Literature Watch

Discovery of Z1362873773: a novel fascin inhibitor from a large chemical library for colorectal cancer

Pharmacogenomics - Mon, 2025-04-28 06:00

Sci Rep. 2025 Apr 28;15(1):14906. doi: 10.1038/s41598-025-96457-x.

ABSTRACT

Metastasis is one of the leading causes of cancer-related death worldwide. Fascin, a protein that bundles actin filaments to produce protrusions in cancer cells, plays a significant role in the enhancement of cell migration. This protein has been shown that the overexpression of this protein is related to the appearance of different types of cancer, such as colorectal cancer. In this study, we conducted in silico screening of the Enamine library, a compound library with a broad chemical space. Using a ligand-based virtual screening approach based on the pharmacophore model of G2, we identified the predicted inhibitors. First, these compounds were validated by physicochemical analysis. Differential scanning calorimetry (DSF) was used to study the binding between the predicted compounds and fascin protein, followed by an F-actin bundling assay to determine which compounds inhibited the bundling function of fascin. Z1362873773, which exhibited binding to fascin and inhibited F-actin bundling, was further tested in cell cultures to assess its effects on cancer cell viability and migration as well as in organoid models to evaluate potential cytotoxicity. Finally, we established a protocol that can be applied to discover anti-fascin agents from diverse compound libraries. A new molecule has been identified with considerable fascin inhibitory and migration-arresting capacity, which may lead to the development of new therapies to treat cancer.

PMID:40295602 | DOI:10.1038/s41598-025-96457-x

Categories: Literature Watch

How equipped are pharmacists for pharmacogenomics?: A cross-sectional study on knowledge, attitudes, and implementation practices in Saudi Arabia

Pharmacogenomics - Mon, 2025-04-28 06:00

Medicine (Baltimore). 2025 Apr 25;104(17):e42240. doi: 10.1097/MD.0000000000042240.

ABSTRACT

Pharmacogenomics, the study of genetic influences on drug response, advances personalized medicine by tailoring therapy to individual genetic profiles, reducing adverse effects and optimizing efficacy. Pharmacists, as accessible healthcare providers, are well-positioned to facilitate the integration of pharmacogenomics into clinical practice. This study assesses Saudi pharmacists' knowledge, attitudes, and practices regarding pharmacogenomics and identifies key barriers and facilitators affecting their readiness. A cross-sectional survey was conducted between July and October 2024 among 426 licensed pharmacists across various practice settings in Saudi Arabia: a validated, structured questionnaire assessed demographics, pharmacogenomics knowledge, attitudes, and implementation practices. Snowball sampling facilitated participant recruitment. Descriptive statistics summarized the findings, and Chi-square tests were applied to examine associations between socio-demographic variables and pharmacogenomics-related responses. Among 426 participants, while most pharmacists recognized the value of pharmacogenomics, knowledge gaps were notable, particularly in interpreting genetic tests and applying clinical recommendations. Only 52.3% received pharmacogenomics training, mainly through university courses, and 40.6% had never consulted pharmacogenomics resources in practice. Key barriers included limited access to genetic testing (74.2%) and lack of reimbursement (64.5%). Socio-demographics, such as age and practice setting, significantly impacted knowledge and attitudes. Saudi pharmacists face considerable barriers to pharmacogenomics readiness, including knowledge gaps, limited access to genetic testing, and insufficient institutional support. Addressing these challenges requires targeted education, structured policy initiatives, and enhanced resource availability to facilitate the effective integration of pharmacogenomics into pharmacy practice. Strengthening pharmacists' competencies in this field will be essential to optimizing patient care and advancing precision medicine in Saudi Arabia.

PMID:40295244 | DOI:10.1097/MD.0000000000042240

Categories: Literature Watch

Recommended gentamicin peak plasma levels rarely reached, even with recommended dosages

Pharmacogenomics - Mon, 2025-04-28 06:00

Infect Dis Now. 2025 Apr 26:105076. doi: 10.1016/j.idnow.2025.105076. Online ahead of print.

ABSTRACT

INTRODUCTION: The recommended gentamicin peak plasma concentration range is 32-40 mg/L; we aimed to determine how frequently it was reached, and for which gentamicin doses.

PATIENTS AND METHODS: We retrospectively reviewed 601 gentamicin peak plasma concentrations in 501 patients aged ≥15 in our institution between 2013 and 2023.

RESULTS: Median gentamicin dose was 5.9 mg/kg [IQR 4.1-7.9]. Median peak plasma concentration was 16.5 mg/L [IQR 10.8-22.8] and was strongly correlated with dose (p < 0.0001). Only 5.7 % of values were ≥32 mg/L, including 22.8 % for dose ≥10 mg/kg.

CONCLUSION: This suggests that existing recommendations regarding either dose or target concentration for gentamicin should be modified.

