Sci Rep. 2025 Mar 8;15(1):8119. doi: 10.1038/s41598-025-92563-y.

ABSTRACT

Social media has attracted society for decades due to its reciprocal and real-life nature. It influenced almost all societal entities, including governments, academics, industries, health, and finance. The Social Network generates unstructured information about brands, political issues, cryptocurrencies, and global pandemics. The major challenge is translating this information into reliable consumer opinion as it contains jargon, abbreviations, and reference links with previous content. Several ensemble models have been introduced to mine the enormous noisy range on social platforms. Still, these need more predictability and are the less-generalized models for social sentiment analysis. Hence, an optimized stacked-Long Short-Term Memory (LSTM)-based sentiment analysis model is proposed for cryptocurrency price prediction. The model can find the relationships of latent contextual semantic and co-occurrence statistical features between phrases in a sentence. Additionally, the proposed model comprises multiple LSTM layers, and each layer is optimized with Particle Swarm Optimization (PSO) technique to learn based on the best hyperparameters. The model's efficiency is measured in terms of confusion matrix, weighted f1-Score, weighted Precision, weighted Recall, training accuracy, and testing accuracy. Moreover, comparative results reveal that an optimized stacked LSTM outperformed. The objective of the proposed model is to introduce a benchmark sentiment analysis model for predicting cryptocurrency prices, which will be helpful for other societal sentiment predictions. A pretty significant thing for this presented model is that it can process multilingual and cross-platform social media data. This could be achieved by combining LSTMs with multilingual embeddings, fine-tuning, and effective preprocessing for providing accurate and robust sentiment analysis across diverse languages, platforms, and communication styles.

PMID:40057585 | DOI:10.1038/s41598-025-92563-y

Sci Data. 2025 Mar 8;12(1):403. doi: 10.1038/s41597-025-04719-0.

ABSTRACT

Under the strategic objectives of carbon peaking and carbon neutrality, energy transition driven by new quality productive forces has emerged as a central theme in China's energy development. Among these, the intelligent sorting and analysis of raw coal using deep learning constitute a pivotal technical process. However, the progress of intelligent coal preparation in China has been constrained by the absence of accurate and large-scale data. To address this gap, this study introduces DsCGF, a large-scale, open-source raw coal image dataset. Over the past five years, extensive raw coal image samples were systematically collected and meticulously annotated from three representative mining regions in China, resulting in a dataset comprising over 270,000 visible-light images. These images are annotated at multiple levels, targeting three primary categories: coal, gangue, and foreign objects, and are designed for three core computer vision tasks: image classification, object detection, and instance segmentation. Comprehensive evaluation results indicate that the DsCGF can effectively support further research into the intelligent sorting of raw coal.

PMID:40057526 | DOI:10.1038/s41597-025-04719-0

Nat Commun. 2025 Mar 8;16(1):2342. doi: 10.1038/s41467-025-57721-w.

ABSTRACT

High-quality nuclear magnetic resonance (NMR) spectra can be rapidly acquired by combining non-uniform sampling techniques (NUS) with reconstruction algorithms. However, current deep learning (DL) based reconstruction methods focus only on single-domain reconstruction (time or frequency domain), leading to drawbacks like peak loss and artifact peaks and ultimately failing to achieve optimal performance. Moreover, the lack of fully sampled spectra makes it difficult, even impossible, to determine the quality of reconstructed spectra, presenting challenges in the practical applications of NUS. In this study, a joint time-frequency domain deep learning network, referred to as JTF-Net, is proposed. It effectively combines time domain and frequency domain features, exhibiting better reconstruction performance on protein spectra across various dimensions compared to traditional algorithms and single-domain DL methods. In addition, the reference-free quality assessment metric, denoted as REconstruction QUalIty assuRancE Ratio (REQUIRER), is proposed base on an established quality space in the field of NMR spectral reconstruction. The metric is capable of evaluating the quality of reconstructed NMR spectra without the fully sampled spectra, making it more suitable for practical applications.

