Front Immunol. 2025 Apr 24;16:1544312. doi: 10.3389/fimmu.2025.1544312. eCollection 2025.

ABSTRACT

Immune checkpoint inhibitors (ICIs) have become a standard treatment for various cancers, but their use is often associated with immune-related adverse events (irAEs), including cutaneous irAEs (cirAEs). Here, we report a rare case of subacute cutaneous lupus erythematosus (SCLE) induced by sintilimab, a PD-1 inhibitor, in a 30-year-old woman undergoing neoadjuvant chemo-immunotherapy for gastric cancer. The patient presented with erythema, macules, papules, and vesicles, with positive ANA (108U/mL) and strongly positive anti-SSA/Ro. After discontinuation of sintilimab and treatment with corticosteroids, hydroxychloroquine, and intravenous immunoglobulin (IVIG), her symptoms improved. This case represents the first reported instance of drug-induced lupus caused by sintilimab and emphasizes the importance of distinguishing between paraneoplastic lupus and ICI-induced lupus.

PMID:40342412 | PMC:PMC12058751 | DOI:10.3389/fimmu.2025.1544312

Pharmacol Res Perspect. 2025 Jun;13(3):e70102. doi: 10.1002/prp2.70102.

ABSTRACT

Pharmacovigilance plays a significant role in guaranteeing the safety of medications for patients. Over the last three decades, China has significantly advanced its pharmacovigilance practices, yet the factors that drive the quality of pharmacovigilance remain unclear. This study aimed to investigate how multiple factors interactively influence the quality of pharmacovigilance and identify pathways for achieving high-quality pharmacovigilance practices. A unique sample of pharmacovigilance-specific inspection reports from 13 representative companies in China was adopted in analysis. Given the qualitative nature of the inspection reports, we utilized crisp-set qualitative comparative analysis (csQCA) with five factors structure based on the technology-organization-environment (TOE) theoretical framework. The csQCA enabled us to elucidate the interactions among the antecedents of pharmacovigilance quality through quantitative univariate necessity analysis and configuration analysis. Three pathways contributing to high-quality pharmacovigilance were identified, and "Dedicated and Qualified Person for Pharmacovigilance (DQPPV)" was shown to be involved in all three pathways. Upon examining the manner in which multiple variables influence the quality of pharmacovigilance, it becomes evident that the DQPPV represents a factor that warrants further investigation. The results of the configuration allow companies to implement targeted measures to enhance the functionality of the pharmacovigilance system and to improve the quality of the system. Further research could explore the influence of additional factors on pharmacovigilance efforts, which could then contribute to marketing authorization holders' (MAHs') pharmacovigilance efforts.

PMID:40341821 | DOI:10.1002/prp2.70102

Arch Esp Urol. 2025 Apr;78(3):325-333. doi: 10.56434/j.arch.esp.urol.20257803.44.

ABSTRACT

BACKGROUND: Drug-related problems (DRPs) are prevalent among older cancer patients. This study aimed to investigate the impact of pharmaceutical services on DRP, disease knowledge, health-related quality of life, and satisfaction among older patients with prostate cancer (PCa).

METHODS: The clinical data of 86 elderly patients with PCa admitted during June 2021-June 2024 were retrospectively analyzed. Descriptive statistics and univariate analysis were used to evaluate the effectiveness of the clinical application of the pharmacy service carried out in our hospital, including the incidence of DRP, knowledge of disease, health-related quality of life score, and satisfaction. The general content of pharmaceutical services is as follows: Arrange hospital pharmacists to directly participate in patient treatment, conduct drug reviews, identify DRPs, and discuss with prescribing doctors based on problems to optimize medication plans. At the same time, it provides disease knowledge education, medication consultation, and primary care guidance.

RESULTS: At admission, 55 patients (63.95%) had DRP, with the most common classification being drug selection, with an incidence rate of 36.36% (20/55). At discharge, the proportion of DRP in patients receiving pharmaceutical services was lower than that in patients refusing pharmaceutical services, and the DRP status was better than that of patients refusing pharmaceutical services (p < 0.05). Patients who received pharmaceutical services had higher level of disease knowledge mastery (p < 0.001), Short-Form-36 (SF-36) score in some dimensions (p < 0.05), and satisfaction (p < 0.05) than those who refused pharmaceutical services.

