Am Heart J Plus. 2025 Mar 1;53:100520. doi: 10.1016/j.ahjo.2025.100520. eCollection 2025 May.

ABSTRACT

The development of vascularized organoids as novel modelling tools of the human cardio-cerebrovascular system for preclinical research has become an essential platform for studying human vascularized tissues/organs for development of personalized therapeutics during recent decades. Organ-on-chip technology is promising for investigating physiological in vitro responses in drug screening development and advanced disease models. Vascularized tissue/organ-on-a-chip benefits every step of drug discovery pipeline as a screening tool with close human genome relevance to investigate human systems biology. Simultaneously, cardio-cerebrovascular-on-chip-integrated microfluidic system serves as an alternative to preclinical animal research for studying (patho-)physiological processes of human blood vessels during embryonic development and cardio-cerebrovascular disease. Integrated with next-generation techniques, such as three-dimensional bioprinting of both cells and matrix, may enable vascularized organoid-on-chip-based novel drug development as personalized therapeutics.

PMID:40230658 | PMC:PMC11995107 | DOI:10.1016/j.ahjo.2025.100520

Exp Ther Med. 2025 Mar 27;29(5):106. doi: 10.3892/etm.2025.12856. eCollection 2025 May.

ABSTRACT

Influenza infections damage the airway and induce the innate immune response that contributes to hyper-inflammation. Eucommiae Cortex (EC) enhances immune function and suppresses inflammation. To determine potential compounds and targets of EC associated with influenza, bioinformatics analyses and experimental verification were employed. The active compounds of EC were retrieved from the Traditional Chinese Medicine Systems Pharmacology database. The intersecting targets of EC and influenza were determined and examined using network pharmacology to analyze the relationship between the compounds and disease targets. The network identified three main compounds (quercetin, genistein and kaempferol) and four main targets (IL6, BCL2, IL1B and TNF). The ligand-target binding affinity was calculated by molecular docking, a computational method used in drug design to predict the interaction between the compound and protein target. The docking results revealed that kaempferol and TNF showed the strongest binding affinity. In vitro experiments confirmed the therapeutic effect of EC in influenza virus-infected Madin-Darby canine kidney cells. Collectively, the present study identified the active compounds and potential targets of EC in influenza and suggested EC as a future influenza treatment.

PMID:40230620 | PMC:PMC11995446 | DOI:10.3892/etm.2025.12856

iScience. 2025 Mar 15;28(4):112120. doi: 10.1016/j.isci.2025.112120. eCollection 2025 Apr 18.

ABSTRACT

Alisertib is a potent aurora A kinase inhibitor in clinical trials for cancer treatment, but its efficacy on cancer vaccines remains unclear. Here, we developed a DNA vaccine targeting glypican-3 (pGPC3) and evaluated its efficacy with alisertib in hepatocellular carcinoma (HCC) models. The combination therapy of pGPC3 vaccine and alisertib significantly inhibited subcutaneous tumor growth, enhanced the induction and maturation of CD11c+ and CD8+CD11c+ dendritic cells (DCs), and expanded tumor-specific CD8+ T cell responses. CD8+ T cell depletion abolished the anti-tumor effects, underscoring the essential role of functional CD8+ T cell responses. Moreover, the combined treatment promoted memory CD8+ T cell induction, providing long-term protection. In liver orthotopic tumor models, the combination of pGPC3 vaccine and alisertib demonstrated potent therapeutic efficacy through CD8+ T cell responses. These results indicate that alisertib enhances the pGPC3 vaccine's therapeutic effect, offering a promising strategy for HCC treatment.

PMID:40230537 | PMC:PMC11995041 | DOI:10.1016/j.isci.2025.112120

iScience. 2025 Mar 13;28(4):112221. doi: 10.1016/j.isci.2025.112221. eCollection 2025 Apr 18.