PMID:40057512 | DOI:10.1038/s41467-025-57721-w

Comput Biol Med. 2025 Mar 6;189:109989. doi: 10.1016/j.compbiomed.2025.109989. Online ahead of print.

ABSTRACT

The Chikungunya virus (CHIKV) represents a significant global health threat, particularly in tropical regions, and no FDA-approved antiviral treatments are currently available. This study investigates the potential of Direct-Acting Antivirals (DAAs) and protease inhibitors (PIs) that have been developed for the hepatitis C virus (HCV) in treating CHIKV. We analyzed the binding of eight HCV DAAs to the nsP2 protease of CHIKV, which is essential for viral replication. Our findings suggest repurposing hepatitis C virus (HCV) antivirals, specifically Simeprevir (SIM) and voxilaprevir (VOX), could be effective against CHIKV. Through computational analyses, we observed their strong binding affinity to CHIKV's nsP2 protease, indicating the promising potential of repositioning these drugs for CHIKV treatment. To validate the results of our computational study, we evaluated the antiviral efficacy of SIM and VOX in vitro, both as monotherapies and in combination with ribavirin (RIBA). Our findings revealed that DAAs exert a multifaced effect by targeting different stages of the CHIKV life cycle. Furthermore, the synergistic effects suggest that combining SIM and VOX with RIBA may provide a more effective therapeutic strategy than using either drug alone. Further research is necessary to optimize treatment protocols and improve outcomes for patients affected by CHIKV.

PMID:40056839 | DOI:10.1016/j.compbiomed.2025.109989

Herz. 2025 Mar 8. doi: 10.1007/s00059-025-05298-x. Online ahead of print.

ABSTRACT

Precision medicine in cardiac electrophysiology tailors diagnosis, treatment, and prevention by integrating genetic, environmental, and lifestyle factors. Unlike traditional, generalized strategies, precision medicine focuses on individual patient characteristics to enhance care. Significant progress has been made, especially in managing channelopathies, where genetic insights now already drive personalized therapies. Identifying specific mutations has clarified molecular mechanisms and enabled targeted interventions, improving outcomes in conditions such as long QT syndrome. The integration of big data from clinical records, omics datasets, and biosignals from devices such as cardiac implantable electronic devices (CIEDs) or wearables may be on the verge of revolutionizing the diagnosis of cardiac arrhythmias once again. Progress is also expected in the field of human-induced pluripotent stem cells (hiPSCs) and in silico modeling, which may overcome the limitations of traditional expression systems for the functional evaluation of patient-specific mutations. Genome-wide association studies (GWAS) and polygenic risk scores (PRS) provide deeper insights into complex arrhythmogenic disorders, aiding in risk stratification and targeted treatment strategies. Finally, emerging technologies such as CRISPR/Cas9 promise gene editing for inherited and acquired arrhythmias. In summary, precision medicine offers the potential for individualized treatment of cardiac arrhythmias.

PMID:40056164 | DOI:10.1007/s00059-025-05298-x

Nat Commun. 2025 Mar 8;16(1):2334. doi: 10.1038/s41467-025-57532-z.

ABSTRACT

Fatty acids are a primary source of carbon for Pseudomonas aeruginosa (PA) in the airways of people with cystic fibrosis (CF). Here, we use tandem mass-tag proteomics to analyse the protein expression profile of a CF clinical isolate grown on different fatty acids. Two fatty acyl-CoA dehydrogenases (designated FadE1 and FadE2) are strongly induced during growth on fatty acids. FadE1 displays a strong preference for long-chain acyl-CoAs, whereas FadE2 exclusively utilizes medium-chain acyl-CoAs. Structural analysis of the enzymes enables us to identify residues comprising the substrate selectivity filter in each. Engineering these residues enables us to invert the substrate specificity of each enzyme. Mutants in fadE1 displayed impaired virulence in an infection model, and decreased growth on long chain fatty acids. The unique features of the substrate binding pocket enable us to identify an inhibitor that is differentially active against FadE1 and FadE2.