CONCLUSIONS: Hospital pharmaceutical services can effectively reduce the occurrence of DRP during hospitalization of elderly patients with PCa, help them to acquire knowledge of the disease and health-related quality of life, and have high patient satisfaction.

PMID:40340998 | DOI:10.56434/j.arch.esp.urol.20257803.44

Sci Rep. 2025 May 8;15(1):16114. doi: 10.1038/s41598-025-01303-9.

ABSTRACT

The growing prevalence of antibiotic resistance in multidrug-resistant Gram-negative bacteria (MDR-GNB), exacerbated by the misuse of antibiotics, presents a critical global health challenge. Colistin, a last-resort antibiotic for severe MDR-GNB infections, has faced diminishing efficacy due to the emergence of colistin-resistant (COL-R) strains. This study evaluates the potential of penfluridol (PF), an antipsychotic drug with notable antibacterial and antibiofilm properties, to restore colistin activity against COL-R GNB in vitro. PF alone exhibited limited antibacterial activity against COL-R GNB; however, its combination with colistin demonstrated strong synergistic effects, significantly reducing colistin's minimum inhibitory concentrations (MICs) by 4-128 times. Time-kill assays confirmed the combination's superior bactericidal activity compared to either agent alone. Membrane permeability assays revealed that PF enhanced colistin's ability to disrupt bacterial membranes, likely by facilitating colistin binding to lipopolysaccharide. Furthermore, PF significantly inhibited the development of colistin resistance over a 30-day resistance development assay. In addition to its antibacterial effects, PF exhibited notable antibiofilm activity. The combination of PF and colistin effectively inhibited biofilm formation and eradicated mature biofilms in most of the tested COL-R GNB strains. These findings mark the first report of PF's synergistic interaction with colistin against GNB biofilms, offering a promising strategy to combat biofilm-associated infections. Overall, the colistin/PF combination holds potential as an effective therapeutic strategy to enhance colistin efficacy, delay resistance development, and manage biofilm-associated infections in MDR-GNB.

PMID:40341530 | DOI:10.1038/s41598-025-01303-9

Psychol Med. 2025 May 9;55:e137. doi: 10.1017/S0033291725000819.

ABSTRACT

BACKGROUND: The Hierarchical Taxonomy of Psychopathology (HiTOP) and Research Domain Criteria (RDoC) frameworks emphasize transdiagnostic and mechanistic aspects of psychopathology. We used a multi-omics approach to examine how HiTOP's psychopathology spectra (externalizing [EXT], internalizing [INT], and shared EXT + INT) map onto RDoC's units of analysis.

METHODS: We conducted analyses across five RDoC units of analysis: genes, molecules, cells, circuits, and physiology. Using genome-wide association studies from the companion Part I article, we identified genes and tissue-specific expression patterns. We used drug repurposing analyses that integrate gene annotations to identify potential therapeutic targets and single-cell RNA sequencing data to implicate brain cell types. We then used magnetic resonance imaging data to examine brain regions and circuits associated with psychopathology. Finally, we tested causal relationships between each spectrum and physical health conditions.

RESULTS: Using five gene identification methods, EXT was associated with 1,759 genes, INT with 454 genes, and EXT + INT with 1,138 genes. Drug repurposing analyses identified potential therapeutic targets, including those that affect dopamine and serotonin pathways. Expression of EXT genes was enriched in GABAergic, cortical, and hippocampal neurons, while INT genes were more narrowly linked to GABAergic neurons. EXT + INT liability was associated with reduced gray matter volume in the amygdala and subcallosal cortex. INT genetic liability showed stronger causal effects on physical health - including chronic pain and cardiovascular diseases - than EXT.

CONCLUSIONS: Our findings revealed shared and distinct pathways underlying psychopathology. Integrating genomic insights with the RDoC and HiTOP frameworks advanced our understanding of mechanisms that underlie EXT and INT psychopathology.

PMID:40340892 | DOI:10.1017/S0033291725000819

J Transl Med. 2025 May 8;23(1):516. doi: 10.1186/s12967-025-06535-x.

