F1000Res. 2024 Jul 9;13:1. doi: 10.12688/f1000research.145146.2. eCollection 2024.

ABSTRACT

Protein phosphatase 2A is a serine/threonine phosphatase with activity dependent on an associated regulatory subunit, serine/threonine-protein phosphatase 2A 56 kDa regulatory subunit delta (δ) isoform (PPP2R5D). PPP2R5D is the δ isoform in the B56 family of regulatory subunits. Abundantly expressed in the brain and involved in a broad range of cellular processes, PPP2R5D plays an essential role in modulating key neuronal pathways and signalling. Pathogenic mutations in the PPP2R5D gene are linked to clinical symptoms characterized by neurodevelopmental delay, intellectual disability, and autism spectrum disorders. The etiology of these genetic disorders remains unknown, which can partly be due to the lack of independently characterized antibodies. Here we have characterized six PPP2R5D commercial antibodies for Western Blot, immunoprecipitation, and immunofluorescence using a standardized experimental protocol based on comparing read-outs in knockout cell lines and isogenic parental controls. These studies are part of a larger, collaborative initiative seeking to address antibody reproducibility by characterizing commercially available antibodies for human proteins and publishing the results openly as a resource for the scientific community. While use of antibodies and protocols vary between laboratories, we encourage readers to use this report as a guide to select the most appropriate antibodies for their specific needs.

PMID:39935523 | PMC:PMC11811605 | DOI:10.12688/f1000research.145146.2

F1000Res. 2024 Jul 23;11:1388. doi: 10.12688/f1000research.125815.2. eCollection 2022.

ABSTRACT

Background Tuberculosis (TB) continues to pose a serious threat to the public health system in India. Although the National Tuberculosis Elimination Program (NTEP) is providing a wide range of interventions from early diagnosis to complete treatment to reduce morbidity and mortality from TB, adverse drug reactions (ADR) remain a challenge in treatment adherence and completion. Methods An observational cross-sectional study was conducted in selected districts of Gujarat state. A total of 593 reported TB patients were recruited with an adjusted unified distribution based on the type of cases, site of diseases, and service facility through a simple random sampling method. A semi-structured questionnaire tool was used to collect socio-demographic, clinical, and ADR-related data from the TB patients. Data was analyzed for the frequency, percentage, chi-squared, and adjusted odds ratio to find the association between the variables. Results The majority of the study participants were male (87.2%), aged 15 to 60 (57.8%), daily laborers (22.4%), and married (64.2%). Over 75% of individuals had pulmonary TB, with 87% having experienced their first episode, 83% being new cases, and 44.7% having a history of addiction. ADR with mild symptoms was reported by more than a quarter (29%) of TB patients during the intensive phase (77%). The association between ADR experience and drug susceptibility was significant (p<0.005) and drug-resistant TB patients experience two times more ADRs than drug-sensitive TB patients (OR 2.04). Binomial logistic regression was carried out to describe the association between various variables and occurrence of ADRs. Conclusion The study highlighted a need to enhance health care providers' capacity and program structure for managing ADRs among TB patients. In order to completely eliminate TB across the country, it also emphasized the attention for a holistic and all-encompassing strategy for managing TB patients at the field level.

PMID:39935535 | PMC:PMC11811607 | DOI:10.12688/f1000research.125815.2

Orphanet J Rare Dis. 2025 Feb 11;20(1):68. doi: 10.1186/s13023-024-03436-y.

ABSTRACT

BACKGROUND: CD55 deficiency with hyper-activation of complement, angiopathic thrombosis, and protein-losing enteropathy (CHAPLE) disease is a newly identified condition with an estimated worldwide prevalence of < 100 patients. Patient interviews can ensure that what is important to patients is assessed in a clinical trial program. Due to the rare and potentially fatal nature of CHAPLE disease, interviews were conducted as part of the pozelimab clinical trial, rather than in a separate study before the trial. The aim of the interviews was to identify the key disease-related signs, symptoms, and health-related quality-of-life (HRQoL) impacts that are important and relevant to patients with CHAPLE disease.