PMID:40294703 | DOI:10.1016/j.idnow.2025.105076

Categories: Literature Watch

Trojan Horse-Like Vehicles for CRISPR-Cas Delivery: Engineering Extracellular Vesicles and Virus-Like Particles for Precision Gene Editing in Cystic Fibrosis

Cystic Fibrosis - Mon, 2025-04-28 06:00

Hum Gene Ther. 2025 Apr 28. doi: 10.1089/hum.2024.258. Online ahead of print.

ABSTRACT

The advent of genome editing has kindled the hope to cure previously uncurable, life-threatening genetic diseases. However, whether this promise can be ultimately fulfilled depends on how efficiently gene editing agents can be delivered to therapeutically relevant cells. Over time, viruses have evolved into sophisticated, versatile, and biocompatible nanomachines that can be engineered to shuttle payloads to specific cell types. Despite the advances in safety and selectivity, the long-term expression of gene editing agents sustained by viral vectors remains a cause for concern. Cell-derived vesicles (CDVs) are gaining traction as elegant alternatives. CDVs encompass extracellular vesicles (EVs), a diverse set of intrinsically biocompatible and low-immunogenic membranous nanoparticles, and virus-like particles (VLPs), bioparticles with virus-like scaffold and envelope structures, but devoid of genetic material. Both EVs and VLPs can efficiently deliver ribonucleoprotein cargo to the target cell cytoplasm, ensuring that the editing machinery is only transiently active in the cell and thereby increasing its safety. In this review, we explore the natural diversity of CDVs and their potential as delivery vectors for the clustered regularly interspaced short palindromic repeats (CRISPR) machinery. We illustrate different strategies for the optimization of CDV cargo loading and retargeting, highlighting the versatility and tunability of these vehicles. Nonetheless, the lack of robust and standardized protocols for CDV production, purification, and quality assessment still hinders their widespread adoption to further CRISPR-based therapies as advanced "living drugs." We believe that a collective, multifaceted effort is urgently needed to address these critical issues and unlock the full potential of genome-editing technologies to yield safe, easy-to-manufacture, and pharmacologically well-defined therapies. Finally, we discuss the current clinical landscape of lung-directed gene therapies for cystic fibrosis and explore how CDVs could drive significant breakthroughs in in vivo gene editing for this disease.

PMID:40295092 | DOI:10.1089/hum.2024.258

Categories: Literature Watch

Segmentation-assisted vessel centerline extraction from cerebral CT Angiography

Deep learning - Mon, 2025-04-28 06:00

Med Phys. 2025 Apr 28. doi: 10.1002/mp.17855. Online ahead of print.

ABSTRACT

BACKGROUND: The accurate automated extraction of brain vessel centerlines from Computed tomographic angiography (CTA) images plays an important role in diagnosing and treating cerebrovascular diseases such as stroke. Despite its significance, this task is complicated by the complex cerebrovascular structure and heterogeneous imaging quality.

PURPOSE: This study aims to develop and validate a segmentation-assisted framework designed to improve the accuracy and efficiency of brain vessel centerline extraction from CTA images. We streamline the process of lumen segmentation generation without additional annotation effort from physicians, enhancing the effectiveness of centerline extraction.

METHODS: The framework integrates four modules: (1) pre-processing techniques that register CTA images with a CT atlas and divide these images into input patches, (2) lumen segmentation generation from annotated vessel centerlines using graph cuts and robust kernel regression, (3) a dual-branch topology-aware UNet (DTUNet) that optimizes the use of the annotated vessel centerlines and the generated lumen segmentation via a topology-aware loss (TAL) and its dual-branch structure, and (4) post-processing methods that skeletonize and refine the lumen segmentation predicted by the DTUNet.

RESULTS: An in-house dataset derived from a subset of the MR CLEAN Registry is used to evaluate the proposed framework. The dataset comprises 10 intracranial CTA images, and 40 cube CTA sub-images with a resolution of 128 × 128 × 128 $128 \times 128 \times 128$ voxels. Via five-fold cross-validation on this dataset, we demonstrate that the proposed framework consistently outperforms state-of-the-art methods in terms of average symmetric centerline distance (ASCD) and overlap (OV). Specifically, it achieves an ASCD of 0.84, an OV 1.0 $\textrm {OV}_{1.0}$ of 0.839, and an OV 1.5 $\textrm {OV}_{1.5}$ of 0.885 for intracranial CTA images, and obtains an ASCD of 1.26, an OV 1.0 $\textrm {OV}_{1.0}$ of 0.779, and an OV 1.5 $\textrm {OV}_{1.5}$ of 0.824 for cube CTA sub-images. Subgroup analyses further suggest that the proposed framework holds promise in clinical applications for stroke diagnosis and treatment.

CONCLUSIONS: By automating the process of lumen segmentation generation and optimizing the network design of vessel centerline extraction, DTUnet achieves high performance without introducing additional annotation demands. This solution promises to be beneficial in various clinical applications in cerebrovascular disease management.