ABSTRACT

Here, we aim to improve our understanding of various colorectal cancer (CRC) risk factors (obesity, unhealthy diet, and gut microbiota/metabolome alteration), analyzing 120 patients with colon polyps, divided in normal-weight (NW) or overweight/obese (OB). Dietary habits data (validated EPIC questionnaires) revealed a higher consumption of processed meat among OB vs. NW patients. Both mucosa-associated microbiota (MAM) on polyps and lumen-associated microbiota (LAM) analyses uncovered distinct bacterial signatures in the two groups. Importantly, we found an enrichment of the pathogenic species Finegoldia magna in MAM of OB patients, regardless of their polyp stage. We observed distinct mucosal-associated metabolome signatures, with OB patients showing increased pyroglutamic acid and reduced niacin levels, and performed microbiota-metabolome integrated analysis. These findings support a model where different risk factors may contribute to tumorigenesis in OB vs. NW patients, highlighting the potential impact of processed meat consumption and F. magna on CRC development among OB patients.

PMID:40230532 | PMC:PMC11995084 | DOI:10.1016/j.isci.2025.112221

ACS Synth Biol. 2025 Apr 15. doi: 10.1021/acssynbio.4c00780. Online ahead of print.

ABSTRACT

The subunit dissociation of oligomeric enzymes is a major challenge that limits their practical applications. In this study, yeast-surface-displayed tetrameric β-glucuronidase with a C-terminal anchor protein fusion was found partially dissociated into dimers. The coexpression of free and anchored subunits significantly improved the display efficiency and catalytic activity. Given that oligomeric enzymes may adopt a non-native conformation on the cell surface, the subunit interfaces of surface-displayed β-glucuronidase were in situ characterized using a Förster resonance energy transfer (FRET) strategy, and the tetrameric structure was well maintained in the coexpressed β-glucuronidases. Finally, the coexpression strategy was applied to yeast-surface-displayed oligomeric cellulases, significantly enhancing the activities of tetrameric endoglucanase and dimeric β-glucosidase and the concentration of cellulosic ethanol for the two-enzyme codisplaying strain. This work provides insights into the structure-activity relationship and the efficient utilization of surface-displayed oligomeric enzymes.

PMID:40230192 | DOI:10.1021/acssynbio.4c00780

Endocrinol Metab (Seoul). 2025 Apr 15. doi: 10.3803/EnM.2024.2200. Online ahead of print.

ABSTRACT

BACKGROUND: Despite their efficacy, statin-related adverse events (AEs) may interfere with statin treatment and contribute to negative outcomes in patients with cardiovascular diseases. In this study, we evaluated the safety and effectiveness of pravastatin in Korea.

METHODS: Pooled data were collected from four multicenter prospective observational studies conducted in Korea between 2011 and 2020. Finally, 7,334 and 2,022 participants were included in the safety and effectiveness analyses, respectively. Overall safety, particularly muscle-related, incidence of new-onset diabetes mellitus (DM), changes in fasting plasma glucose and hemoglobin A1c level, achievement of target low-density lipoprotein cholesterol (LDL-C) level, and changes in LDL-C level were analyzed.

RESULTS: At week 24, after 20 or 40 mg pravastatin treatment, safety results showed that AEs and adverse drug reactions (ADRs) were 8.7% and 1.3%, respectively, and that muscle-related AEs and ADRs were 0.5% and 0.3%, respectively, with no statistically significant difference in risk factors for statin-associated muscle symptoms. No patients developed DM during the study period. Additionally, at week 24, the achievement rates of target LDL-C levels were 87.9%, 78.4%, 57.8%, and 11.6% in low-, moderate-, high-, and very high-risk groups, respectively.

CONCLUSION: This study found that 20 or 40 mg pravastatin had minimal side effects and was safe for use in real-world clinical settings in Korea. Specifically, these doses effectively achieved the target LDL-C levels in patients with dyslipidemia in low-, moderate-, and high-risk groups for atherosclerotic cardiovascular disease (ASCVD). These results demonstrate that pravastatin can be safely administered continuously to patients with low-, moderate-, and high-risk ASCVD in a real-world clinical setting.