METHODS: Interviews were conducted with patients and/or caregivers at two timepoints (screening and Week 24) during the pozelimab trial to document the signs/symptoms and HRQoL impacts of CHAPLE disease, and document the most bothersome sign/symptom at screening. At Week 24, interviews gathered additional information on the patient experience from caregivers and patients (note: the impact of pozelimab treatment was also collected, though these results are presented elsewhere).

RESULTS: Ten patients, aged 3-19 years, were enrolled in the trial; caregivers contributed to nine interviews. Thirty-one signs‌/symptoms and 65 HRQoL impacts were reported during the interviews. Abdominal pain, diarrhea, facial and peripheral edema/‌swelling, nausea, and vomiting emerged as the core signs/‌symptoms of CHAPLE disease (i.e., experienced by ≥ 90% of patients prior to treatment). The remaining 25 signs/symptoms were experienced by four or fewer (n ≤ 4, ≤ 40.0%) patients, and 15 were only reported by one patient each. Abdominal pain and facial edema were reported as the most bothersome signs/‌symptoms (n = 9, 90.0% and n = 1, 10.0%, respectively). The most frequently reported (i.e., ≥ 80% of interviews) HRQoL impacts were restricted diet (n = 10, 100.0%), sleep disruptions (n = 10, 100.0%), missing school (n = 9, 90.0%), ability to get dressed independently (n = 8, 80.0%), and difficulty engaging in play activities (n = 8, 80.0%).

CONCLUSIONS: The main finding from these patient interviews is the identification of six core signs/symptoms of CHAPLE disease: abdominal pain, diarrhea, facial edema/swelling, peripheral edema/swelling, nausea, and vomiting. The severity of the core signs/symptoms leads to substantial impacts on patients' lives.

TRIAL REGISTRATION: ClinicalTrials.gov, NCT04209634. Registered 20 December 2019 https://classic.

CLINICALTRIALS: gov/ct2/show/NCT04209634 .

PMID:39934837 | DOI:10.1186/s13023-024-03436-y

Sci Rep. 2025 Feb 11;15(1):5093. doi: 10.1038/s41598-025-89096-9.

ABSTRACT

Medical image segmentation plays a crucial role in addressing emerging healthcare challenges. Although several impressive deep learning architectures based on convolutional neural networks (CNNs) and Transformers have recently demonstrated remarkable performance, there is still potential for further performance improvement due to their inherent limitations in capturing feature correlations of input data. To address this issue, this paper proposes a novel encoder-decoder architecture called MedFuseNet that aims to fuse local and global deep feature representations with hybrid attention mechanisms for medical image segmentation. More specifically, the proposed approach contains two branches for feature learning in parallel: one leverages CNNs to learn local correlations of input data, and the other utilizes Swin-Transformer to capture global contextual correlations of input data. For feature fusion and enhancement, the designed hybrid attention mechanisms combine four different attention modules: (1) an atrous spatial pyramid pooling (ASPP) module for the CNN branch, (2) a cross attention module in the encoder for fusing local and global features, (3) an adaptive cross attention (ACA) module in skip connections for further performing fusion, and (4) a squeeze-and-excitation attention (SE-attention) module in the decoder for highlighting informative features. We evaluate our proposed approach on the public ACDC and Synapse datasets, and achieves the average DSC of 89.73% and 78.40%, respectively. Experimental results on these two datasets demonstrate the effectiveness of our proposed approach on medical image segmentation tasks, outperforming other used state-of-the-art approaches.

PMID:39934248 | DOI:10.1038/s41598-025-89096-9

Radiologie (Heidelb). 2025 Feb 11. doi: 10.1007/s00117-025-01422-4. Online ahead of print.