PMID:40296200 | DOI:10.1002/mp.17855

Categories: Literature Watch

Multi-sequence brain tumor segmentation boosted by deep semantic features

Deep learning - Mon, 2025-04-28 06:00

Med Phys. 2025 Apr 28. doi: 10.1002/mp.17845. Online ahead of print.

ABSTRACT

BACKGROUND: The main task of deep learning (DL) based brain tumor segmentation is to get accurate projection from learned image features to their corresponding semantic labels (i.e., brain tumor sub-regions). To achieve this goal, segmentation networks are required to learn image features with high intra-class consistency. However, brain tumor are known to be heterogeneous, and it often causes high diversity in image gray values which further influences the learned image features. Therefore, projecting such diverse image features (i.e., low intra-class consistency) to the same semantic label is often difficult and inefficient.

PURPOSE: The purpose of this study is to address the issue of low intra-class consistency of image features learned from heterogeneous brain tumor regions and ease the projection of image features to their corresponding semantic labels. In this way, accurate segmentation of brain tumor can be achieved.

METHODS: We propose a new DL-based method for brain tumor segmentation, where a semantic feature module (SFM) is introduced to consolidate image features with meaningful semantic information and enhance their intra-class consistency. Specifically, in the SFM, deep semantic vectors are derived and used as prototypes to re-encode image features learned in the segmentation network. Since the relatively consistent deep semantic vectors, diversity of the resulting image features can be reduced; moreover, semantic information in the resulting image features can also be enriched, both facilitating accurate projection to the final semantic labels.

RESULTS: In the experiment, a public brain tumor dataset, BraTS2022 containing, multi-sequence MR images of 1251 patients is used to evaluate our method in the task of brain tumor sub-region segmentation, and the experimental results demonstrate that, benefiting from the SFM, our method outperforms the state-of-the-art methods with statistical significance ( p < 0.05 $p<0.05$ using the Wilcoxon signed rank test). Further ablation study shows that the proposed SFM can yield an improvement in segmentation accuracy (Dice index) of up to 11% comparing with that without the SFM.

CONCLUSIONS: In DL-based segmentation, low intra-class consistency of learned image features degrades segmentation performance. The proposed SFM can effectively enhance the intra-class consistency with high-level semantic information, making the projection of image features to their corresponding semantic labels more accurate.

PMID:40296197 | DOI:10.1002/mp.17845

Categories: Literature Watch

Singular value decomposition based under-sampling pattern optimization for MRI reconstruction

Deep learning - Mon, 2025-04-28 06:00

Med Phys. 2025 Apr 28. doi: 10.1002/mp.17860. Online ahead of print.

ABSTRACT

BACKGROUND: Magnetic resonance imaging (MRI) is a crucial medical imaging technique that can determine the structural and functional status of body tissues and organs. However, the prolonged MRI acquisition time increases the scanning cost and limits its use in less developed areas.

PURPOSE: The objective of this study is to design a lightweight, data-driven under-sampling pattern for fastMRI to achieve a balance between MRI reconstruction quality and sampling time while also being able to be integrated with deep learning to further improve reconstruction quality.

METHODS: In this study, we attempted to establish a connection between k-space and the corresponding MRI through singular value decomposition(SVD). Specifically, we apply SVD to MRI to decouple it into multiple components, which are sorted by energy contribution. Then, the sampling points that match the energy contribution in the k-space, which correspond to each component are selected sequentially. Finally, the sampling points obtained from all components are merged to obtain a mask. This mask can be used directly as a sampler or integrated into deep learning as an initial or fixed sampling points.

RESULTS: The experiments were conducted on two public datasets, and the results demonstrate that when the mask generated based on our method is directly used as the sampler, the MRI reconstruction quality surpasses that of state-of-the-art heuristic samplers. In addition, when integrated into the deep learning models, the models converge faster and the sampler performance is significantly improved.

CONCLUSIONS: The proposed lightweight data-driven sampling approach avoids time-consuming parameter tuning and the establishment of complex mathematical models, achieving a balance between reconstruction quality and sampling time.

PMID:40296184 | DOI:10.1002/mp.17860

Categories: Literature Watch

Deep learning-based tennis match type clustering

Deep learning - Mon, 2025-04-28 06:00

BMC Sports Sci Med Rehabil. 2025 Apr 28;17(1):104. doi: 10.1186/s13102-025-01147-w.

ABSTRACT

BACKGROUND: This study aims to define and cluster tennis match types based on how they are played.

METHODS: The research data selected for this study were from the 100th round of 32 matches of the five finals of the 2023 International Tennis Open Tournament. Based on expert knowledge and sports expertise, 27 variables were included across seven areas. Three models were applied and the silhouette coefficient was calculated to identify the optimal number of clusters. A difference test was conducted on the game record variables based on the cluster results.