ABSTRACT

BACKGROUND: Long COVID is a major public health burden causing a diverse array of debilitating symptoms in tens of millions of patients globally. In spite of this overwhelming disease prevalence, staggering cost, severe impact on patients' lives and intense global research efforts, study of the disease has proved challenging due to its complexity. Genome-wide association studies (GWAS) have identified only four loci potentially associated with the disease, although these results did not statistically replicate between studies. A previous combinatorial analysis study identified a total of 73 genes that were highly associated with two long COVID cohorts in the predominantly (> 91%) white European ancestry Sano GOLD population, and we sought to reproduce these findings in the independent and ancestrally more diverse All of Us (AoU) population.

METHODS: We assessed the reproducibility of the 5343 long COVID disease signatures from the original study in the AoU population. Because the very small population sizes provide very limited power to replicate findings, we initially tested whether we observed a statistically significant enrichment of the Sano GOLD disease signatures that are also positively correlated with long COVID in the AoU cohort after controlling for population substructure.

RESULTS: For the Sano GOLD disease signatures that have a case frequency greater than 5% in AoU, we consistently observed a significant enrichment (77-83%, p < 0.01) of signatures that are also positively associated with long COVID in the AoU cohort. These encompassed 92% of the genes identified in the original study. At least five of the disease signatures found in Sano GOLD were also shown to be individually significantly associated with increased long COVID prevalence in the AoU population. Rates of signature reproducibility are strongest among self-identified white patients, but we also observe significant enrichment of reproducing disease associations in self-identified black/African-American and Hispanic/Latino cohorts. Signatures associated with 11 out of the 13 drug repurposing candidates identified in the original Sano GOLD study were reproduced in this study.

CONCLUSION: These results demonstrate the reproducibility of long COVID disease signal found by combinatorial analysis, broadly validating the results of the original analysis. They provide compelling evidence for a much broader array of genetic associations with long COVID than previously identified through traditional GWAS studies. This strongly supports the hypothesis that genetic factors play a critical role in determining an individual's susceptibility to long COVID following recovery from acute SARS-CoV-2 infection. It also lends weight to the drug repurposing candidates identified in the original analysis. Together these results may help to stimulate much needed new precision medicine approaches to more effectively diagnose and treat the disease. This is also the first reproduction of long COVID genetic associations across multiple populations with substantially different ancestry distributions. Given the high reproducibility rate across diverse populations, these findings may have broader clinical application and promote better health equity. We hope that this will provide confidence to explore some of these mechanisms and drug targets and help advance research into novel ways to diagnose the disease and accelerate the discovery and selection of better therapeutic options, both in the form of newly discovered drugs and/or the immediate prioritization of coordinated investigations into the efficacy of repurposed drug candidates.

PMID:40340717 | DOI:10.1186/s12967-025-06535-x

J Med Chem. 2025 May 9. doi: 10.1021/acs.jmedchem.5c00021. Online ahead of print.

ABSTRACT

Aging induces dysfunction and increases the risk of chronic diseases in the elderly, positioning the development of antiaging drugs to the forefront of research. Drug repurposing offers an efficient strategy for identifying antiaging lead compounds. In this study, we employed phenotypic screening and discovered that enrofloxacin could extend the lifespan in Caenorhabditis elegans. Based on these findings, we conducted rational drug design to eliminate its antibacterial activity while maintaining the lifespan-extending effect, with the goal of developing safe and novel antiaging compounds. Consequently, JX10 exhibited minimal antibacterial activity and competent antiaging effects in C. elegans, senescent cells, and aged mice. In terms of its mechanism, JX10 acted as a senomorphic agent by suppressing the expression of p38 MAPK and NF-κB. Furthermore, JX10 demonstrated favorable safety and pharmacokinetic properties, supporting the feasibility of JX10 as a promising candidate with the potential for therapeutic interventions in aging and aging-related diseases.

PMID:40340340 | DOI:10.1021/acs.jmedchem.5c00021

Am Soc Clin Oncol Educ Book. 2025 Jun;45(3):e473106. doi: 10.1200/EDBK-25-473106. Epub 2025 May 8.