ABSTRACT

BACKGROUND: The rapid development of large language models (LLMs) opens up new possibilities for the automated processing of medical texts. Transforming unstructured radiology reports into structured data is crucial for efficient use in clinical decision support systems, research, and improving patient care.

OBJECTIVES: What are the challenges of transforming natural language radiology reports into structured data using LLMs? Which methods and architectures are promising? How can the quality and reliability of the extracted data be ensured?

MATERIALS AND METHODS: This article examines current research on the application of LLMs in radiological information processing. Various approaches such as rule-based systems, machine learning, and deep learning models, particularly neural network architectures, are analyzed and compared. The focus is on extracting information such as diagnoses, anatomical locations, findings, and measurements.

RESULTS AND CONCLUSION: LLMs show great potential in transforming reports into structured data. In particular, deep learning models trained on large datasets achieve high accuracies. However, challenges remain, such as dealing with ambiguities, abbreviations, and the variability of linguistic expressions. Combining LLMs with domain-specific knowledge, for example, in the form of ontologies, can further improve the performance of the systems. Integrating contextual information and developing robust evaluation metrics are also important research directions.

PMID:39934245 | DOI:10.1007/s00117-025-01422-4

Sci Rep. 2025 Feb 12;15(1):5157. doi: 10.1038/s41598-024-84922-y.

ABSTRACT

Early detection of ocular diseases is vital to preventing severe complications, yet it remains challenging due to the need for skilled specialists, complex imaging processes, and limited resources. Automated solutions are essential to enhance diagnostic precision and support clinical workflows. This study presents a deep learning-based system for automated classification of ocular diseases using the Ocular Disease Intelligent Recognition (ODIR) dataset. The dataset includes 5,000 patient fundus images labeled into eight categories of ocular diseases. Initial experiments utilized transfer learning models such as DenseNet201, EfficientNetB3, and InceptionResNetV2. To optimize computational efficiency, a novel two-level feature selection framework combining Linear Discriminant Analysis (LDA) and advanced neural network classifiers-Deep Neural Networks (DNN), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BiLSTM)-was introduced. Among the tested approaches, the "Combined Data" strategy utilizing features from all three models achieved the best results, with the BiLSTM classifier attaining 100% accuracy, precision, and recall on the training set, and over 98% performance on the validation set. The LDA-based framework significantly reduced computational complexity while enhancing classification accuracy. The proposed system demonstrates a scalable, efficient solution for ocular disease detection, offering robust support for clinical decision-making. By bridging the gap between clinical demands and technological capabilities, it has the potential to alleviate the workload of ophthalmologists, particularly in resource-constrained settings, and improve patient outcomes globally.

PMID:39934192 | DOI:10.1038/s41598-024-84922-y

Acad Radiol. 2025 Feb 10:S1076-6332(25)00087-X. doi: 10.1016/j.acra.2025.01.032. Online ahead of print.

ABSTRACT

RATIONALE AND OBJECTIVES: Type 2 diabetes is a known risk factor for vascular disease with an impact on the aorta. The aim of this study was to develop a deep learning framework for quantification of aortic phenotypes from magnetic resonance imaging (MRI) and to investigate the association between aortic features and impaired glucose metabolism beyond traditional cardiovascular (CV) risk factors.

MATERIALS AND METHODS: This study used data from the prospective Cooperative Health Research in the Region of Augsburg (KORA) study to develop a deep learning framework for automatic quantification of aortic features (maximum aortic diameter, total volume, length, and width of the aortic arch) derived from MRI. Aortic features were compared between different states of glucose metabolism and tested for associations with impaired glucose metabolism adjusted for traditional CV risk factors (age, sex, height, weight, hypertension, smoking, and lipid panel).