RESULTS: Calculation of the silhouette coefficients for the three models showed that Model 3 (silhouette coefficient: 0.406) had the highest performance. The clustering results for the tennis match types are as follows. First, the NEt Rusher Defensive type, which is defensive and induces net play. Second, the ALl Courter Defensive type, which is either defensive or all-round. Third, the STroke Placement Offensive type, which is aggressive and has strengths in stroke. Fourth, the SErve Placement Offensive type, which is aggressive and has strengths in sub courses.

CONCLUSION: This study's findings are not only provide basic data to cluster game types in tennis matches but also to contribute to establishing game strategies for each game type, thereby further improving performance.

PMID:40296175 | DOI:10.1186/s13102-025-01147-w

Categories: Literature Watch

Intermittent hypoxemia during hemodialysis: AI-based identification of arterial oxygen saturation saw-tooth pattern

Deep learning - Mon, 2025-04-28 06:00

BMC Nephrol. 2025 Apr 28;26(1):214. doi: 10.1186/s12882-025-04133-z.

ABSTRACT

BACKGROUND: Maintenance hemodialysis patients experience high morbidity and mortality, primarily from cardiovascular and infectious diseases. It was discovered recently that low arterial oxygen saturation (SaO2) is associated with a pro-inflammatory phenotype and poor patient outcomes. Sleep apnea is highly prevalent in maintenance hemodialysis patients and may contribute to intradialytic hypoxemia. In sleep apnea, normal respiration patterns are disrupted by episodes of apnea because of either disturbed respiratory control (i.e., central sleep apnea) or upper airway obstruction (i.e., obstructive sleep apnea). Intermittent SaO2 saw-tooth patterns are a hallmark of sleep apnea. Continuous intradialytic measurements of SaO2 provide an opportunity to follow the temporal evolution of SaO2 during hemodialysis. Using artificial intelligence, we aimed to automatically identify patients with repetitive episodes of intermittent SaO2 saw-tooth patterns.

METHODS: The analysis utilized intradialytic SaO2 measurements by the Crit-Line device (Fresenius Medical Care, Waltham, MA). In patients with an arterio-venous fistula as vascular access, this FDA approved device records 150 SaO2 measurements per second in the extracorporeal blood circuit of the hemodialysis system. The average SaO2 of a 10-second segment is computed and streamed to the cloud. Periods comprising thirty 10-second segments (i.e., 300 s or five minutes) were independently adjudicated by two researchers for the presence or absence of SaO2 saw-tooth pattern. We built one-dimensional convolutional neural networks (1D-CNN), a state-of-the-art deep learning method, for SaO2 pattern classification and randomly assigned SaO2 time series segments to either a training (80%) or a test (20%) set.

RESULTS: We analyzed 4,075 consecutive 5-minute segments from 89 hemodialysis treatments in 22 hemodialysis patients. While 891 (21.9%) segments showed saw-tooth pattern, 3,184 (78.1%) did not. In the test data set, the rate of correct SaO2 pattern classification was 96% with an area under the receiver operating curve of 0.995 (95% CI: 0.993 to 0.998).

CONCLUSION: Our 1D-CNN algorithm accurately classifies SaO2 saw-tooth pattern. The SaO2 pattern classification can be performed in real time during an ongoing hemodialysis treatment, provide timely alert in the event of respiratory instability or sleep apnea, and trigger further diagnostic and therapeutic interventions.

PMID:40295983 | DOI:10.1186/s12882-025-04133-z

Categories: Literature Watch

(18)F-FDG PET/CT-based deep learning models and a clinical-metabolic nomogram for predicting high-grade patterns in lung adenocarcinoma

Deep learning - Mon, 2025-04-28 06:00

BMC Med Imaging. 2025 Apr 28;25(1):138. doi: 10.1186/s12880-025-01684-3.

ABSTRACT

BACKGROUND: To develop and validate deep learning (DL) and traditional clinical-metabolic (CM) models based on 18 F-FDG PET/CT images for noninvasively predicting high-grade patterns (HGPs) of invasive lung adenocarcinoma (LUAD).

METHODS: A total of 303 patients with invasive LUAD were enrolled in this retrospective study; these patients were randomly divided into training, validation and test sets at a ratio of 7:1:2. DL models were trained and optimized on PET, CT and PET/CT fusion images, respectively. CM model was built from clinical and PET/CT metabolic parameters via backwards stepwise logistic regression and visualized via a nomogram. The prediction performance of the models was evaluated mainly by the area under the curve (AUC). We also compared the AUCs of different models for the test set.

RESULTS: CM model was established upon clinical stage (OR: 7.30; 95% CI: 2.46-26.37), cytokeratin 19 fragment 21 - 1 (CYFRA 21-1, OR: 1.18; 95% CI: 0.96-1.57), mean standardized uptake value (SUVmean, OR: 1.31; 95% CI: 1.17-1.49), total lesion glycolysis (TLG, OR: 0.994; 95% CI: 0.990-1.000) and size (OR: 1.37; 95% CI: 0.95-2.02). Both the DL and CM models exhibited good prediction efficacy in the three cohorts, with AUCs ranging from 0.817 to 0.977. For the test set, the highest AUC was yielded by the CT-DL model (0.895), followed by the PET/CT-DL model (0.882), CM model (0.879) and PET-DL model (0.817), but no significant difference was revealed between any two models.