PMID:40057486 | DOI:10.1038/s41467-025-57532-z

Int J Antimicrob Agents. 2025 Mar 6:107488. doi: 10.1016/j.ijantimicag.2025.107488. Online ahead of print.

ABSTRACT

Hypermutable P. aeruginosa isolates frequently display resistance emergence during treatment. Mechanisms of such resistance emergence have not been explored using dynamic hollow-fiber studies and multi-omics-informed mathematical modeling. Two hypermutable and heteroresistant P. aeruginosa isolates, CW8 (MICmeropenem=8mg/L, MICtobramycin=8mg/L) and CW44 (MICmeropenem=4mg/L, MICtobramycin=2mg/L), were studied. Both isolates had genotypes resembling those of carbapenem- and aminoglycoside-resistant strains. Achievable lung fluid concentration-time profiles following meropenem at 1 or 2g every 8h (3-h infusion) and tobramycin at 5 or 10mg/kg body weight every 24h (0.5-h infusion), in monotherapy and combinations, were simulated over 8 days. Total and resistant bacterial counts were determined. Resistant colonies and whole population samples at 191h were whole-genome sequenced, and population transcriptomics performed at 1 and 191h. The multi-omics analyses informed mechanism-based modeling of total and resistant populations. While both isolates eventually displayed resistance emergence against all regimens, the high-dose combination synergistically suppressed resistant regrowth of only CW8 up to ∼96h. Mutations that emerged during treatment were in pmrB, ampR, and multiple efflux pump regulators for CW8, and in pmrB and PBP2 for CW44. At 1h, mexB, oprM and ftsZ were differentially downregulated in CW8 by the combination. These transcriptomics results informed inclusion of mechanistic synergy in the mechanism-based model for only CW8. At 191h, norspermidine genes were upregulated (without a pmrB mutation) in CW8 by the combination, and informed the adaptive loss of synergy in the model. Multi-omics information enabled mechanism-based modeling to describe the bacterial response of both isolates simultaneously. IMPORTANCE: Pseudomonas aeruginosa causes serious bacterial infections in people with cystic fibrosis (pwCF), and has numerous resistance mechanisms. Current empirical approaches to informing antibiotic regimen selection have important limitations. This study exposed two P. aeruginosa clinical isolates to concentration-time profiles of meropenem and tobramycin as would be observed in lung fluid of pwCF. The combination elicited different bacterial count profiles between the isolates, despite similar bacterial baseline characteristics. We found differences between the isolates in the expression of a key resistance mechanism against meropenem at 1h, and expression that implied a loss of cell membrane permeability for tobramycin without the expected DNA mutation. This information enabled mathematical modeling to accurately describe all bacterial profiles over time. For the first time, this multi-omics informed modeling approach using DNA and RNA data was applied to a hollow-fiber infection study. Using bacterial molecular insights with mechanism-based mathematical modeling has high potential for ultimately informing personalized antibiotic therapy.

PMID:40057138 | DOI:10.1016/j.ijantimicag.2025.107488

Tuberculosis (Edinb). 2025 Mar 4;152:102629. doi: 10.1016/j.tube.2025.102629. Online ahead of print.

ABSTRACT

Animal models that can mimic progressive granulomatous pulmonary disease (PD) due to non-tuberculous mycobacteria (NTM) have not been established in rats to date. These models could assist with the study of the pathophysiology of NTM-PD as well as the preclinical development of new therapies. In the present study, an immunocompetent rat model of progressive Mycobacterium abscessus (MABs)- PD was developed using MABs originating from a patient with cystic fibrosis. MABs was embedded in agarose beads and delivered intratracheally to the lungs of Sprague Dawley rats two times at a one-week time interval. The bacterial burden of lysed lungs, spleen and liver was assessed by calculating colony forming units (CFUs) on day 28. Lung CFUs indicated a ∼1.2-2 log10 total CFU increase compared to the initial total bacterial load instilled into the lungs. In all infected rats, multinodular granulomatous inflammatory lesions containing MABs were found in the lung. These findings support the establishment of an immunocompetent MABs PD rat model, characterised by an increase in mycobacterial burden over time and a chronic granulomatous inflammatory response to the MABs infection.

