotic vertebral compression fractures (OVCFs) are prevalent in the elderly population, typically assessed on computed tomography (CT) scans by evaluating vertebral height loss. This assessment helps determine the fracture's impact on spinal stability and the need for surgical intervention. However, the absence of pre-fracture CT scans and standardized vertebral references leads to measurement errors and inter-observer variability, while irregular compression patterns further challenge the precise grading of fracture severity. While deep learning methods have shown promise in aiding OVCFs screening, they often lack interpretability and sufficient sensitivity, limiting their clinical applicability. To address these challenges, we introduce a novel vertebra synthesis-height loss quantification-OVCFs grading framework. Our proposed model, HealthiVert-GAN, utilizes a coarse-to-fine synthesis network designed to generate pseudo-healthy vertebral images that simulate the pre-fracture state of fractured vertebrae. This model integrates three auxiliary modules that leverage the morphology and height information of adjacent healthy vertebrae to ensure anatomical consistency. Additionally, we introduce the Relative Height Loss of Vertebrae (RHLV) as a quantification metric, which divides each vertebra into three sections to measure height loss between pre-fracture and post-fracture states, followed by fracture severity classification using a Support Vector Machine (SVM). Our approach achieves state-of-the-art classification performance on both the Verse2019 dataset and in-house dataset, and it provides cross-sectional distribution maps of vertebral height loss. This practical tool enhances diagnostic accuracy in clinical settings and assisting in surgical decision-making.

PMID:40402696 | DOI:10.1109/JBHI.2025.3572458

Br J Radiol. 2025 Jun 1;98(1170):974-980. doi: 10.1093/bjr/tqaf059.

ABSTRACT

OBJECTIVES: To investigate the impacts of a deep learning-based iterative reconstruction algorithm on image quality and measuring accuracy of bone mineral density (BMD) in low-dose chest CT.

METHODS: Phantom and patient studies were separately conducted in this study. The same low-dose protocol was used for phantoms and patients. All images were reconstructed with filtered back projection, hybrid iterative reconstruction (HIR) (KARL®, level of 3,5,7), and deep learning-based iterative reconstruction (artificial intelligence iterative reconstruction [AIIR], low, medium, and high strength). The noise power spectrum (NPS) and the task-based transfer function (TTF) were evaluated using phantom. The accuracy and the relative error (RE) of BMD were evaluated using a European spine phantom. The subjective evaluation was performed by 2 experienced radiologists. BMD was measured using quantitative CT (QCT). Image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), BMD values, and subjective scores were compared with Wilcoxon signed-rank test. The Cohen's kappa test was used to evaluate the inter-reader and inter-group agreement.

RESULTS: AIIR reduced noise and improved resolution on phantom images significantly. There were no significant differences among BMD values in all groups of images (all P > 0.05). RE of BMD measured using AIIR images was smaller. In objective evaluation, all strengths of AIIR achieved less image noise and higher SNR and CNR (all P < 0.05). AIIR-H showed the lowest noise and highest SNR and CNR (P < 0.05). The increase in AIIR algorithm strengths did not affect BMD values significantly (all P > 0.05).

CONCLUSION: The deep learning-based iterative reconstruction did not affect the accuracy of BMD measurement in low-dose chest CT while reducing image noise and improving spatial resolution.

ADVANCES IN KNOWLEDGE: The BMD values could be measured accurately in low-dose chest CT with deep learning-based iterative reconstruction while reducing image noise and improving spatial resolution.

PMID:40402596 | DOI:10.1093/bjr/tqaf059

Br J Radiol. 2025 Jun 1;98(1170):956-964. doi: 10.1093/bjr/tqaf055.

ABSTRACT

OBJECTIVES: To determine the value of on-site deep learning-based CT-derived fractional flow reserve (CT-FFR) for therapeutic management and adverse clinical outcomes in patients suspected of coronary artery disease (CAD) compared with coronary CT angiography (CCTA) alone.

METHODS: This single-centre prospective study included consecutive patients suspected of CAD between June 2021 and September 2021 at our hospital. Four hundred and sixty-one patients were randomized into either CT-FFR+CCTA or CCTA-alone group. The first endpoint was the invasive coronary angiography (ICA) efficiency, defined as the ICA with nonobstructive disease (stenosis <50%) and the ratio of revascularization to ICA (REV-to-ICA ratio) within 90 days. The second endpoint was the incidence of major adverse cardiaovascular events (MACE) at 2 years.