PMID:40229969 | DOI:10.3803/EnM.2024.2200

Genome Med. 2025 Apr 14;17(1):40. doi: 10.1186/s13073-025-01464-2.

ABSTRACT

BACKGROUND: Both promoters and untranslated regions (UTRs) have critical regulatory roles, yet variants in these regions are largely excluded from clinical genetic testing due to difficulty in interpreting pathogenicity. The extent to which these regions may harbour diagnoses for individuals with rare disease is currently unknown.

METHODS: We present a framework for the identification and annotation of potentially deleterious proximal promoter and UTR variants in known dominant disease genes. We use this framework to annotate de novo variants (DNVs) in 8040 undiagnosed individuals in the Genomics England 100,000 genomes project, which were subject to strict region-based filtering, clinical review, and validation studies where possible. In addition, we performed region and variant annotation-based burden testing in 7862 unrelated probands against matched unaffected controls.

RESULTS: We prioritised eleven DNVs and identified an additional variant overlapping one of the eleven. Ten of these twelve variants (82%) are in genes that are a strong match to the individual's phenotype and six had not previously been identified. Through burden testing, we did not observe a significant enrichment of potentially deleterious promoter and/or UTR variants in individuals with rare disease collectively across any of our region or variant annotations.

CONCLUSIONS: Whilst screening promoters and UTRs can uncover additional diagnoses for individuals with rare disease, including these regions in diagnostic pipelines is not likely to dramatically increase diagnostic yield. Nevertheless, we provide a framework to aid identification of these variants.

PMID:40229884 | DOI:10.1186/s13073-025-01464-2

Best Pract Res Clin Rheumatol. 2025 Apr 13:102064. doi: 10.1016/j.berh.2025.102064. Online ahead of print.

ABSTRACT

This update addresses new developments in imaging of axial spondyloarthritis from the past 5 years. These have focused mostly on enhanced CT and MRI-based technologies that bring greater precision to the assessment of both inflammatory and structural lesions in the sacroiliac joint. An international consensus has recommended a 4-sequence MRI for routine diagnostic evaluation of the sacroiliac joint aimed at depicting the location and extent of inflammation as well as an erosion-sensitive sequence for structural damage. The latter include high resolution thin slice sequences that accentuate the interface between subchondral bone and the overlying cartilage and joint space as well as synthetic CT, a deep learning-based technique that transforms certain MRI sequences into images resembling CT. Algorithms based on deep learning derived from plain radiographic, CT, and MRI datasets are increasingly more accurate at identifying sacroiliitis and individual lesions observed on images of the sacroiliac joints and spine.

PMID:40229184 | DOI:10.1016/j.berh.2025.102064

Zhongguo Zhen Jiu. 2025 Apr 12;45(4):413-420. doi: 10.13703/j.0255-2930.20240611-0001. Epub 2025 Jan 7.

ABSTRACT

OBJECTIVE: To develop an artificial intelligence-assisted system for the automatic detection of the features of common 21 auricular points based on the YOLOv8 neural network.

METHODS: A total of 660 human auricular images from three research centers were collected from June 2019 to February 2024. The rectangle boxes and features of images were annotated using the LabelMe5.3.1 tool and converted them into a format compatible with the YOLO model. Using these data, transfer learning and fine-tuning training were conducted on different scales of pretrained YOLO neural network models. The model's performance was evaluated on validation and test sets, including the mean average precision (mAP) at various thresholds, recall rate (recall), frames per second (FPS) and confusion matrices. Finally, the model was deployed on a local computer, and the real-time detection of human auricular images was conducted using a camera.

RESULTS: Five different versions of the YOLOv8 key-point detection model were developed, including YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, and YOLOv8x. On the validation set, YOLOv8n showed the best performance in terms of speed (225.736 frames per second) and precision (0.998). On the external test set, YOLOv8n achieved the accuracy of 0.991, the sensitivity of 1.0, and the F1 score of 0.995. The localization performance of auricular point features showed the average accuracy of 0.990, the precision of 0.995, and the recall of 0.997 under 50% intersection ration (mAP50).