PMID:40056658 | DOI:10.1016/j.tube.2025.102629

Respir Res. 2025 Mar 8;26(1):91. doi: 10.1186/s12931-025-03173-1.

ABSTRACT

BACKGROUND: High altitude pulmonary edema (HAPE) poses a significant medical challenge to individuals ascending rapidly to high altitudes. Hypoxia-induced cellular morphological changes in the alveolar-capillary barrier such as mitochondrial structural alterations and cytoskeletal reorganization, play a crucial role in the pathogenesis of HAPE. These morphological changes are critical in understanding the cellular response to hypoxia and represent potential therapeutic targets. However, there is still a lack of effective and valid drug discovery strategies for anti-HAPE treatments based on these cellular morphological features. This study aims to develop a pipeline that focuses on morphological alterations in Cell Painting images to identify potential therapeutic agents for HAPE interventions.

METHODS: We generated over 100,000 full-field Cell Painting images of human alveolar adenocarcinoma basal epithelial cells (A549s) and human pulmonary microvascular endothelial cells (HPMECs) under different hypoxic conditions (1%~5% of oxygen content). These images were then submitted to our newly developed segmentation network (SegNet), which exhibited superior performance than traditional methods, to proceed to subcellular structure detection and segmentation. Subsequently, we created a hypoxia scoring network (HypoNet) using over 200,000 images of subcellular structures from A549s and HPMECs, demonstrating outstanding capacity in identifying cellular hypoxia status.

RESULTS: We proposed a deep neural network-based drug screening pipeline (CPHNet), which facilitated the identification of two promising natural products, ferulic acid (FA) and resveratrol (RES). Both compounds demonstrated satisfactory anti-HAPE effects in a 3D-alveolus chip model (ex vivo) and a mouse model (in vivo).

CONCLUSION: This work provides a brand-new and effective pipeline for screening anti-HAPE agents by integrating artificial intelligence (AI) tools and Cell Painting, offering a novel perspective for AI-driven phenotypic drug discovery.

PMID:40057746 | DOI:10.1186/s12931-025-03173-1

Respir Res. 2025 Mar 8;26(1):94. doi: 10.1186/s12931-025-03174-0.

ABSTRACT

BACKGROUND: To evaluate the clinical applicability of deep learning (DL) models based on automatic segmentation in preoperatively predicting tumor spread through air spaces (STAS) in peripheral stage I lung adenocarcinoma (LUAD).

METHODS: This retrospective study analyzed data from patients who underwent surgical treatment for lung tumors from January 2022 to December 2023. An external validation set was introduced to assess the model's generalizability. The study utilized conventional radiomic features and DL models for comparison. ROI segmentation was performed using the VNet architecture, and DL models were developed with transfer learning and optimization techniques. We assessed the diagnostic accuracy of our models via calibration curves, decision curve analysis, and ROC curves.

RESULTS: The DL model based on automatic segmentation achieved an AUC of 0.880 (95% CI 0.780-0.979), outperforming the conventional radiomics model with an AUC of 0.833 (95% CI 0.707-0.960). The DL model demonstrated superior performance in both internal validation and external testing cohorts. Calibration curves, decision curve analysis, and ROC curves confirmed the enhanced diagnostic accuracy and clinical utility of the DL approach.

CONCLUSION: The DL model based on automatic segmentation technology shows significant promise in preoperatively predicting STAS in peripheral stage I LUAD, surpassing traditional radiomics models in diagnostic accuracy and clinical applicability. Clinical trial number The clinical trial was registered on April 22, 2024, with the registration number researchregistry10213 ( www.researchregistry.com ).