RESULTS: A total of 461 patients (267 [57.9%] men; median age, 64 [55-69]) were included. At 90 days, the rate of ICA with nonobstructive disease in the CT-FFR+CCTA group was lower than in the CCTA group (14.7% vs 34.0%, P=.047). The REV-to-ICA ratio in the CT-FFR+CCTA group was significantly higher than in the CCTA group (73.5% vs. 50.9%, P=.036). No significant difference in ICA efficiency was found in intermediate stenosis (25%-69%) between the 2 groups (all P>.05). After a median follow-up of 23 (22-24) months, MACE were observed in 11 patients in the CT-FFR+CCTA group and 24 in the CCTA group (5.9% vs 10.0%, P=.095).

CONCLUSIONS: The on-site deep learning-based CT-FFR improved the efficiency of ICA utilization with a similarly low rate of MACE compared with CCTA alone.

ADVANCES IN KNOWLEDGE: The on-site deep learning-based CT-FFR was superior to CCTA for therapeutic management.

PMID:40402592 | DOI:10.1093/bjr/tqaf055

Comput Biol Chem. 2025 May 15;119:108505. doi: 10.1016/j.compbiolchem.2025.108505. Online ahead of print.

ABSTRACT

It is evident that a robust immune system keeps Candida albicans infection in check, but weakened immunity opens the door for shifting from a benign yeast form to an invasive hyphal form which leads to systemic candidiasis with high mortality rate. However, the crucial players contributing to the increased susceptibility of immune-deficient individuals to Candida infection remain obscure. To uncover the molecular differences between these conditions, blood-associated proteins from the NDEx database and differentially expressed genes from GEO datasets of immunocompetent and immune-deficient individuals infected with C. albicans were analysed. We focused on deregulated proteins exhibiting inverse expression patterns i.e. upregulated in one group and downregulated in the other and identified 539 proteins. Mapping them onto protein-protein interaction network reconstructed with blood- associated proteins, revealed that they exhibit in 45 hubs, 31 network nodes forming 29 intermodular complexes, and 69 clustered into 11 immunologically relevant MCODE modules. Amongst them 13 key host molecules emerging as key player based on their network topological properties. Furthermore, a machine learning model was developed with a precision of 85 %, recall of 92 %, F1-score of 89 %, and accuracy of 81 % which substantiates the robust association of 11 out of 13 proteins with fungal co-infections in immune-deficient individuals. These findings underscore key host proteins maintaining immune balance in healthy individuals while their disruption in immune-deficient conditions may weaken defense mechanisms and promote fungal infections. Identification of crucial proteins promoting T-reg cells proliferation and M2 macrophage polarization in immune-deficient conditions offers promising therapeutic targets following experimental validation.

PMID:40403354 | DOI:10.1016/j.compbiolchem.2025.108505

Plant Cell. 2025 May 22:koaf124. doi: 10.1093/plcell/koaf124. Online ahead of print.

ABSTRACT

Plant roots dynamically respond to nitrogen availability by executing a signaling and transcriptional cascade resulting in altered plant growth that is optimized for nutrient uptake. The NIN-LIKE PROTEIN 7 (NLP7) transcription factor senses nitrogen and, along with its paralog NLP6, partially coordinates transcriptional responses. While the post-translational regulation of NLP6 and NLP7 is well established, their upstream transcriptional regulation remains understudied in Arabidopsis (Arabidopsis thaliana) and other plant species. Here, we dissected a known sub-circuit upstream of NLP6 and NLP7 in Arabidopsis, which was predicted to contain multiple multi-node feedforward loops suggestive of an optimized design principle of nitrogen transcriptional regulation. This sub-circuit comprises AUXIN RESPONSE FACTOR 18 (ARF18), ARF9, DEHYDRATION-RESPONSIVE ELEMENT-BINDING PROTEIN 26 (DREB26), Arabidopsis NAC-DOMAIN CONTAINING PROTEIN 32 (ANAC032), NLP6 and NLP7 and their regulation of NITRITE REDUCTASE 1 (NIR1). Conservation and divergence of this circuit and its influence on nitrogen-dependent root system architecture were similarly assessed in tomato (Solanum lycopersicum). The specific binding sites of these factors within their respective promoters and their putative cis-regulatory architectures were identified. The direct or indirect nature of these interactions was validated in planta. The resulting models were genetically validated in varying concentrations of available nitrate by measuring the transcriptional output of the network revealing rewiring of nitrogen regulation across distinct plant lineages.