ABSTRACT

Rare uterine malignancies present treatment challenges because of their clinical and biological heterogeneity. Among the rarest of the uterine cancers are leiomyosarcomas, uterine stromal tumors, and the mesonephric-like and serous carcinomas. In this article, we review recent advancements in diagnostic precision, risk stratification, and identification of biomarker-guided therapeutic options for these rare subtypes of uterine tumors. The improved understanding of the molecular profile of these tumors has led to the development of targeted treatment approaches. Further progress will depend on a coordinated, global effort to further characterize these diseases and enroll patients on biomarker-driven clinical trials.

PMID:40340459 | DOI:10.1200/EDBK-25-473106

J Biomed Semantics. 2025 May 8;16(1):9. doi: 10.1186/s13326-025-00330-9.

ABSTRACT

BACKGROUND: The Swiss Personalized Health Network (SPHN) adopted the Resource Description Framework (RDF), a core component of the Semantic Web technology stack, for the formal encoding and exchange of healthcare data in a medical knowledge graph. The SPHN RDF Schema defines the semantics on how data elements should be represented. While RDF is proven to be machine readable and interpretable, it can be challenging for individuals without specialized background to read and understand the knowledge represented in RDF. For this reason, the semantics described in the SPHN RDF Schema are primarily defined in a user-accessible tabular format, the SPHN Dataset, before being translated into its RDF representation. However, this translation process was previously manual, time-consuming and labor-intensive.

RESULT: To automate and streamline the translation from tabular to RDF representation, the SPHN Schema Forge web service was developed. With a few clicks, this tool automatically converts an SPHN-compliant Dataset spreadsheet into an RDF schema. Additionally, it generates SHACL rules for data validation, an HTML visualization of the schema and SPARQL queries for basic data analysis.

CONCLUSION: The SPHN Schema Forge significantly reduces the manual effort and time required for schema generation, enabling researchers to focus on more meaningful tasks such as data interpretation and analysis within the SPHN framework.

PMID:40341005 | DOI:10.1186/s13326-025-00330-9

NPJ Vaccines. 2025 May 8;10(1):88. doi: 10.1038/s41541-025-01139-4.

ABSTRACT

This genome-wide association study (GWAS) explores the genetic components of severe adverse events following COVID-19 vaccination, with focus on myocarditis and pericarditis. Three SNPs (rs536572545, rs146289966 and rs142297026) near the SCAF11 gene were linked to pericarditis, while rs570375365 in the LRRC4C gene was associated with myocarditis. These findings suggest that genetic variants may influence inflammation pathways, providing a basis for further investigation into the immunological responses triggered by vaccines.

PMID:40341528 | DOI:10.1038/s41541-025-01139-4

Mol Med. 2025 May 8;31(1):179. doi: 10.1186/s10020-025-01237-y.

ABSTRACT

BACKGROUND: The remodeling of the extracellular matrix (ECM) plays a pivotal role in tumor progression and drug resistance. However, the compositional patterns of ECM in breast cancer and their underlying biological functions remain elusive.

METHODS: Transcriptome and genome data of breast cancer patients from TCGA database was downloaded. Patients were classified into different clusters by using non-negative matrix factorization (NMF) based on signatures of ECM components and regulators. Weighted Gene Co-expression Network Analysis (WGCNA) was used to identify core genes related to ECM clusters. Additional 10 independent public cohorts including Metabric, SCAN_B, GSE12276, GSE16446, GSE19615, GSE20685, GSE21653, GSE58644, GSE58812, and GSE88770 were collected to construct Training or Testing cohort, following machine learning calculating ECM correlated index (ECI) for survival analysis. Pathway enrichment and correlation analysis were used to explore the relationship among ECM clusters, ECI and TME. Single-cell transcriptome data from GSE161529 was processed for uncovering the differences among ECM clusters.