RESULTS: The deep learning framework yielded a high performance for aortic feature quantification with a Dice coefficient of 91.1±0.02. Of 381 participants (58% male, mean age 56 years), 231 (60.6%) had normal blood glucose, 97 (25.5%) had prediabetes, and 53 (13.9%) had diabetes. All aortic features showed a significant increase between different groups of glucose metabolism (p≤0.04). Total aortic length and total aortic volume were associated with impaired glucose metabolism (OR 0.85, 95%CI 0.74-0.96; p=0.01, and OR 0.99, 95%CI 0.98-0.99; p=0.02) independent of CV risk factors.

CONCLUSION: Aortic features showed a glucose level dependent increase from normoglycemic individuals to those with prediabetes and diabetes. Total aortic length and volume were independently and inversely associated with impaired glucose metabolism beyond traditional CV risk factors.

PMID:39934079 | DOI:10.1016/j.acra.2025.01.032

J Prosthet Dent. 2025 Feb 10:S0022-3913(25)00050-2. doi: 10.1016/j.prosdent.2025.01.020. Online ahead of print.

NO ABSTRACT

PMID:39934030 | DOI:10.1016/j.prosdent.2025.01.020

Cancer Metastasis Rev. 2025 Feb 11;44(1):31. doi: 10.1007/s10555-025-10249-3.

ABSTRACT

Cellular plasticity and the ability to avoid terminal differentiation are hallmarks of cancer. Here, we review the evidence that tumor cells themselves can take on properties of neurons of the central nervous system, which can regulate tumor growth and metastasis. We discuss recent evidence that axon guidance molecules and regulators of electrical activity and synaptic transmission, such as ion channels and neurotransmitters, can drive the oncogenic and invasive properties of tumor cells from a range of cancers. We also review how FDA-approved treatments for neurological disorders are being tested in pre-clinical models and clinical trials for repurposing as anti-cancer agents, offering the potential for new therapies for cancer patients that can be accessed more quickly.

PMID:39934425 | DOI:10.1007/s10555-025-10249-3

Eur Arch Psychiatry Clin Neurosci. 2025 Feb 12. doi: 10.1007/s00406-025-01970-9. Online ahead of print.

ABSTRACT

This study investigates treatment-resistant schizophrenia (TRS) by analysing genetic markers in dopamine and serotonin receptors. Conducted on a cohort of 221 patients with treatment-resistant mental disorders, the research focused on DRD2 and HTR2A gene variants-specifically, rs1801028, rs6314, rs7997012, and rs6311. The findings suggest specific associations between certain genetic variants and TRS. Notably, the HTR2A rs6314 A|G genotype and rs7997012 G|G genotype were significantly more prevalent in TRS patients compared to healthy controls (HCs). Haplotype analyses revealed associations between specific haplotypes-such as A|G (rs6314-rs7997012)-and TRS, indicating their potential predictive value for TRS versus HCs. The study underscores the involvement of the serotonergic system in TRS. These findings offer valuable insights into the genetic factors contributing to TRS, paving the way for future research and the development of personalised prevention and treatment strategies in psychiatry.

PMID:39934320 | DOI:10.1007/s00406-025-01970-9

Open Heart. 2025 Feb 11;12(1):e003088. doi: 10.1136/openhrt-2024-003088.

ABSTRACT

AIMS: Clopidogrel is the most commonly prescribed thienopyridine as part of dual anti-platelet therapy for the treatment of cardiovascular diseases. However, clopidogrel responsiveness shows variability based on CYP2C19 polymorphism. Therefore, we planned a study with an objective of evaluating safety, tolerability, pharmacodynamics and pharmacokinetics of a novel thienopyridine antiplatelet agent AT-10 in healthy Indian subjects compared with standard dosage regimen of clopidogrel based on their CYP2C19 genotyping.

METHODS: Two CYP2C19 genotype-based groups were identified, that is, poor metabolisers and extensive metabolisers, with 20 subjects in each group (n=40) for participating in a randomised, two-period, crossover study. Each study period lasted 6 days including administration of loading and maintenance doses of AT-10 (40 mg/10 mg) or clopidogrel (300 mg/75 mg). The pharmacokinetics and pharmacodynamics were assessed on day 1 and day 6 at several time intervals.