PMID:40403157 | DOI:10.1093/plcell/koaf124

Circ Res. 2025 May 23;136(11):1335-1362. doi: 10.1161/CIRCRESAHA.125.325492. Epub 2025 May 22.

ABSTRACT

The liver and heart are closely interconnected organs, and their bidirectional interaction plays a central role in cardiometabolic disease. In this review, we summarize current evidence linking liver dysfunction-particularly metabolic dysfunction-associated steatotic liver disease, alcohol-associated liver disease, and cirrhosis-with an increased risk of heart failure and other cardiovascular diseases. We discuss how these liver conditions contribute to cardiac remodeling, systemic inflammation, and hemodynamic stress and how cardiac dysfunction in turn impairs liver perfusion and promotes hepatic injury. Particular attention is given to the molecular mediators of liver-heart communication, including hepatokines and cardiokines, as well as the emerging role of advanced research methodologies, including omics integration, proximity labeling, and organ-on-chip platforms, that are redefining our understanding of interorgan cross talk. By integrating mechanistic insights with translational tools, this review aims to support the development of multiorgan therapeutic strategies for cardiometabolic disease.

PMID:40403112 | DOI:10.1161/CIRCRESAHA.125.325492

Database (Oxford). 2025 Mar 21;2025:baaf020. doi: 10.1093/database/baaf020.

ABSTRACT

Ontologies are widely used in databases to standardize data, improving data quality, integration, and ease of comparison. Within ontologies tailored to diverse use cases, post-composing user-defined terms reconciles the demands for standardization on the one hand and flexibility on the other. In many instances of Breedbase, a digital ecosystem for plant breeding designed for genomic selection, the goal is to capture phenotypic data using highly curated and rigorous crop ontologies, while adapting to the specific requirements of plant breeders to record data quickly and efficiently. For example, post-composing enables users to tailor ontology terms to suit specific and granular use cases such as repeated measurements on different plant parts and special sample preparation techniques. To achieve this, we have implemented a post-composing tool based on orthogonal ontologies providing users with the ability to introduce additional levels of phenotyping granularity tailored to unique experimental designs. Post-composed terms are designed to be reused by all breeding programs within a Breedbase instance but are not exported to the crop reference ontologies. Breedbase users can post-compose terms across various categories, such as plant anatomy, treatments, temporal events, and breeding cycles, and, as a result, generate highly specific terms for more accurate phenotyping.

PMID:40402802 | DOI:10.1093/database/baaf020

Database (Oxford). 2025 Jan 22;2025:baae133. doi: 10.1093/database/baae133.

ABSTRACT

Ontologies and knowledge graphs (KGs) are general-purpose computable representations of some domain, such as human anatomy, and are frequently a crucial part of modern information systems. Most of these structures change over time, incorporating new knowledge or information that was previously missing. Managing these changes is a challenge, both in terms of communicating changes to users and providing mechanisms to make it easier for multiple stakeholders to contribute. To fill that need, we have created KGCL, the Knowledge Graph Change Language (https://github.com/INCATools/kgcl), a standard data model for describing changes to KGs and ontologies at a high level, and an accompanying human-readable Controlled Natural Language (CNL). This language serves two purposes: a curator can use it to request desired changes, and it can also be used to describe changes that have already happened, corresponding to the concepts of "apply patch" and "diff" commonly used for managing changes in text documents and computer programs. Another key feature of KGCL is that descriptions are at a high enough level to be useful and understood by a variety of stakeholders-e.g. ontology edits can be specified by commands like "add synonym 'arm' to 'forelimb'" or "move 'Parkinson disease' under 'neurodegenerative disease'." We have also built a suite of tools for managing ontology changes. These include an automated agent that integrates with and monitors GitHub ontology repositories and applies any requested changes and a new component in the BioPortal ontology resource that allows users to make change requests directly from within the BioPortal user interface. Overall, the KGCL data model, its CNL, and associated tooling allow for easier management and processing of changes associated with the development of ontologies and KGs. Database URL: https://github.com/INCATools/kgcl.

PMID:40402778 | DOI:10.1093/database/baae133

Blood Adv. 2025 May 22:bloodadvances.2025016002. doi: 10.1182/bloodadvances.2025016002. Online ahead of print.