RESULTS: Using NMF, we identified three ECM clusters in the TCGA database: C1 (Neuron), C2 (ECM), and C3 (Immune). Subsequently, WGCNA was employed to pinpoint cluster-specific genes and develop a prognostic model. This model demonstrated robust predictive power for breast cancer patient survival in both the Training cohort (n = 5,392, AUC = 0.861) and the Testing cohort (n = 1,344, AUC = 0.711). Upon analyzing the tumor microenvironment (TME), we discovered that fibroblasts and B cell lineage were the core cell types associated with the ECM cluster phenotypes. Single-cell RNA sequencing data further revealed that angiopoietin like 4 (ANGPTL4)+ fibroblasts were specifically linked to the C2 phenotype, while complement factor D (CFD)+ fibroblasts characterized the other ECM clusters. CellChat analysis indicated that ANGPTL4+ and CFD+ fibroblasts regulate B cell lineage via distinct signaling pathways. Additionally, analysis using the Kaplan-Meier Plotter website showed that CFD was favorable for immunotherapy response, whereas ANGPTL4 negatively impacted the outcomes of cancer patients receiving immunotherapy.

CONCLUSION: We identified distinct ECM clusters in breast cancer patients, irrespective of molecular subtypes. Additionally, we constructed an effective prognostic model based on these ECM clusters and recognized ANGPTL4+ and CFD+ fibroblasts as potential biomarkers for immunotherapy in breast cancer.

PMID:40340806 | DOI:10.1186/s10020-025-01237-y

J Am Chem Soc. 2025 May 9. doi: 10.1021/jacs.5c00955. Online ahead of print.

ABSTRACT

Cholera is a severe infectious disease caused by the Gram-negative bacterium Vibrio cholerae after colonization in the intestinal tract. Cholera toxin (CT), a key exotoxin protein, primarily causes acute secretory diarrhea and life-threatening complications in infected patients. Traditional approaches remain insufficient for effectively treating cholera, underscoring the need for innovative countermeasures to eliminate CT-caused symptoms. Here, we report a glycan-modified cellular nanosponge for the enhanced treatment of CT-induced secretory diarrhea. Specifically, intestinal epithelial cell membrane-camouflaged nanosponges are functionalized with a glycan receptor to promote their capability for CT neutralization, thereby competitively inhibiting CT entry into host cells. Moreover, an inhibitor is encapsulated into the cellular nanosponge to synergistically improve the therapeutic effect of diarrhea by blocking the excessive chloride ion efflux from the cystic fibrosis transmembrane conductance regulator (a crucial anion channel) on the membrane of CT-intoxicated epithelial cells. Upon oral administration, the biomimetic nanomedicine effectively eliminates CT-induced secretory diarrhea and intestinal injuries in mice. Overall, this study highlights the potential of glycan-modified cellular nanosponges as promising and broad-spectrum therapeutic agents against secretory diarrhea caused by bacterial exotoxins.

PMID:40340322 | DOI:10.1021/jacs.5c00955

Sci Rep. 2025 May 8;15(1):16001. doi: 10.1038/s41598-025-98852-w.

ABSTRACT

Accurate diagnosis of orthopedic injuries, especially pelvic and hip fractures, is vital in trauma management. While pelvic radiographs (PXRs) are widely used, misdiagnosis is common. This study proposes an automated system that uses convolutional neural networks (CNNs) to detect potential fracture areas and predict fracture conditions, aiming to outperform traditional object detection-based systems. We developed two deep learning models for hip fracture detection and prediction, trained on PXRs from three hospitals. The first model utilized automated hip area detection, cropping, and classification of the resulting patches. The images were preprocessed using the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm. The YOLOv5 architecture was employed for the object detection model, while three different pre-trained deep neural network (DNN) architectures were used for classification, applying transfer learning. Their performance was evaluated on a test dataset, and compared with 35 clinicians. YOLOv5 achieved a 92.66% accuracy on regular images and 88.89% on CLAHE-enhanced images. The classifier models, MobileNetV2, Xception, and InceptionResNetV2, achieved accuracies between 94.66% and 97.67%. In contrast, the clinicians demonstrated a mean accuracy of 84.53% and longer prediction durations. The DNN models showed significantly better accuracy and speed compared to human evaluators (p < 0.0005, p < 0.01). These DNN models highlight promising utility in trauma diagnosis due to their high accuracy and speed. Integrating such systems into clinical practices may enhance the diagnostic efficiency of PXRs.