CONCLUSION: The key-point detection model of 21 common auricular points based on YOLOv8n exhibits the excellent predictive performance, which is capable of rapidly and automatically locating and classifying auricular points.

PMID:40229149 | DOI:10.13703/j.0255-2930.20240611-0001

NMR Biomed. 2025 May;38(5):e70029. doi: 10.1002/nbm.70029.

ABSTRACT

Previous work indicates evidence that cerebrospinal fluid (CSF) plays a crucial role in brain waste clearance processes and that altered flow patterns are associated with various diseases of the central nervous system. In this study, we investigate the potential of deep learning to predict the distribution in human brain of a gadolinium-based CSF contrast agent (tracer) administered intrathecal. For this, T1-weighted magnetic resonance imaging (MRI) scans taken at multiple time points before and after injection were utilized. We propose a U-net-based supervised learning model to predict pixel-wise signal increase at its peak after 24 h. Performance is evaluated based on different tracer distribution stages provided during training, including predictions from baseline scans taken before injection. Our findings show that training with imaging data from only the first 2-h postinjection yields tracer flow predictions comparable to models trained with additional later-stage scans. Validation against ventricular reflux gradings from neuroradiologists confirmed alignment with expert evaluations. These results demonstrate that deep learning-based methods for CSF flow prediction deserve more attention, as minimizing MR imaging without compromising clinical analysis could enhance efficiency, improve patient well-being and lower healthcare costs.

PMID:40229147 | DOI:10.1002/nbm.70029

Med Phys. 2025 Apr 14. doi: 10.1002/mp.17818. Online ahead of print.

ABSTRACT

BACKGROUND: Accurate and reliable segmentation of esophageal gross tumor volume (GTV) in computed tomography (CT) is beneficial for diagnosing and treating. However, this remains a challenging task because the esophagus has a variable shape and extensive vertical range, resulting in tumors potentially appearing at any position within it.

PURPOSE: This study introduces a novel CNN-transformer-based U-shape model (LRRM-U-TransNet) designed to enhance the segmentation accuracy of esophageal GTV. By leveraging advanced deep learning techniques, we aim to address the challenges posed by the variable shape and extensive range of the esophagus, ultimately improving diagnostic and treatment outcomes.

METHODS: Specifically, we propose a long-range relay mechanism to converge all layer feature information by progressively passing adjacent layer feature maps in the pixel and semantic pathways. Moreover, we propose two ready-to-use blocks to implement this mechanism concretely. The Dual FastViT block interacts with feature maps from two paths to enhance feature representation capabilities. The Dual AxialViT block acts as a secondary auxiliary bottleneck to acquire global information for more precise feature map reconstruction.

RESULTS: We build a new esophageal tumor dataset with 1665 real-world patient CT samples annotated by five expert radiologists and employ multiple evaluation metrics to validate our model. Results of a five-fold cross-validation on this dataset show that LRRM-U-TransNet achieves a Dice coefficient of 0.834, a Jaccard coefficient of 0.730, a Precision of 0.840, a HD95 of 3.234 mm, and a Volume Similarity of 0.143.

CONCLUSIONS: We propose a CNN-Transformer hybrid deep learning network to improve the segmentation effect of esophageal tumors. We utilize the local and global information between shallower and deeper layers to prevent early information loss and enhance the cross-layer communication. To validate our model, we collect a dataset composed of 1665 CT images of esophageal tumors from Sichuan Tumor Hospital. The results show that our model outperforms the state-of-the-art models. It is of great significance to improve the accuracy and clinical application of esophageal tumor segmentation.

PMID:40229138 | DOI:10.1002/mp.17818

Prog Neuropsychopharmacol Biol Psychiatry. 2025 Apr 12:111363. doi: 10.1016/j.pnpbp.2025.111363. Online ahead of print.