ABSTRACT

Primary renal manifestations of diffuse large B-cell lymphoma (prDLBCL) represent an exceptionally rare variant of the most common type of non-Hodgkin lymphoma (NHL). Insights into prDLBCL pathogenesis have been limited to small case series and methodologically limited approaches. To address this gap, we conducted the largest comprehensive molecular study of prDLBCL to date, analyzing 30 cases using whole exome sequencing, RNA sequencing, and somatic copy number alteration profiling. The mechanisms driving lymphomagenesis within an organ lacking an intrinsic lymphatic niche and its proclivity for dissemination to immune-privileged sites, including testes and the central nervous system, remain poorly understood. Our findings reveal significant molecular similarities to primary large B-cell lymphomas of immune-privileged sites (IP-LBCL), including a high frequency of immune-escape mechanisms, particularly through deleterious MHC class I and II aberrations and loss of CDKN2A. Despite significant mutational heterogeneity with a broad distribution among molecular clusters, transcriptional deregulation of interferon signaling and MYC target pathways emerged as key hallmarks of prDLBCL pathogenesis. Our comprehensive analysis of prDLBCL biology significantly advances the molecular understanding of this rare variant. These insights not only highlight shared pathogenetic pathways with IP-LBCL but also uncover unique features of prDLBCL, offering potential biomarkers for diagnostic refinement and therapeutic targeting. These findings have profound implications for the future development of diagnostic algorithms and risk-adapted therapeutic approaches, potentially improving the clinical management of this rare and challenging lymphoma subtype.

PMID:40402672 | DOI:10.1182/bloodadvances.2025016002

JCI Insight. 2025 May 22:e191314. doi: 10.1172/jci.insight.191314. Online ahead of print.

ABSTRACT

CD16 is an activating Fc receptor on natural killer cells that mediates antibody-dependent cellular cytotoxicity (ADCC), a key mechanism in antiviral immunity. However, the role of NK cell-mediated ADCC in SARS-CoV-2 infection remains unclear, particularly whether it limits viral spread and disease severity or contributes to the immunopathogenesis of COVID-19. We hypothesized that the high-affinity CD16AV176 polymorphism influences these outcomes. Using a novel in vitro reporter system, we demonstrated that CD16AV176 is a more potent and sensitive activator than the common CD16AF176 allele. To assess its clinical relevance, we analyzed 1,027 hospitalized COVID-19 patients from the Immunophenotyping Assessment in a COVID-19 Cohort (IMPACC), a comprehensive longitudinal dataset with extensive transcriptomic, proteomic, and clinical data. The high-affinity CD16AV176 allele was associated with a significantly reduced risk of ICU admission, mechanical ventilation, and severe disease trajectories. Lower anti-SARS-CoV-2 IgG titers were correlated to CD16AV176; however, there was no difference in viral load across CD16 genotypes. Proteomic analysis revealed that participants homozygous for CD16AV176 had lower levels of inflammatory mediators. These findings suggest that CD16AV176 enhances early NK cell-mediated immune responses, limiting severe respiratory complications in COVID-19. This study identifies a protective genetic factor against severe COVID-19, informing future host-directed therapeutic strategies.

PMID:40402577 | DOI:10.1172/jci.insight.191314

Ther Drug Monit. 2025 May 22. doi: 10.1097/FTD.0000000000001343. Online ahead of print.

ABSTRACT

BACKGROUND: Neuropsychiatric toxicity is a common adverse effect of antibiotics. Advanced age, renal insufficiency, high drug doses, and prolonged therapy are relevant risk factors, suggesting that this event might be caused due to the accumulation of antibiotics in the central nervous system. In this review, the authors aimed to evaluate the potential role of therapeutic drug monitoring in identifying patients at risk of antibiotic-induced neuropsychiatric toxicity.

METHODS: A MEDLINE PubMed search was conducted for articles published between January 1990 and December 2024, matching the terms "pharmacokinetics" or "therapeutic drug monitoring" with "antibiotics" (including individual drug classes) and "neurotoxicity" (including synonyms). Additional studies were identified from the reference lists of retrieved articles.

RESULTS: Significant associations have been reported between plasma concentrations of some beta-lactam antibiotics (ceftazidime, cefepime, piperacillin, and meropenem) or linezolid and drug-induced central nervous system adverse events (such as seizures, encephalopathy, peripheral neuropathy, and optic neuropathy). Safety thresholds of plasma concentrations have been proposed for these drugs.