PMID:40057743 | DOI:10.1186/s12931-025-03174-0

BMC Pediatr. 2025 Mar 8;25(1):177. doi: 10.1186/s12887-025-05532-9.

ABSTRACT

BACKGROUND: Turner syndrome (TS) is one of the important causes of short stature in girls, but there are cases of misdiagnosis and missed diagnosis in clinical practice. Our aim is to analyze the hand skeletal characteristics of TS patients and establish a disease screening model using deep learning.

METHODS: A total of 101 pediatric patients with TS were included in this retrospective case-control study. Their radiation parameters from hand X-rays were summarized and compared. Receiver operating characteristic (ROC) curves for parameters with differences between the groups were plotted. Additionally, we used deep learning networks to establish a predictive model.

RESULTS: Four parameters were identified as having diagnostic value for TS: the length ratio of metacarpal IV and metacarpal III, the distance between ulnoradial tangents, the carpal angle, and the ulnar-radial angle. When the cutoff value of the distance between the ulnoradial tangents was 0.40 cm, the specificity reached 92.57%. And for the ulnar- radius angle, according to the ROC analysis, the maximum value of Youden's index was obtained when the cut-off value was 170°, with a sensitivity of 66.34% and specificity of 61.38%. The ResNet50 deep neural network architecture was utilized, resulting in an accuracy of 78.89%, specificity of 76.67%, and sensitivity of 83.33% on a test dataset.

CONCLUSIONS: We propose that certain hand radiograph parameters have the potential to serve as diagnostic indicators for TS. The utilization of deep learning models has significantly enhanced the precision of disease diagnosis.

PMID:40057693 | DOI:10.1186/s12887-025-05532-9

Sci Rep. 2025 Mar 8;15(1):8114. doi: 10.1038/s41598-025-92776-1.

ABSTRACT

In the diagnosis and treatment of brain tumors, the automatic classification and segmentation of medical images play a pivotal role. Early detection facilitates timely intervention, significantly improving patient survival rates. This study introduces a novel method for the automated classification and segmentation of brain tumors, aiming to enhance both diagnostic accuracy and efficiency. Magnetic Resonance (MR) imaging remains the gold standard in clinical brain tumor diagnostics; however, it is a time-intensive and labor-intensive process. Consequently, the integration of automated detection, localization, and classification methods is not only desirable but essential. In this research, we present a novel framework that enables both tumor classification and post-classification diagnostic feature extraction, allowing for the first-time classification of multiple tumor types. To improve tumor characterization, we applied data augmentation techniques to MR images and developed a hierarchical multiscale deformable attention module (MS-DAM). This model effectively captures irregular and complex tumor patterns, enhancing classification performance. Following classification, a comprehensive segmentation process was conducted across a large dataset, reinforcing the model's role as a decision support system. Utilizing a Kaggle dataset containing 14 different tumor types with highly similar morphologic structures, we validated the proposed model's efficacy. Compared to existing multi-scale channel attention modules, MS-DAM achieved superior accuracy, exceeding 96.5%. This study presents a highly promising approach for the automated classification and segmentation of brain tumors in medical imaging, offering significant advancements for diagnostic imaging clinics and paving the way for more efficient, accurate, and scalable tumor detection methodologies.

PMID:40057634 | DOI:10.1038/s41598-025-92776-1

Sci Rep. 2025 Mar 8;15(1):8086. doi: 10.1038/s41598-025-85678-9.