CONCLUSIONS: Deep learning and clinical-metabolic models based on the 18F-FDG PET/CT model could effectively identify LUAD patients with HGP. These models could aid in treatment planning and precision medicine.

CLINICAL TRIAL NUMBER: Not applicable.

PMID:40295979 | DOI:10.1186/s12880-025-01684-3

Categories: Literature Watch

Research on noninvasive electrophysiologic imaging based on cardiac electrophysiology simulation and deep learning methods for the inverse problem

Deep learning - Mon, 2025-04-28 06:00

BMC Cardiovasc Disord. 2025 Apr 28;25(1):335. doi: 10.1186/s12872-025-04728-2.

ABSTRACT

BACKGROUND: The risk stratification and prognosis of cardiac arrhythmia depend on the individual condition of patients, while invasive diagnostic methods may be risky to patient health, and current non-invasive diagnostic methods are applicable to few disease types without sensitivity and specificity. Cardiac electrophysiologic imaging (ECGI) technology reflects cardiac activities accurately and non-invasively, which is of great significance for the diagnosis and treatment of cardiac diseases. This paper aims to provide a new solution for the realization of ECGI by combining simulation model and deep learning methods.

METHODS: A complete three-dimensional bidomain cardiac electrophysiologic activity model was constructed, and simulated electrocardiogram data were obtained as training samples. Particle swarm optimization-back propagation neural network, convolutional neural network, and long short-term memory network were used respectively to reconstruct the cardiac surface potential.

RESULTS: The correlation coefficients between the simulation results and the clinical data range from 75.76 to 84.61%. The P waves, PR intervals, QRS complex, and T waves in the simulated waveforms were within the normal clinical range, and the distribution trend of the simulated body surface potential mapping was consistent with the clinical data. The coefficient of determination R2 between the reconstruction results of all the algorithms and the true value is above 0.80, and the mean absolute error is below 2.1 mV, among which the R2 of long short-term memory network is about 0.99 and the mean absolute error about 0.5 mV.

CONCLUSIONS: The electrophysiologic model constructed in this study can reflect cardiac electrical activity, and contains the mapping relationship between the cardiac potential and the body surface potential. In cardiac potential reconstruction, long short-term memory network has significant advantages over other algorithms.

CLINICAL TRIAL NUMBER: Not applicable.

PMID:40295939 | DOI:10.1186/s12872-025-04728-2

Categories: Literature Watch

Impact of fine-tuning parameters of convolutional neural network for skin cancer detection

Deep learning - Mon, 2025-04-28 06:00

Sci Rep. 2025 Apr 28;15(1):14779. doi: 10.1038/s41598-025-99529-0.

ABSTRACT

Melanoma skin cancer is a deadly disease with a high mortality rate. A prompt diagnosis can aid in the treatment of the disease and potentially save the patient's life. Artificial intelligence methods can help diagnose cancer at a rapid speed. The literature has employed numerous Machine Learning (ML) and Deep Learning (DL) algorithms to detect skin cancer. ML algorithms perform well for small datasets but cannot comprehend larger ones. Conversely, DL algorithms exhibit strong performance on large datasets but misclassify when applied to smaller ones. We conduct extensive experiments using a convolutional neural network (CNN), varying its parameter values to determine which set of values yields the best performance measure. We discovered that adding layers, making each Conv2D layer have multiple filters, and getting rid of dropout layers greatly improves the accuracy of the classifiers, going from 62.5% to 85%. We have also discussed the parameters that have the potential to significantly impact the model's performance. This shows how powerful it is to fine-tune the parameters of a CNN-based model. These findings can assist researchers in fine-tuning their CNN-based models for use with skin cancer image datasets.

PMID:40295678 | DOI:10.1038/s41598-025-99529-0

Categories: Literature Watch

Optimizing photovoltaic integration in grid management via a deep learning-based scenario analysis

Deep learning - Mon, 2025-04-28 06:00

Sci Rep. 2025 Apr 28;15(1):14851. doi: 10.1038/s41598-025-98724-3.

ABSTRACT

Addressing the challenges of integrating photovoltaic (PV) systems into power grids, this research develops a dual-phase optimization model incorporating deep learning techniques. Given the fluctuating nature of solar energy, the study employs Generative Adversarial Networks (GANs) to simulate diverse and high-resolution energy generation-consumption patterns. These synthetic scenarios are subsequently utilized within a real-time adaptive control framework, allowing for dynamic adjustments in operational strategies that enhance both efficiency and grid stability. By leveraging this approach, the model has demonstrated substantial improvements in economic and environmental performance, achieving up to 96% efficiency while reducing energy expenses by 20%, lowering carbon emissions by 30%, and cutting annual operational downtime by half (from 120 to 60 h). Through a scenario-driven predictive analysis, this framework provides data-driven optimization for energy systems, strengthening their resilience against renewable energy intermittency. Furthermore, the integration of AI-enhanced forecasting techniques ensures proactive decision-making, supporting a sustainable transition toward greener energy solutions.