RESULTS: Overall result of pharmacodynamic parameters showed that mean %inhibition of platelet aggregation between AT-10 and clopidogrel in all subjects at 6 hours postdose (loading dose) (AT-10: clopidogrel; 73.30% vs 18.53%) and 6 hours postdose on day 6 (maintenance dose) (AT-10: clopidogrel; 83.41% vs 51.19 %) obtained from the AT-10 group was significantly higher than the clopidogrel group. Further, %inhibition of platelet aggregation from AT-10 treatment in poor metaboliser group was significantly higher than the clopidogrel treatments in extensive metaboliser group.Overall pharmacokinetic comparison in all subjects indicates that AT-10 gives greater exposure to active Metabolite H4 than clopidogrel.

CONCLUSION: AT-10 showed better inhibition of platelet aggregation in poor metabolizers as compared to Clopidogrel. AT-10 may emerge as a potential alternative to Clopidogrel as an anti-platelet drug. It can be further developed in clinical studies for the unmet medical needs in management of CVDs and overcome the pharmacogenomic limitations of Clopidogrel.

TRIAL REGISTRATION NUMBER: Clinical Trial Registry-India URL: http://ctri.nic.in.

REGISTRATION NUMBER: CTRI/2021/03/032206.

PMID:39933830 | DOI:10.1136/openhrt-2024-003088

Value Health Reg Issues. 2025 Feb 10;47:101085. doi: 10.1016/j.vhri.2025.101085. Online ahead of print.

ABSTRACT

OBJECTIVES: This study aimed to provide the first evidence of the socioeconomic burden of cystic fibrosis (CF) in Czechia.

METHODS: In a cross-sectional questionnaire-based primary data collection conducted from 2020 to 2021 among Czech patients with CF, we collected demographic, clinical, and healthcare resource use data, out-of-pocket and social transfer costs, and questionnaires: Cystic Fibrosis Questionnaire-Revised, Work Productivity and Activity Impairment, EQ-5D, and Zarit Burden Interview. Productivity loss/costs were assessed using the human capital approach with patient patient-assumed life expectancy of 45 years and caregiver retirement age of 64 years and discounted by 3%.

RESULTS: A total of 257 patients completed the questionnaires (37% of the Czech CF population). The average age was 17 years; most were females (59%), and the average forced expiratory volume in 1 second was 81.4% (SD 25.4%). A total of 107 patients had caregivers with an average age of 39 years and a significant caregiver time burden (extra 4.6 hours/day). The average Zarit Burden Interview score (25.4) was comparable with advanced cancer, dementia, or Duchenne muscular dystrophy. The proportion of unemployed caregivers was 10× higher than the general population (31% vs 3.2%). Total out-of-pocket family costs related to CF were €278/month, mainly for medicines (€105), foods (€73), and transport (€59); 25% received a disability pension and 18% other social security benefits. The work impairment of employed patients and caregivers was 25% and 15%, respectively, mostly due to presenteeism. Total lifetime productivity costs extrapolated to all Czech patients with CF (n = 687) and their caregivers were €155 181 286 (€225 883/person).

CONCLUSIONS: The societal burden imposed on Czech patients with CF and their caregivers is significant. Caregivers seem to be affected by higher disease activity more than patients.

PMID:39933437 | DOI:10.1016/j.vhri.2025.101085

Plant Methods. 2025 Feb 11;21(1):16. doi: 10.1186/s13007-025-01334-3.

ABSTRACT

In the era of machine learning-driven plant imaging, the production of annotated datasets is a very important contribution. In this data paper, a unique annotated dataset of seedling emergence kinetics is proposed. It is composed of almost 70,000 RGB-depth frames and more than 700,000 plant annotations. The dataset is shown valuable for training deep learning models and performing high-throughput phenotyping by imaging. The ability of such models to generalize to several species and outperform the state-of-the-art owing to the delivered dataset is demonstrated. We also discuss how this dataset raises new questions in plant phenotyping.