PMID:40341645 | DOI:10.1038/s41598-025-98852-w

Sci Rep. 2025 May 8;15(1):16090. doi: 10.1038/s41598-025-00017-2.

ABSTRACT

In architectural and engineering design, minimizing weight, deflection, and strain energy requires navigating complex, non-linear interactions among competing objectives, making the optimization of concrete thin shell constructions particularly challenging. Traditional multi-objective optimization (MOO) methods frequently encounter difficulties in effectively exploring design spaces, which often necessitate substantial computational resources and result in suboptimal solutions. This paper presents a novel approach for enhancing topology and thickness optimization. Graph-constrained conditional Generative Adversarial Networks (GANs) and the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) are used in the study. The hybrid approach addresses fundamental limitations in current optimization techniques by combining the generative capabilities of deep learning with the refinement processes of evolutionary algorithms. NSGA-II enhances the algorithm by employing evolutionary processes to generate various structural designs that adhere to topological constraints. Specialized graph-constrained GANs accomplish this. The implementation of the system in a concrete thin shell structure at the Shenzhen Qianhai Smart Community resulted in significant performance improvements: a 33.3% reduction in total weight, a 50% decrease in maximum deflection, and a 20% reduction in strain energy compared to baseline models. A comparative comparison of traditional NSGA-II techniques shows substantial benefits, including a 50% enhancement in convergence speed and notable advancements in solution diversity and quality. We confirmed structural integrity through extensive finite element analysis and practical prototyping, achieving performance variations under 3.5%. This work illustrates the potential of sophisticated machine learning and evolutionary algorithms to produce innovative, high-performance architectural solutions, thereby providing a new methodology for structural optimization.

PMID:40341580 | DOI:10.1038/s41598-025-00017-2

Sci Rep. 2025 May 8;15(1):16087. doi: 10.1038/s41598-025-00374-y.

ABSTRACT

Indoor activity monitoring methods assurance the well-being and security of disabled and aging individuals living in their homes. These models utilize numerous technologies and sensors to monitor day-to-day work like movement, medication adherence, and sleep patterns, and provide valued perceptions of the user's everyday life and entire health. Internet of Things (IoT) based health systems have an important part in medical assistance and help in enhancing data processing and its prediction. Communicating data or reports requires more time and energy, in addition to causing energy problems and greater latency. Currently, numerous studies focus on human activity recognition (HAR) using deep learning (DL) and machine learning (ML) methods, but more effort is needed to enhance HAR models for disabled individuals. Therefore, this article presents a Smart Indoor Monitoring for Disabled People Using an Ensemble of Deep Learning Models in an Internet of Things Environment (SIMDP-EDLIoT) technique. The SIMDP-EDLIoT model is designed to monitor and detect various conditions and activities within indoor spaces for disabled people. Initially, the SIMDP-EDLIoT approach uses linear scaling normalization (LSN) to ensure that the input data is scaled appropriately. Besides, the Improved Osprey Optimization Algorithm (IOOA)-based feature selection is employed to classify the most relevant features, enhancing the efficiency of the system by reducing dimensionality. For monitoring indoor activities, an ensemble of three DL techniques such as bidirectional long short-term memory (BiLSTM), gated recurrent unit (GRU), and conditional variational autoencoder (CVAE) are employed. Experimental study is performed to underscore the importance of the SIMDP-EDLIoT method under the HAR dataset. The comparative analysis of the SIMDP-EDLIoT method demonstrated a superior performance with an accuracy of 98.85%, precision of 97.71%, sensitivity of 97.70%, specificity of 99.24%, and F-measure of 97.70%, outperforming existing approaches across all metrics.

PMID:40341573 | DOI:10.1038/s41598-025-00374-y

J Microsc. 2025 May 8. doi: 10.1111/jmi.13423. Online ahead of print.