PMID:40295668 | DOI:10.1038/s41598-025-98724-3

Categories: Literature Watch

SkinEHDLF a hybrid deep learning approach for accurate skin cancer classification in complex systems

Deep learning - Mon, 2025-04-28 06:00

Sci Rep. 2025 Apr 28;15(1):14913. doi: 10.1038/s41598-025-98205-7.

ABSTRACT

Skin cancer represents a significant global public health issue, and prompt and precise detection is essential for effective treatment. This study introduces SkinEHDLF, an innovative deep-learning model that enhances skin cancer classification. SkinEHDLF utilizes the advantages of several advanced models, i.e., ConvNeXt, EfficientNetV2, and Swin Transformer, while integrating an adaptive attention-based feature fusion mechanism to enhance the synthesis of acquired features. This hybrid methodology combines ConvNeXt's proficient feature extraction capabilities, EfficientNetV2's scalability, and Swin Transformer's long-range attention mechanisms, resulting in a highly accurate and dependable model. The adaptive attention mechanism dynamically optimizes feature fusion, enabling the model to focus on the most relevant information, enhancing accuracy and reducing false positives. We trained and evaluated SkinEHDLF using the ISIC 2024 dataset, which comprises 401,059 skin lesion images extracted from 3D total-body photography. The dataset is divided into three categories: melanoma, benign lesions, and noncancerous skin anomalies. The findings indicate the superiority of SkinEHDLF compared to current models. In binary skin cancer classification, SkinEHDLF surpassed baseline models, achieving an AUROC of 99.8% and an accuracy of 98.76%. The model attained 98.6% accuracy, 97.9% precision, 97.3% recall, and 99.7% AUROC across all lesion categories in multi-class classification. SkinEHDLF demonstrates a 7.9% enhancement in accuracy and a 28% decrease in false positives, outperforming leading models including ResNet-50, EfficientNet-B3, ViT-B16, and hybrid methodologies such as ResNet-50 + EfficientNet and ViT + CNN, thereby positioning itself as a more precise and reliable solution for automated skin cancer detection. These findings underscore SkinEHDLF's capacity to transform dermatological diagnostics by providing a scalable and accurate method for classifying skin cancer.

PMID:40295588 | DOI:10.1038/s41598-025-98205-7

Categories: Literature Watch

Dysregulated metabolic pathways of pulmonary fibrosis and the lipids associated with the effects of nintedanib therapy

Idiopathic Pulmonary Fibrosis - Mon, 2025-04-28 06:00

Respir Res. 2025 Apr 28;26(1):166. doi: 10.1186/s12931-025-03239-0.

ABSTRACT

BACKGROUND: Pulmonary fibrosis (PF) is a disease with a poor prognosis, and its pathogenesis is not fully understood. Identifying dysregulation of lipid metabolism in PF may provide insight and promote the development of novel therapies. The present study was designed to clarify the dysregulated lipid pathways and identify lipids correlated with treatment response.

METHODS: This research comprised two prospective cohort studies. Study 1 aimed to identify dysregulated metabolic pathways and lipids in the peripheral blood of PF patients, compared with healthy control (HC) subjects. Study 2 aimed to identify lipids associated with the decline in % forced vital capacity (%FVC) and survival in PF patients treated with the anti-fibrotic drug, nintedanib. As a preliminary ancillary experiment, we attempted to identify the lipids associated with endothelial cells and fibroblasts.

RESULTS: In Study 1, 38 lipids were identified that differed between the PF (n = 66) and HC (n = 63) groups. Compared with the HC subjects, phosphatidylcholine (PC) 36:5 was the most up-regulated and lysophosphatidylcholine (LPC) 18:0 was the most down-regulated in PF patients. Glycerophospholipid metabolism was the most enriched pathway. Plasmenyl phosphatidylethanolamine (pPE) and plasmanyl phosphatidylcholine (pPC) were determined to be endothelial-related lipids, and phosphatidylethanolamine (PE) were fibroblast-related lipids in PF. In Study 2, 10 lipids were identified that differed between the absolute decline in %FVC < 2.5% group (6 M responders, n = 14) and the decline in %FVC > 2.5% group (6 M non-responders, n = 6) after 6 M of nintedanib therapy, and 6 lipids were identified that differed between the absolute decline in %FVC < 5% group (12 M responders, n = 15) and the decline in %FVC > 5% group (12 M non-responders, n = 5) after 12 M of nintedanib therapy. Four lipids were consistently detected at 6 M and 12 M, and among them, higher levels of pPE 18:0p/22:6 at 6 M showed a poorer prognosis for 24 M survival (p < 0.05, HR = 6.547, 95% CI = 1.471-29.13). Under nintedanib therapy, pPE species were correlated with progressive fibrosis, and pPE 18:0p/22:6 was considered an endothelial-related lipid.