ABSTRACT

Lung cancer remains a major global health challenge, and accurate pathological examination is crucial for early detection. This study aims to enhance hyperspectral pathological image analysis by refining annotations at the cell level and creating a high-quality hyperspectral dataset of lung tumors. We address the challenge of coarse manual annotations in hyperspectral lung cancer datasets, which limit the effectiveness of deep learning models requiring precise labels for training. We propose a semi-automated annotation refinement method that leverages hyperspectral data to enhance pathological diagnosis. Specifically, we employ K-means unsupervised clustering combined with human-guided selection to refine coarse annotations into cell-level masks based on spectral features. Our method is validated using a hyperspectral lung squamous cell carcinoma dataset containing 65 image samples. Experimental results demonstrate that our approach improves pixel-level segmentation accuracy from 77.33% to 92.52% with a lower level of prediction noise. The time required to accurately label each pathological slide is significantly reduced. While pixel-level labeling methods for an entire slide can take over 30 mins, our semi-automated method requires only about 5 mins. To enhance visualization for pathologists, we apply a conservative post-processing strategy for instance segmentation. These results highlight the effectiveness of our method in addressing annotation challenges and improving the accuracy of hyperspectral pathological analysis.

PMID:40057531 | DOI:10.1038/s41598-025-85678-9

Nucleic Acids Res. 2025 Feb 27;53(5):gkaf158. doi: 10.1093/nar/gkaf158.

ABSTRACT

Spatial transcriptomics technology has revolutionized our understanding of cellular systems by capturing RNA transcript levels in their original spatial context. Single-cell spatial transcriptomics (scST) offers single-cell resolution expression level and precise spatial information of RNA transcripts, while it has a limited capacity for simultaneously detecting a wide range of RNA transcripts, hindering its broader applications. Characterizing the whole transcriptome level and comprehensively annotating cell types represent two significant challenges in scST applications. Despite several proposed methods for one or both tasks, their performance remains inadequate. In this work, we introduce stAI, a deep learning-based model designed to address both missing gene imputation and cell-type annotation for scST data. stAI leverages a joint embedding for the scST and the reference scRNA-seq data with two separate encoder-decoder modules. Both the imputation and annotation are performed within the latent space in a supervised manner, utilizing scRNA-seq data to guide the processes. Experiments for datasets generated from diverse platforms with varying numbers of measured genes were conducted and compared with the updated methods. The results demonstrate that stAI can predict the unmeasured genes, especially the marker genes, with much higher accuracy, and annotate the cell types, including those of small size, with high precision.

PMID:40057378 | DOI:10.1093/nar/gkaf158

Med Eng Phys. 2025 Mar;137:104302. doi: 10.1016/j.medengphy.2025.104302. Epub 2025 Feb 6.

ABSTRACT

Cardiovascular diseases (CVDs) are the leading global cause of death, which requires the early and accurate detection of cardiac abnormalities. Abnormal heart sounds, indicative of potential cardiac problems, pose a challenge due to their low-frequency nature. Utilizing digital signal processing and Phonocardiogram (PCG) analysis, this study employs advanced deep learning techniques for automated heart sound classification. Time-frequency representations capture multiple heart sound features, including gammatonegram, Mel-spectrogram, and Constant-Q Transform (CQT). A Convolutional Neural Network with Directed Acyclic Graph (DAG-CNN) architecture is designed and rigorously evaluated, achieving high classification accuracies of 100%, 99.7%, and 99.5% for gammatonegram, Mel-spectrogram, and CQT, respectively. Comparative analysis with pre-trained CNN models demonstrates the superior performance of the proposed model. This advancement in automated heart sound classification offers a promising and cost-effective tool for early diagnosis, particularly in resource-limited settings, helping to address the diagnostic gap and enhance cardiac care accessibility.

PMID:40057368 | DOI:10.1016/j.medengphy.2025.104302

Med Eng Phys. 2025 Mar;137:104305. doi: 10.1016/j.medengphy.2025.104305. Epub 2025 Feb 7.