PMID:39934882 | DOI:10.1186/s13007-025-01334-3

BMC Med Inform Decis Mak. 2025 Feb 11;25(1):73. doi: 10.1186/s12911-025-02895-y.

ABSTRACT

BACKGROUND: Despite recent progress in misinformation detection methods, further investigation is required to develop more robust fact-checking models with particular consideration for the unique challenges of health information sharing. This study aimed to identify the most effective approach for detecting and classifying reliable information versus misinformation health content shared on Twitter/X related to COVID-19.

METHODS: We have used 7 different machine learning/deep learning models. Tweets were collected, processed, labeled, and analyzed using relevant keywords and hashtags, then classified into two distinct datasets: "Trustworthy information" versus "Misinformation", through a labeling process. The cosine similarity metric was employed to address oversampling the minority of the Trustworthy information class, ensuring a more balanced representation of both classes for training and testing purposes. Finally, the performance of the various fact-checking models was analyzed and compared using accuracy, precision, recall, and F1-score ROC curve, and AUC.

RESULTS: For measures of accuracy, precision, F1 score, and recall, the average values of TextConvoNet were found to be 90.28, 90.28, 90.29, and 0.9030, respectively. ROC AUC was 0.901."Trustworthy information" class achieved an accuracy of 85%, precision of 93%, recall of 86%, and F1 score of 89%. These values were higher than other models. Moreover, its performance in the misinformation category was even more impressive, with an accuracy of 94%, precision of 88%, recall of 94%, and F1 score of 91%.

CONCLUSION: This study showed that TextConvoNet was the most effective in detecting and classifying trustworthy information V.S misinformation related to health issues that have been shared on Twitter/X.

PMID:39934858 | DOI:10.1186/s12911-025-02895-y

BMC Med Inform Decis Mak. 2025 Feb 11;25(1):71. doi: 10.1186/s12911-024-02828-1.

ABSTRACT

This study proposes a deep learning-based motion assessment method that integrates the pose estimation algorithm (Keypoint RCNN) with signal processing techniques, demonstrating its reliability and effectiveness.The reliability and validity of this method were also verified.Twenty college students were recruited to pedal a stationary bike. Inertial sensors and a smartphone simultaneously recorded the participants' cycling movement. Keypoint RCNN(KR) algorithm was used to acquire 2D coordinates of the participants' skeletal keypoints from the recorded movement video. Spearman's rank correlation analysis, intraclass correlation coefficient (ICC), error analysis, and t-test were conducted to compare the consistency of data obtained from the two movement capture systems, including the peak frequency of acceleration, transition time point between movement statuses, and the complexity index average (CIA) of the movement status based on multiscale entropy analysis.The KR algorithm showed excellent consistency (ICC1,3=0.988) between the two methods when estimating the peak acceleration frequency. Both peak acceleration frequencies and CIA metrics estimated by the two methods displayed a strong correlation (r > 0.70) and good agreement (ICC2,1>0.750). Additionally, error values were relatively low (MAE = 0.001 and 0.040, MRE = 0.00% and 7.67%). Results of t-tests showed significant differences (p = 0.003 and 0.030) for various acceleration CIAs, indicating our method could distinguish different movement statuses.The KR algorithm also demonstrated excellent intra-session reliability (ICC = 0.988). Acceleration frequency analysis metrics derived from the KR method can accurately identify transitions among movement statuses. Leveraging the KR algorithm and signal processing techniques, the proposed method is designed for individualized motor function evaluation in home or community-based settings.

PMID:39934805 | DOI:10.1186/s12911-024-02828-1

BMC Bioinformatics. 2025 Feb 11;26(1):50. doi: 10.1186/s12859-025-06068-6.