ABSTRACT

Atomic force microscopy (AFM) plays a pivotal role in cell biology research. It enables scientists to observe the morphology of cell surfaces at the nanoscale, providing essential data for understanding cellular functions, including cell-cell interactions and responses to the microenvironment. Nevertheless, AFM-captured cell images frequently suffer from artefacts, which significantly hinder detailed analyses of cell structures. In this study, we developed a cross-module resolution enhancement method for post-processing AFM cell images. The method leverages the AFM topological deep learning neural network. We propose an enhanced spatial fusion structure and an optimised back-projection mechanism within an adversarial-based super-resolution network to detect weak signals and complex textures unique to AFM cell images. Furthermore, we designed a crossover-based frequency division module, capitalising on the distinct frequency characteristics of AFM images. This module effectively separates and enhances features pertinent to cell structure. In this paper, experiments were conducted using AFM images of various cells, and the results demonstrated the model's superiority. It substantially enhances image quality compared to existing methods. Specifically, the peak signal-to-noise ratio (PSNR) of the reconstructed image increased by 1.65 decibels, from 28.121 to 29.771, the structural similarity (SSIM) increased by 0.041, from 0.746 to 0.787, the Learned Perceptual Image Patch Similarity (LPIPS) decreased by 0.205, from 0.437 to 0.232, the Fréchet Inception Distance (FID) decreased by 6.996, from 55.442 to 48.446 and the Natural Image Quality Evaluator (NIQE) decreased by 0.847, from 4.296 to 3.449. Lay abstract: This study proposes a deep learning-based cross-module method for super-resolving AFM cell images, integrating frequency division and adaptive fusion modules. It boosts PSNR by 1.65 dB and SSIM by 0.041, accurately recovering cellular microstructures, thus significantly aiding cell biology research and biomedicine applications.

PMID:40341533 | DOI:10.1111/jmi.13423

Nat Commun. 2025 May 8;16(1):4276. doi: 10.1038/s41467-025-59523-6.

ABSTRACT

Human-machine voice interaction based on speech recognition offers an intuitive, efficient, and user-friendly interface, attracting wide attention in applications such as health monitoring, post-disaster rescue, and intelligent control. However, conventional microphone-based systems remain challenging for complex human-machine collaboration in noisy environments. Herein, an anti-noise triboelectric acoustic sensor (Anti-noise TEAS) based on flexible nanopillar structures is developed and integrated with a convolutional neural network-based deep learning model (Anti-noise TEAS-DLM). This highly synergistic system enables robust acoustic signal recognition for human-machine collaboration in complex, noisy scenarios. The Anti-noise TEAS directly captures acoustic fundamental frequency signals from laryngeal mixed-mode vibrations through contact sensing, while effectively suppressing environmental noise by optimizing device-structure buffering. The acoustic signals are subsequently processed and semantically decoded by the DLM, ensuring high-fidelity interpretation. Evaluated in both simulated virtual and real-life noisy environments, the Anti-noise TEAS-DLM demonstrates near-perfect noise immunity and reliably transmits various voice commands to guide robotic systems in executing complex post-disaster rescue tasks with high precision. The combined anti-noise robustness and execution accuracy endow this DLM-enhanced Anti-noise TEAS as a highly promising platform for next-generation human-machine collaborative systems operating in challenging noisy environments.

PMID:40341503 | DOI:10.1038/s41467-025-59523-6

Int J Comput Assist Radiol Surg. 2025 May 8. doi: 10.1007/s11548-025-03382-5. Online ahead of print.

ABSTRACT

PURPOSE: Identifying and quantifying coronary artery calcification (CAC) is crucial for preoperative planning, as it helps to estimate both the complexity of the 2D coronary angiography (2DCA) procedure and the risk of developing intraoperative complications. Despite the relevance, the actual practice relies upon visual inspection of the 2DCA image frames by clinicians. This procedure is prone to inaccuracies due to the poor contrast and small size of the CAC; moreover, it is dependent on the physician's experience. To address this issue, we developed a workflow to assist clinicians in identifying CAC within 2DCA using data from 44 image acquisitions across 14 patients.

METHODS: Our workflow consists of three stages. In the first stage, a classification backbone based on ResNet-18 is applied to guide the CAC identification by extracting relevant features from 2DCA frames. In the second stage, a U-Net decoder architecture, mirroring the encoding structure of the ResNet-18, is employed to identify the regions of interest (ROI) of the CAC. Eventually, a post-processing step refines the results to obtain the final ROI. The workflow was evaluated using a leave-out cross-validation.