ABSTRACT

Lung cancer remains the principal cause of cancer-related deaths. Nodules are the main radiological finding, typically observed from low-dose CT scans. Nonetheless, the nodule characterization diagnosis remains subjective, reporting a moderate agreement among experts' observations, especially in identifying malignancy stratification. The proposed approach presents a deep multi-attention strategy, validated exhaustively to classify nodule masses according to four malignancy degrees. This work introduces a multi-attention architecture dedicated to stratifying nodules among malignancy stages. The architecture receives volumetric nodule regions and learns multi-scale saliency maps, focusing on determinant malignancy patterns of the observed masses. Specialized attention heads capture related patterns associated with lobulated, textural, and spiculated features. Validation includes an extensive analysis regarding multiple attention features, allowing to establish a correlation with other radiological findings. The proposed approach achieves an AUC of 85.35% for a classical multi-classification and a mean AUC of 82.90% in a one-vs-all validation methodology, showing competitive results in the state-of-the-art. The introduced architecture has capabilities to support nodule stratification and to classify nodule features. The exhaustive validation also suggests a proper generalization performance, which is a potential property to transfer this strategy in real scenarios.

PMID:40057364 | DOI:10.1016/j.medengphy.2025.104305

Med Eng Phys. 2025 Mar;137:104300. doi: 10.1016/j.medengphy.2025.104300. Epub 2025 Feb 8.

ABSTRACT

Tuberculosis is a high-mortality infectious disease. Manual sputum smear microscopy is a common and effective method for screening tuberculosis. However, it is time-consuming, labor-intensive, and has low sensitivity. In this study, we propose ResGloTBNet, a framework that integrates convolutional neural network and graph convolutional network for sputum smear image classification with high discriminative power. In this framework, the global reasoning unit is introduced into the residual structure of ResNet to form the ResGloRe module, which not only fully extracts the local features of the image but also models the global relationship between different regions in the image. Furthermore, we applied activation maximization and class activation mapping to generate explanations for the model's predictions on the test sets. ResGloTBNet achieved remarkable results on a publicly available dataset, reaching 97.2 % accuracy and 99.0 % sensitivity. It also maintained a high level of performance on a private dataset, attaining 98.0 % accuracy and 96.6 % sensitivity. In addition, interpretable analysis demonstrated that ResGloTBNet can effectively identify the features and regions in the input images that contribute the most to the model's predictions, providing valuable insights into the decision-making process of the deep learning model.

PMID:40057359 | DOI:10.1016/j.medengphy.2025.104300

SLAS Technol. 2025 Mar 6:100264. doi: 10.1016/j.slast.2025.100264. Online ahead of print.

ABSTRACT

Gastrointestinal cancer represents a significant health burden, necessitating innovative approaches for personalized treatment. This study aims to develop an advanced natural language processing (NLP)-driven predictive modeling framework for tailored treatment strategies in gastrointestinal cancer, leveraging the capabilities of deep learning. The Resilient Adam Algorithm-driven Versatile Long-Short Term Memory (RAA-VLSTM) model is proposed to analyze comprehensive clinical data. The dataset comprises extensive electronic health records (EHRs) from multiple healthcare centers, focusing on patient demographics, clinical history, treatment outcomes, and genetic factors. Data preprocessing employs techniques such as tokenization, normalization, and stop-word removal to ensure effective representation of textual data. For feature extraction, state-of-the-art word embeddings are utilized to enhance model performance. The proposed framework outlines a comprehensive process: data collection from EHRs, preprocessing to prepare the data for analysis, and employing NLP techniques to extract meaningful features. The RAA optimization algorithm significantly improves training efficiency by adapting learning rates for each parameter, addressing common issues in gradient descent. This optimization enhances feature learning from sequential clinical data, enabling accurate predictions of treatment responses and outcomes. The overall performance in terms of F1-score (89.4%), accuracy (92.5%), recall (88.7%), and precision (90.1%). Preliminary results demonstrate the model's strong predictive capabilities, achieving high accuracy in predicting treatment outcomes, thereby suggesting its potential to improve individualized care. In conclusion, this study establishes a robust foundation for employing advanced NLP and machine learning techniques in the management of gastrointestinal cancer, paving the way for future research and clinical applications.