ABSTRACT

Pharmacogenetics in psychiatry may have benefits for medication treatment success. However, medication regimes leading to drug-drug interactions and potential phenoconversion of actionable pharmacogenetic phenotypes challenge the application of pharmacogenetics. Although polypharmacy is common, its impact in patients with psychosis is understudied, even though these patients might benefit from pharmacogenetics-guided medication adjustment. Here, we investigated the impact of two pharmacogenes relevant in psychiatric practice, CYP2C19 and CYP2D6, and the effect of sex and age. Medication use and predicted occurrence of phenoconversion was examined in a sample of patients with psychosis over a period of approximately six years. Bayesian statistics were applied to examine longitudinal effects. Our results show that women used more medications, including CYP2C19 and CYP2D6 inhibitors and (actionable) substrates. No significant sex or age differences were found for phenoconversion of either enzyme. A sex-effect on CYP2C19 inhibitor use was found but appeared to be driven by weakly inhibiting oral contraceptives, which were reported only in women. The phenoconversion rate for both enzymes appeared to change over time, suggesting that phenoconversion is a dynamic state that may affect patients differently over their lifetime. To further improve treatment in this patient population, long-term and regular updated medication monitoring in (pharmacogenetic) research as well as application in practice are recommended.

PMID:40228694 | DOI:10.1016/j.pnpbp.2025.111363

Bioorg Med Chem Lett. 2025 Apr 12:130240. doi: 10.1016/j.bmcl.2025.130240. Online ahead of print.

ABSTRACT

A series of hybrids (8a-h and 11a-h) containing 2,4-diphenylpyrimidine scaffold and coumarin moiety were designed and synthesized as novel focal adhesion kinase (FAK) inhibitors for the intervention of non-small-cell lung cancer (NSCLC). Most compounds effectively suppressed the proliferative of NSCLC cells, and compound 8a was identified as the most active compound with IC50 value of 0.28 μM in H1299 cells, superior to TAE226 (IC50 = 2.28 μM). In addition, 8a was also found to inhibit the invasion and migration of NSCLC cells. Furthermore, 8a exhibited potent kinase inhibitory activity of FAK (IC50 = 4.968 nM) with a considerable selectivity profile against various kinase families, subsequently resulting in cell cycle arrest, apoptosis- inducing as well as the decrease of MMP-2 and MMP-9 expression in H1299 cells dose-dependently. Moreover, 8a was relatively safe to mice and inhibited the growth of implanted NSCLC tumors more potently than TAE226 in mice. Therefore, 8a may be a promising candidate for the treatment of NSCLC.

PMID:40228675 | DOI:10.1016/j.bmcl.2025.130240

J Cyst Fibros. 2025 Apr 13:S1569-1993(25)00767-2. doi: 10.1016/j.jcf.2025.04.001. Online ahead of print.

NO ABSTRACT

PMID:40229182 | DOI:10.1016/j.jcf.2025.04.001

BMC Pregnancy Childbirth. 2025 Apr 14;25(1):445. doi: 10.1186/s12884-025-07503-5.

ABSTRACT

BACKGROUND: Circulating cell-free RNA (cfRNA) is gaining recognition as an effective biomarker for the early detection of preeclampsia (PE). However, the current methods for selecting disease-specific biomarkers are often inefficient and typically one-dimensional.

PURPOSE: This study introduces a Pyramid Scene Parsing Network (PSPNet) model to predict PE, aiming to improve early risk assessment using cfRNA profiles.

METHODS: The theoretical maximum Preeclamptic Risk Index (PRI) of patients clinically diagnosed with PE is defined as "1", and the control group (NP) is defined as "0", referred to as the clinical PRI. A data preprocessing algorithm was used to screen relevant cfRNA indicators for PE. The cfRNA expression profiles were obtained from the Gene Expression Omnibus (GSE192902), consisting of 180 normal pregnancies (NP) and 69 preeclamptic (PE) samples, collected at two gestational time points: ≤ 12 weeks and 13-20 weeks. Based on the differences in cfRNA expression profiles, the Calculated Ground Truth values of the NP and PE groups in the sequencing data were acquired (Calculated PRI). The differential algorithm was embedded in the PSPNet neural network and the network was then trained using the generated dataset. Subsequently, the real-world sequencing dataset was used to validate and optimize the network, ultimately outputting the PRI values of the healthy control group and the PE group (PSPNet-based PRI). The model's predictive ability for PE was evaluated by comparing the fit between Calculated PRI (Calculated Ground Truth) and PSPNet-based PRI.