ABSTRACT

BACKGROUND: Piwi-interacting RNAs (piRNAs) are well established for monitoring and protecting the genome from transposons in germline cells. Recently, numerous studies provided evidence that piRNAs also play important roles in regulating mRNA transcript levels. Despite their significant role in regulating cellular RNA levels, the piRNA targeting rules are not well defined, especially in mammals, which poses obstacles to the elucidation of piRNA function.

RESULTS: Given the complexity and current limitation in understanding the mammalian piRNA targeting rules, we designed a deep learning model by selecting appropriate deep learning sub-networks based on the targeting patterns of piRNA inferred from previous experiments. Additionally, to alleviate the problem of insufficient data, a transfer learning approach was employed. Our model achieves a good discriminatory power (Accuracy: 98.5%) in predicting an independent test dataset. Finally, this model was utilized to predict the targets of all mouse and human piRNAs available in the piRNA database.

CONCLUSIONS: In this research, we developed a deep learning framework that significantly advances the prediction of piRNA targets, overcoming the limitations posed by insufficient data and current incomplete targeting rules. The piRNA target prediction network and results can be downloaded from https://github.com/SofiaTianjiaoZhang/piRNATarget .

PMID:39934678 | DOI:10.1186/s12859-025-06068-6

BMC Bioinformatics. 2025 Feb 11;26(1):48. doi: 10.1186/s12859-025-06051-1.

ABSTRACT

BACKGROUND: Alterations of metabolism, including changes in mitochondrial metabolism as well as glutathione (GSH) metabolism are a well appreciated hallmark of many cancers. Mitochondrial GSH (mGSH) transport is a poorly characterized aspect of GSH metabolism, which we investigate in the context of cancer. Existing functional annotation approaches from machine (ML) or deep learning (DL) models based only on protein sequences, were unable to annotate functions in biological contexts.

RESULTS: We develop a flexible ML framework for functional annotation from diverse feature data. This hybrid ML framework leverages cancer cell line multi-omics data and other biological knowledge data as features, to uncover potential genes involved in mGSH metabolism and membrane transport in cancers. This framework achieves strong performance across functional annotation tasks and several cell line and primary tumor cancer samples. For our application, classification models predict the known mGSH transporter SLC25A39 but not SLC25A40 as being highly probably related to mGSH metabolism in cancers. SLC25A10, SLC25A50, and orphan SLC25A24, SLC25A43 are predicted to be associated with mGSH metabolism in multiple biological contexts and structural analysis of these proteins reveal similarities in potential substrate binding regions to the binding residues of SLC25A39.

CONCLUSION: These findings have implications for a better understanding of cancer cell metabolism and novel therapeutic targets with respect to GSH metabolism through potential novel functional annotations of genes. The hybrid ML framework proposed here can be applied to other biological function classifications or multi-omics datasets to generate hypotheses in various biological contexts. Code and a tutorial for generating models and predictions in this framework are available at: https://github.com/lkenn012/mGSH_cancerClassifiers .

PMID:39934670 | DOI:10.1186/s12859-025-06051-1

Sci Rep. 2025 Feb 11;15(1):5080. doi: 10.1038/s41598-025-89752-0.