CONCLUSIONS: Lipidomic profiling revealed distinct pathways in PF patients. pPE species were strongly associated with the responses to nintedanib therapy. Targeting the lipids or catabolic enzymes involved in dysregulated pathways has the potential to ameliorate PF.

TRIAL REGISTRATION: Registry for UMIN, Lipidomic analysis on plasma in idiopathic pulmonary fibrosis patients. Trial registry number, UMIN000020872. Registered 3 February 2016, https://center6.umin.ac.jp/cgiopenbin/ctr/index.cgi .

PMID:40296094 | DOI:10.1186/s12931-025-03239-0

Categories: Literature Watch

Ferroptosis: the potential key roles in idiopathic pulmonary fibrosis

Idiopathic Pulmonary Fibrosis - Mon, 2025-04-28 06:00

Eur J Med Res. 2025 Apr 28;30(1):341. doi: 10.1186/s40001-025-02623-2.

ABSTRACT

Idiopathic pulmonary fibrosis (IPF) is a chronic progressive interstitial lung disease characterized by recurrent injury to alveolar epithelial cells, epithelial-mesenchymal transition, and fibroblast activation, which leads to excessive deposition of extracellular matrix (ECM) proteins. However, effective preventative and therapeutic interventions are currently lacking. Ferroptosis, a unique form of iron-dependent lipid peroxidation-induced cell death, exhibits distinct morphological, physiological, and biochemical features compared to traditional programmed cell death. Recent studies have revealed a close relationship between iron homeostasis and the pathogenesis of pulmonary interstitial fibrosis. Ferroptosis exacerbates tissue damage and plays a crucial role in regulating tissue repair and the pathological processes involved. It leads to recurrent epithelial injury, where dysregulated epithelial cells undergo epithelial-mesenchymal transition via multiple signaling pathways, resulting in the excessive release of cytokines and growth factors. This dysregulated environment promotes the activation of pulmonary fibroblasts, ultimately culminating in pulmonary fibrosis. This review summarizes the latest advancements in ferroptosis research and its role in the pathogenesis and treatment of IPF, highlighting the significant potential of targeting ferroptosis for IPF management. Importantly, despite the rapid developments in this emerging research field, ferroptosis studies continue to face several challenges and issues. This review also aims to propose solutions to these challenges and discusses key concepts and pressing questions for the future exploration of ferroptosis.

PMID:40296070 | DOI:10.1186/s40001-025-02623-2

Categories: Literature Watch

Basal and AT2 Cells Promote IPF-Lung Cancer Co-occurrence via EMT: Single-cell Analysis

Idiopathic Pulmonary Fibrosis - Mon, 2025-04-28 06:00

Exp Cell Res. 2025 Apr 26:114578. doi: 10.1016/j.yexcr.2025.114578. Online ahead of print.

ABSTRACT

Idiopathic pulmonary fibrosis (IPF) is a chronic, progressive, fibrotic interstitial lung disease. With IPF, the probability of complication with lung cancer (LCA) increases considerably, and the prognosis is worse than that of simple IPF. To understand the pathological mechanisms and molecular pathways shared by these two diseases, we used the single-cell analysis from the Gene Expression Omnibus (GEO) database, and find that basal cells (BCs) and alveolar type 2 cells (AT2 cells) are important components of lung epithelial cells. Changes in molecular pathways in BCs and AT2 cells may be involved in the common pathogenesis of IPF and LCA. KRT17 and S100A14 in BCs may promote the IPF co-occurrence with LCA by mediating the EMT. WFDC2 and KRT19 may be the elements in AT2 cells that activate the EMT process to promote IPF co-occurrence with LCA. In both IPF and LCA, FN1-WNT axis may be involved in the interaction between BCs and AT2 cells. Importantly, the results of immunofluorescence colocalization experiments on tissue samples from patients with IPF and LCA were consistent with these conclusions. Basal-macrophage interactions may have also induced the IPF co-occurrence with LCA via the CYBA-ERK1/2 axis. The regulation of M2 macrophage polarization by JUN/SOD2-glycolysis axis may therefore be involved in the co-morbidity mechanism of IPF and LCA. Therefore, our results suggest that molecular changes in BCs, AT2 cells and macrophages may play important roles in the pathogenesis of IPF co-occurrence with LCA, and the cellular interactions between these cells may be critical for the progression of both diseases.

PMID:40294812 | DOI:10.1016/j.yexcr.2025.114578

Categories: Literature Watch

Translating community-wide spectral library into actionable chemical knowledge: a proof of concept with monoterpene indole alkaloids

Systems Biology - Mon, 2025-04-28 06:00

J Cheminform. 2025 Apr 28;17(1):62. doi: 10.1186/s13321-025-01009-0.