RESULTS: The proposed method outperformed the comparative methods by achieving an F1-score for the classification step of 0.87 (0.77 - 0.94) (median ± quartiles), while for the CAC identification step the intersection over minimum (IoM) was 0.64 (0.46 - 0.86) (median ± quartiles).

CONCLUSION: This is the first attempt to propose a clinical decision support system to assist the identification of CAC within 2DCA. The proposed workflow holds the potential to improve both the accuracy and efficiency of CAC quantification, with promising clinical applications. As future work, the concurrent use of multiple auxiliary tasks could be explored to further improve the segmentation performance.

PMID:40341465 | DOI:10.1007/s11548-025-03382-5

Sci Rep. 2025 May 8;15(1):16042. doi: 10.1038/s41598-025-01120-0.

ABSTRACT

With the increasing urbanization in China, monitoring and predicting the deformation of deep excavations has become increasingly critical. Concurrently, as neural network models find application and development in deep excavation displacement prediction, traditional models face challenges such as insufficient accuracy and weak generalization capabilities, failing to meet the high-precision warning demands of practical engineering. Therefore, research into hybrid models is necessary. This study proposes a combined neural network model integrating a Convolutional Neural Network, Long Short-Term Memory network, and Self-Attention Mechanism (CNN-LSTM-SAM), which utilizes time-series monitoring data as input. The CNN-LSTM-SAM model merges the data feature extraction capabilities of CNN, the long-term memory function of LSTM, and the information weighting capacity of the self-attention mechanism, synthesizing the advantages of various deep excavation displacement prediction models to enhance prediction accuracy and provide more effective support for construction practice. Furthermore, given the limited application of the CNN-LSTM-SAM model in deep excavation displacement analysis, this research contributes to addressing gaps in this field. Applied to an internally braced deep excavation project in the Donggang Business District of Dalian, displacement data acquired through Distributed Fiber Optic Sensing (DFOS) technology were used as training data. The CNN-LSTM-SAM model was employed to predict the horizontal displacement at the pile top. The resulting deformation predictions were compared and analyzed against those from Back Propagation (BP) neural network, Long Short-Term Memory (LSTM) network, and a combined Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model. Results indicate that at monitoring point S5, the coefficient of determination (R2) for the CNN-LSTM-SAM model's predictions increased by 12.42%, 10.85%, and 5.63% compared to the BP, LSTM, and CNN-LSTM models, respectively, demonstrating higher accuracy than the other three models. Similar patterns were observed when training and predicting using data from other monitoring points, proving the applicability and robustness of the CNN-LSTM-SAM model. The findings of this study offer valuable references for the design and construction of similar deep excavation projects.

PMID:40341437 | DOI:10.1038/s41598-025-01120-0

Bioinformatics. 2025 May 8:btaf275. doi: 10.1093/bioinformatics/btaf275. Online ahead of print.

ABSTRACT

MOTIVATION: Molecular property prediction with deep learning has accelerated drug discovery and retrosynthesis. However, the shortage of labeled molecular data and the challenge of generalizing across the vast chemical spaces pose significant hurdles for leveraging deep learning in molecular property prediction. This study proposes a self-supervised framework designed to acquire a Simplified Molecular Input Line Entry System (SMILES) representation, which we have dubbed "SimSon" (Simple SMILES contrastive learning). SimSon was pre-trained using unlabeled SMILES data through contrastive learning to grasp the SMILES representations.

RESULTS: Our findings demonstrate that contrastive learning with randomized SMILES enriches the ability of the model to generalize and its robustness as it captures the global semantic context at the molecular level. In downstream tasks, SimSon performs competitively when compared to graph-based methods and even outperforms them on certain benchmark datasets. These results indicate that SimSon effectively captures structural information from SMILES, exhibiting remarkable generalization and robustness. The potential applications of SimSon extend to bioinformatics and cheminformatics, encompassing areas such as drug discovery and drug-drug interaction prediction.

AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/lee00206/SimSon.

SUPPLEMENTARY INFORMATION: Supplementary information is available at Bioinformatics online.

PMID:40341364 | DOI:10.1093/bioinformatics/btaf275