RESULTS: The mean absolute error (MAE) between the Calculated Ground Truth the PSPNet-based PRI was 0.0178 for cfRNA data sampled at ≤ 12 gws and 0.0195 for data sampled at 13-20 gws. For cfRNA data sequenced at ≤ 12 gws and 13-20 gws, the corresponding loss values, maximum absolute errors, peak-to-valley error values, mean absolute errors, and average prediction times per sample were 0.0178 (0.0195).

CONCLUSIONS: The present PSPNet model is reliable and fast for cfRNA-based PE prediction and its PRI output allows for continuous PE risk monitoring, introducing an innovative and effective method for early PE prediction. This model enables timely interventions and better management of pregnancy complications, particularly benefiting densely populated developing countries with high PE incidence and limited access to routine prenatal care.

PMID:40229739 | DOI:10.1186/s12884-025-07503-5

BMC Med Imaging. 2025 Apr 14;25(1):120. doi: 10.1186/s12880-025-01661-w.

ABSTRACT

Polyp segmentation is crucial in computer-aided diagnosis but remains challenging due to the complexity of medical images and anatomical variations. Current state-of-the-art methods struggle with accurate polyp segmentation due to the variability in size, shape, and texture. These factors make boundary detection challenging, often resulting in incomplete or inaccurate segmentation. To address these challenges, we propose DCATNet, a novel deep learning architecture specifically designed for polyp segmentation. DCATNet is a U-shaped network that combines ResNetV2-50 as an encoder for capturing local features and a Transformer for modeling long-range dependencies. It integrates three key components: the Geometry Attention Module (GAM), the Contextual Attention Gate (CAG), and the Multi-scale Feature Extraction (MSFE) block. We evaluated DCATNet on five public datasets. On Kvasir-SEG and CVC-ClinicDB, the model achieved mean dice scores of 0.9351 and 0.9444, respectively, outperforming previous state-of-the-art (SOTA) methods. Cross-validation further demonstrated its superior generalization capability. Ablation studies confirmed the effectiveness of each component in DCATNet. Integrating GAM, CAG, and MSFE effectively improves feature representation and fusion, leading to precise and reliable segmentation results. These findings underscore DCATNet's potential for clinical application and can be used for a wide range of medical image segmentation tasks.

PMID:40229681 | DOI:10.1186/s12880-025-01661-w

J Chem Inf Model. 2025 Apr 14. doi: 10.1021/acs.jcim.5c00476. Online ahead of print.

ABSTRACT

Recently, therapeutic peptides have demonstrated great promise for cancer treatment. To explore powerful anticancer peptides, artificial intelligence (AI)-based approaches have been developed to systematically screen potential candidates. However, the lack of efficient featurization of peptides has become a bottleneck for these machine-learning models. In this paper, we propose a topology-enhanced machine learning model (Top-ML) for anticancer peptide prediction. Our Top-ML employs peptide topological features derived from its sequence "connection" information characterized by spectral descriptors. Our Top-ML model, employing an Extra-Trees classifier, has been validated on the AntiCP 2.0 and mACPpred 2.0 benchmark data sets, achieving state-of-the-art performance or results comparable to existing deep learning models, while providing greater interpretability. Our results highlight the potential of leveraging novel topology-based featurization to accelerate the identification of anticancer peptides.

PMID:40229641 | DOI:10.1021/acs.jcim.5c00476

Commun Med (Lond). 2025 Apr 14;5(1):116. doi: 10.1038/s43856-025-00776-z.