PMID:40057234 | DOI:10.1016/j.slast.2025.100264

Best Pract Res Clin Endocrinol Metab. 2025 Mar 3:101985. doi: 10.1016/j.beem.2025.101985. Online ahead of print.

ABSTRACT

Primary hyperparathyroidism is a common endocrine disorder characterized by inappropriate elevation of parathyroid hormone and hypercalcemia. While predominantly an asymptomatic disease in Western populations, symptomatic presentations are more prevalent in Eastern countries. The molecular pathogenesis of sporadic PHPT primarily involves genetic and epigenetic alterations leading to abnormal parathyroid cell proliferation and altered calcium sensing mechanism. To date, MEN1 and cyclin D1 are the only established drivers of sporadic PHPT. Somatic MEN1 gene mutations occur in 30-40 % of sporadic parathyroid adenomas (PA), with a recent study on symptomatic cases reporting germline variants.Cyclin D1 overexpression in sporadic PA has been observed in 20-40 % of cases in Western populations and 80 % of cases in Eastern populations, with an inverse association with cyclin-dependent kinase inhibitors CDKN2A and CDKN2B expression. The calcium-sensing receptor expression was significantly lower in symptomatic compared to asymptomatic PHPT, strongly supported by epigenetic deregulation (promoter hypermethylation and histone methylation). Recent studies have highlighted the potential involvement of EZH2, a histone methyltransferase, in parathyroid tumorigenesis. Additionally, parathyroid-specific transcription factors like GCM2, PAX1, and GATA3 are emerging as putative tumor suppressors, especially from the symptomatic PHPT. Next-generation sequencing has identified novel potential drivers such as PIK3CA, MTOR, and NF1 in sporadic PC, alongside CDC73. The molecular landscape of sporadic PHPT appears to differ between Eastern and Western populations. This heterogeneity underscores the need for further large-scale studies, particularly in symptomatic cases from developing nations, to comprehensively elucidate the molecular drivers of parathyroid tumorigenesis.

PMID:40057423 | DOI:10.1016/j.beem.2025.101985

Biochim Biophys Acta Mol Basis Dis. 2025 Mar 6:167781. doi: 10.1016/j.bbadis.2025.167781. Online ahead of print.

ABSTRACT

Non-coding RNAs (ncRNAs) are frequently dysregulated in various cancers and have been implicated in the etiology and progression of cancer. Ovarian cancer, the most fatal gynecological cancer, has a poor prognosis and a high patient fatality rate due to metastases. In this study, we classified patients with ovarian cancer into three groups based on their ncRNA expression levels. Notably, an ncRNA transcribed by RNA polymerase III, RNA component of mitochondrial RNA processing endoribonuclease (RMRP), is highly expressed in a group with a poor prognosis. Functional assays using SKOV3 and HeyA8 human ovarian cancer cell lines revealed that while RMRP modulation had no significant effect on cell viability, it markedly enhanced cell invasion. Knockdown and ectopic expression experiments demonstrated that RMRP promotes the secretion of matrix metalloproteinase (MMP)-2 and -9, thereby facilitating ovarian cancer cell invasiveness. Transcriptomic analysis further revealed a positive correlation between RMRP expression and genes involved in cellular localization, including RAB31, a member of the Ras-related protein family. Notably, RAB31 knockdown abrogated the pro-invasive effects of RMRP, identifying it as a key downstream effector in SKOV3 and HeyA8 cells. In addition, MechRNA analysis identified RAB31 as a putative RMRP-interacting transcript. These findings establish RMRP as a critical regulator of RAB31-dependent MMP secretion and ovarian cancer cell invasion. Moreover, our results suggest that RMRP could serve as a promising prognostic biomarker for ovarian cancer.

PMID:40057205 | DOI:10.1016/j.bbadis.2025.167781