ABSTRACT

With over 3000 representatives, the monoterpene indole alkaloids (MIAs) class is among the most diverse families of plant natural products. The MS/MS spectral space exploration of these complex compounds using chemoinformatic and computational mass spectrometry tools offers a valuable opportunity to extract and share chemical insights from this emblematic family of natural products (NPs). In this work, we first present a substantially updated version of the MIADB, a database now containing 422 MS/MS spectra of MIAs that has been uploaded to the GNPS library versus 172 initial entries. We then introduce an innovative workflow that leverages hundreds of fragmentation spectra to support the FAIRification, extraction and dissemination of chemical knowledge. This workflow aims at the extraction of spectral patterns matching finely defined MIA skeletons. These extracted signatures can then be queried against complex biological extract datasets using MassQL. By applying this strategy to an LC-MS/MS dataset of 75 plant extracts, our results demonstrated the efficiency of this approach in identifying the diversity of MIA skeletons present in the analyzed samples. Additionally, our work enabled the digitization of structural data for diverse MIA skeletons by converting them into machine-readable formats and thereby enhancing their dissemination for the scientific community.Scientific contribution A comprehensive investigation of the monoterpene indole alkaloid chemical space, aiming to highlight skeleton-dependent fragmentation similarity trends and to generate valuable spectrometric signatures that could be used as queries.

PMID:40296170 | DOI:10.1186/s13321-025-01009-0

Categories: Literature Watch

Modest functional diversity decline and pronounced composition shifts of microbial communities in a mixed waste-contaminated aquifer

Systems Biology - Mon, 2025-04-28 06:00

Microbiome. 2025 Apr 28;13(1):106. doi: 10.1186/s40168-025-02105-x.

ABSTRACT

BACKGROUND: Microbial taxonomic diversity declines with increased environmental stress. Yet, few studies have explored whether phylogenetic and functional diversities track taxonomic diversity along the stress gradient. Here, we investigated microbial communities within an aquifer in Oak Ridge, Tennessee, USA, which is characterized by a broad spectrum of stressors, including extremely high levels of nitrate, heavy metals like cadmium and chromium, radionuclides such as uranium, and extremely low pH (< 3).

RESULTS: Both taxonomic and phylogenetic α-diversities were reduced in the most impacted wells, while the decline in functional α-diversity was modest and statistically insignificant, indicating a more robust buffering capacity to environmental stress. Differences in functional gene composition (i.e., functional β-diversity) were pronounced in highly contaminated wells, while convergent functional gene composition was observed in uncontaminated wells. The relative abundances of most carbon degradation genes were decreased in contaminated wells, but genes associated with denitrification, adenylylsulfate reduction, and sulfite reduction were increased. Compared to taxonomic and phylogenetic compositions, environmental variables played a more significant role in shaping functional gene composition, suggesting that niche selection could be more closely related to microbial functionality than taxonomy.

CONCLUSIONS: Overall, we demonstrated that despite a reduced taxonomic α-diversity, microbial communities under stress maintained functionality underpinned by environmental selection. Video Abstract.

PMID:40296156 | DOI:10.1186/s40168-025-02105-x

Categories: Literature Watch

Regional concentrations of heavy metals in surface soils and risk of body pain in elderly residential population: a national cohort study in China

Systems Biology - Mon, 2025-04-28 06:00

BMC Public Health. 2025 Apr 28;25(1):1571. doi: 10.1186/s12889-025-22638-y.

ABSTRACT

BACKGROUND: The accumulation of heavy metals in surface soil raises significant environmental and public health concerns around the world. This study aimed to examine the relationship between exposure to heavy metals in surface soil and the risk of pain among residents.

METHODS: Using national data on eight heavy metals (arsenic, cadmium, chromium, copper, lead, mercury, nickel and zinc) in China's surface soil and a population cohort from 2011 to 2018, we analyzed pain occurrences in various body locations. Logistic regression models were used to assess the association between exposure to heavy metal in soil and pain, as adjusting for gender, age, education level, body mass index, living region, and lifestyle. The study included 13,178 individuals.

RESULTS: Higher exposure to soil arsenic was found to be associated with increased risk of shoulders [adjusted odds ratio (99.99% CI), 1.49 (1.01, 2.19)], wrists [1.68 (1.06, 2.64)] and ankles pain [1.58 (1.01, 2.50)]. No association was found between the remaining seven heavy metals and different types of body pain.

CONCLUSION: Our results indicate that higher soil arsenic exposure is associated with an increased risk of pain in specific body regions. This study is the first examining the associations between multiple heavy metals in surface soil and the risks of pain in different body sites. Our findings provide new insights into the health risks of soil heavy metal exposure.

PMID:40295964 | DOI:10.1186/s12889-025-22638-y

Categories: Literature Watch

Pages

Subscribe to Anil Jegga aggregator - Literature Watch