ABSTRACT

BACKGROUND: Endotracheal intubation (ETI) is an emergency procedure performed in civilians and combat casualty care settings to establish an airway. It's crucial that healthcare personnel are proficient in these skills, which traditionally have been evaluated through direct feedback from experts. Unfortunately, this method can be inconsistent and subjective, requiring considerable time and resources.

METHODS: This study introduces a system for assessing ETI skills using video analysis. The system employs advanced video processing techniques, including a 2D convolutional autoencoder (AE) based on a self-supervision model, capable of recognizing complex patterns in videos. A 1D convolutional model enhanced with a cross-view attention module then uses AE features to make assessments. Data for the study was gathered in two phases, focusing first on comparisons between experts and novices, and then examining how novices perform under time constraints with outcomes labeled as either successful or unsuccessful. A separate set of data using videos from head-mounted cameras was also analyzed.

RESULTS: The system successfully distinguishes between experts and novices in initial trials and demonstrates high accuracy in further classifications, including under time pressure and using head-mounted camera footage.

CONCLUSIONS: This system's ability to accurately differentiate between experts and novices instills confidence in its effectiveness and potential to improve training and certification processes for healthcare providers.

PMID:40229550 | DOI:10.1038/s43856-025-00776-z

Commun Biol. 2025 Apr 14;8(1):606. doi: 10.1038/s42003-025-08009-8.

ABSTRACT

We had previously reported a convolutional neural network (CNN) based approach, called the holistic kinetic model (HK model 1), for detecting 5-methylcytosine (5mC) by single molecule real-time sequencing (Pacific Biosciences). In this study, we constructed a hybrid model with CNN and transformer layers, named HK model 2. We improve the area under the receiver operating characteristic curve (AUC) for 5mC detection from 0.91 for HK model 1 to 0.99 for HK model 2. We further demonstrate that HK model 2 can detect other types of base modifications, such as 5-hydroxymethylcytosine (5hmC) and N6-methyladenine (6mA). Using HK model 2 to analyze 5mC patterns of cell-free DNA (cfDNA) molecules, we demonstrate the enhanced detection of patients with hepatocellular carcinoma, with an AUC of 0.97. Moreover, HK model 2-based detection of 6mA enables the detection of jagged ends of cfDNA and the delineation of cellular chromatin structures. HK model 2 is thus a versatile tool expanding the applications of single molecule real-time sequencing in liquid biopsies.

PMID:40229481 | DOI:10.1038/s42003-025-08009-8

Sci Rep. 2025 Apr 14;15(1):12801. doi: 10.1038/s41598-025-97719-4.

ABSTRACT

Current artificial intelligence (AI) trends are revolutionizing medical image processing, greatly improving cervical cancer diagnosis. Machine learning (ML) algorithms can discover patterns and anomalies in medical images, whereas deep learning (DL) methods, specifically convolutional neural networks (CNNs), are extremely accurate at identifying malignant lesions. Deep models that have been pre-trained and tailored through transfer learning and fine-tuning become faster and more effective, even when data is scarce. This paper implements a state-of-the-art Hybrid Learning Network that combines the Progressive Resizing approach and Principal Component Analysis (PCA) for enhanced cervical cancer diagnostics of whole slide images (WSI) slides. ResNet-152 and VGG-16, two fine-tuned DL models, are employed together with transfer learning to train on augmented and progressively resized training data with dimensions of 224 × 224, 512 × 512, and 1024 × 1024 pixels for enhanced feature extraction. Principal component analysis (PCA) is subsequently employed to process the combined features extracted from two DL models and reduce the dimensional space of the feature set. Furthermore, two ML methods, Support Vector Machine (SVM) and Random Forest (RF) models, are trained on this reduced feature set, and their predictions are integrated using a majority voting approach for evaluating the final classification results, thereby enhancing overall accuracy and reliability. The accuracy of the suggested framework on SIPaKMeD data is 99.29% for two-class classification and 98.47% for five-class classification. Furthermore, it achieves 100% accuracy for four-class categorization on the LBC dataset.

PMID:40229435 | DOI:10.1038/s41598-025-97719-4