ABSTRACT

The detection and classification of arrhythmia play a vital role in the diagnosis and management of cardiac disorders. Many deep learning techniques are utilized for arrhythmia classification in current research but only based on ECG data, lacking the mathematical foundations of cardiac electrophysiology. A finite element model (FEM) of the human heart based on the FitzHugh-Nagumo (FHN) model was established for cardiac electrophysiology simulation and the ECG signals were acquired from the FEM results of representative points. Two different kinds of arrhythmia characterized by major anomalies of parameters a and ɛ in the FHN model were simulated, and the synthetic ECG signals were obtained respectively. A multi-objective optimization method based on non-dominated sorting was incorporated into the crayfish optimization algorithm to optimize the key parameters in VMD, then a variational mode decomposition technique for ECG signal processing based on a multi-objective crayfish optimization algorithm (MOCOA-VMD) was proposed, wherein the spectral kurtosis and KL divergence were determined as the indicators for decomposition. The Pareto optimal front was generated by MOCOA and the intrinsic mode functions of VMD with the best combination of K and α were obtained. A deep attention model based on MOCOA-VMD was constructed for ECG signal classification. The ablation study was implemented to verify the effectiveness of the proposed signal decomposition method and deep attention modules. The performance of the model based on MOCOA-VMD achieves the best accuracy of 94.35%, much higher than the model constructed by modules of EEMD, VMD and CNN. Moreover, Bayesian optimization was carried out to fine-tune the hyperparameters batch size, learning rate, epochs, and momentum. After TPE optimization, the deep model's performance achieved a maximum accuracy of 95.91%. The MIT-BIH arrhythmia database was further utilized for model validation, ascertaining its robustness and generalizability. The proposed deep attention modeling and classification strategy can help in arrhythmia signal processing and may offer inspiration for other signal processing fields as well.

PMID:39934416 | DOI:10.1038/s41598-025-89752-0

Sci Rep. 2025 Feb 11;15(1):5117. doi: 10.1038/s41598-025-89768-6.

ABSTRACT

CorneAI, a deep learning model designed for diagnosing cataracts and corneal diseases, was assessed for its impact on ophthalmologists' diagnostic accuracy. In the study, 40 ophthalmologists (20 specialists and 20 residents) classified 100 images, including iPhone 13 Pro photos (50 images) and diffuser slit-lamp photos (50 images), into nine categories (normal condition, infectious keratitis, immunological keratitis, corneal scar, corneal deposit, bullous keratopathy, ocular surface tumor, cataract/intraocular lens opacity, and primary angle-closure glaucoma). The iPhone and slit-lamp images represented the same cases. After initially answering without CorneAI, the same ophthalmologists responded to the same cases with CorneAI 2-4 weeks later. With CorneAI's support, the overall accuracy of ophthalmologists increased significantly from 79.2 to 88.8% (P < 0.001). Specialists' accuracy rose from 82.8 to 90.0%, and residents' from 75.6 to 86.2% (P < 0.001). Smartphone image accuracy improved from 78.7 to 85.5% and slit-lamp image accuracy from 81.2 to 90.6% (both, P < 0.001). In this study, CorneAI's own accuracy was 86%, but its support enhanced ophthalmologists' accuracy beyond the CorneAI's baseline. This study demonstrated that CorneAI, despite being trained on diffuser slit-lamp images, effectively improved diagnostic accuracy, even with smartphone images.

PMID:39934383 | DOI:10.1038/s41598-025-89768-6

Sci Rep. 2025 Feb 11;15(1):5121. doi: 10.1038/s41598-025-88734-6.

ABSTRACT

Stock market stability relies on the shares, investors, and stakeholders' participation and global commodity exchanges. In general, multiple factors influence the stock market stability to ensure profitable returns and commodity transactions. This article presents a contradictory-factor-based stability prediction model using the sigmoid deep learning paradigm. Sigmoid learning identifies the possible stabilizations of different influencing factors toward a profitable stock exchange. In this model, each influencing factor is mapped with the profit outcomes considering the live shares and their exchange value. The stability is predicted using sigmoid and non-sigmoid layers repeatedly until the maximum is reached. This stability is matched with the previous outcomes to predict the consecutive hours of stock market changes. Based on the actual changes and predicted ones, the sigmoid function is altered to accommodate the new range. The non-sigmoid layer remains unchanged in the new changes to improve the prediction precision. Based on the outcomes the deep learning's sigmoid layer is trained to identify abrupt changes in the stock market.

PMID:39934296 | DOI:10.1038/s41598-025-88734-6