CONCLUSIONS: Consistent data on the associations between plasma drug concentrations and neuropsychiatric disorders are available only for some antibiotics, whereas for others, there are few and often inconsistent data, hindering the establishment of therapeutic drug monitoring-based safety thresholds for these antibiotics.

PMID:40403142 | DOI:10.1097/FTD.0000000000001343

Langenbecks Arch Surg. 2025 May 22;410(1):168. doi: 10.1007/s00423-025-03735-3.

ABSTRACT

PURPOSE: The perioperative period is characterized by psychological stress and inflammatory reactions that can contribute to disease recurrence or metastatic spread. These reactions are mediated particularly by catecholamines and prostaglandins. The PROSPER trial aimed to evaluate whether a perioperative drug repurposing with a non-selective betablocker (propranolol) and a COX-2 inhibitor (etodolac) is feasible and safe in the setting of pancreatic cancer surgery.

METHODS: Patients undergoing partial pancreatoduodenectomy for pancreatic cancer were randomized to perioperative treatment with propranolol and etodolac or placebo. Main safety endpoint was the rate of serious adverse events (SAE) and the main feasibility endpoint was adherence. Overall and disease-free survival (DFS) as well as recurrences were assessed as efficacy parameters and the trial was accompanied by a translational study.

RESULTS: The trial was prematurely closed due to slow recruitment. 26 patients were randomized, but 6 never started trial medication. Finally, 9 patients received the trial medication and 11 patients placebo. There were 6 SAE in the treatment vs. 14 in the placebo group. Adherence was lower in the treatment group, but without statistically significance. Median DFS was 16.36 months (95%-CI 1.18 - not reached) in verum vs. 11.25 (95%-CI 2.2 - 17.25) in placebo group. The rate of distant recurrences was 11.1% in verum vs. 54.5% in placebo group.

CONCLUSION: There were no safety concerns, but the trial intervention was not feasible given slow recruitment and limited adherence. However, the translational study and preliminary efficacy data revealed some promising findings, warranting further investigation.

REGISTRATION: DRKS00014054.

PMID:40402347 | DOI:10.1007/s00423-025-03735-3

Pharmacogenomics. 2025 May 22:1-12. doi: 10.1080/14622416.2025.2504863. Online ahead of print.

ABSTRACT

Pharmacogenomic variations in genes involved in drug disposition and in drug targets is a major determinant of inter-individual differences in drug response and toxicity. While the effects of common variants are well established, millions of rare variations remain functionally uncharacterized, posing a challenge for the implementation of precision medicine. Recent advances in machine learning (ML) have significantly enhanced the prediction of variant effects by considering DNA as well as protein sequences, as well as their evolutionary conservation and haplotype structures. Emerging deep learning models utilize techniques to capture evolutionary conservation and biophysical properties, and ensemble approaches that integrate multiple predictive models exhibit increased accuracy, robustness, and interpretability. This review explores the current landscape of ML-based variant effect predictors. We discuss key methodological differences and highlight their strengths and limitations for pharmacogenomic applications. We furthermore discuss emerging methodologies for the prediction of substrate-specificity and for consideration of variant epistasis. Combined, these tools improve the functional effect prediction of drug-related variants and offer a viable strategy that could in the foreseeable future translate comprehensive genomic information into pharmacogenetic recommendations.

PMID:40401639 | DOI:10.1080/14622416.2025.2504863

Crit Care Med. 2025 May 22. doi: 10.1097/CCM.0000000000006716. Online ahead of print.

ABSTRACT

OBJECTIVES: Soluble ST2 (sST2), a decoy receptor for the alarmin interleukin-33 (IL-33), has been implicated in adverse clinical outcomes in acute respiratory failure (ARF). We evaluated sST2 distribution across diverse cohorts of patients with different etiologies of ARF, compared plasma and lower respiratory tract (LRT) concentrations, and examined associations with individual organ dysfunction, biological subphenotypes, and outcomes.

DESIGN: Observational study.

SETTING: Multicenter cohorts of ARF patients.

PATIENTS: A total of 1432 ARF patients, including 863 non-COVID and 569 COVID-19 cases, from five cohorts.

INTERVENTIONS: None.

MEASUREMENTS AND MAIN RESULTS: sST2 levels were measured in plasma and LRT specimens (when available) and analyzed for associations with ARF etiology, severity, organ dysfunction, systemic host response, subphenotypes, and 30-day mortality. Plasma sST2 levels were higher in non-COVID ARF patients compared with COVID-19 patients (p < 0.05) and were markedly elevated compared with LRT levels (> 19-fold), with weak intercompartmental correlation. Elevated plasma sST2 levels were associated with extrapulmonary organ dysfunction and a hyperinflammatory ARF subphenotype but not with respiratory indices, including hypoxemia. Plasma sST2 independently predicted 30-day mortality in pooled cohort data, adjusted for age, sex, and illness severity. In longitudinal measurements, nonsurvivors had persistently elevated plasma sST2 levels in the first 2 weeks of critical illness compared with survivors.

CONCLUSIONS: Plasma sST2 levels independently predict outcomes in ARF and are strongly associated with extrapulmonary organ dysfunction. The weak correlation between plasma and LRT sST2 levels suggests a predominantly systemic source. These findings highlight the potential of the IL-33/ST2 axis as a therapeutic target and warrant further investigation into its role in multiple organ dysfunction in ARF.

PMID:40402026 | DOI:10.1097/CCM.0000000000006716

J Biomol Struct Dyn. 2025 May 22:1-12. doi: 10.1080/07391102.2025.2499949. Online ahead of print.

ABSTRACT

One of the most important public health concerns is the rise of the multi-drug resistance bacteria in the recent years. Pseudomonas aeruginosa is a frequent Gram-negative bacterium prominent in the hospital-acquired illness and is considered as an opportunistic human pathogen responsible for causing nosocomial infections. Numerous burn victims, cystic fibrosis patients, and those with neutropenic malignancy die as a result of it. The current approach involves molecular docking for the predominant recognition of the drug binding site for the designing of the potent inhibitors for inhibiting the membrane protein of Pseudomonas aeruginosa. The present study has targeted 11 outer membrane proteins of Pseudomonas aeruginosa with 12 different FDA approved drugs. Protein modeling has been applied to create the target proteins. As per the results revealed out from the docking perspective, Piperacillin which has been categorized under the broad-spectrum antibiotics has emerged out as one of the forerunners as compared to the other group of antibiotics as it exhibited highest binding energy, i.e. -10.4 kcal/mol. Hence, the compound has been validated using in-silico tools such as ADME and PROTOX-II server which indicates its nontoxic nature. Molecular dynamics simulations were conducted for EGCG-OprP, Piperacillin-OprB, OprP (Apoprotein), and OprB (Apoprotein) complexes to assess their binding efficacy. Statistical parameters such as RMSD, RMSF, h-bond interactions, and % occupancies indicated stability in ligand binding. Protein RMSD values plateaued at approximately 0.5 nm, while ligand RMSD values remained below 0.2 nm, affirming stability in binding OprP and OprB. H-bond analysis revealed stable contacts for EGCG and Piperacillin, and % occupancies indicated specific interactions. Energetics analysis yielded deltaG values of -30.45 for EGCG and -56.66 for Piperacillin, suggesting efficient binding with OprP and OprB. This positioned Piperacillin as a promising candidate for future pharmacological studies, considering its classification as a broad-spectrum antibiotic against P. aeruginosa. The study served as a crucial roadmap for designing drugs to inhibit this formidable pathogen amid rising antibiotic resistance, emphasizing its significance in the ongoing battle against infectious diseases.

PMID:40401805 | DOI:10.1080/07391102.2025.2499949

JMIR Hum Factors. 2025 May 22;12:e72838. doi: 10.2196/72838.

ABSTRACT

Traditional medical education encounters several challenges. The introduction of advanced facial expression recognition technology offers a new approach to address these issues. The aim of the study is to propose a medical education-assisted teaching and student evaluation method based on facial expression recognition technology. This method consists of 4 key steps. In data collection, multiangle high-definition cameras record students' facial expressions to ensure data comprehensiveness and accuracy. Facial expression recognition uses computer vision and deep learning algorithms to identify students' emotional states. The result analysis stage organizes and statistically analyzes the recognized emotional data to provide teachers with students' learning status feedback. In the teaching feedback stage, teaching strategies are adjusted according to the analysis results. Although this method faces challenges such as technical accuracy, device dependency, and privacy protection, it has the potential to improve teaching effectiveness, optimize personalized learning, and promote teacher-student interaction. The application prospects of this method in medical education are broad, and it is expected to significantly enhance teaching quality and students' learning experience.

PMID:40402552 | DOI:10.2196/72838