JMIR bioinformatics and biotechnology最新文献

{"title":"Enriching Public Pathogen Genomic Records With Patient Metadata: Quantitative Study and Exploratory Case Analysis.","authors":"Michael J Pavia, Karen O'Connor, Graciela Gonzalez-Hernandez, Matthew Scotch","doi":"10.2196/92529","DOIUrl":"10.2196/92529","url":null,"abstract":"<p><strong>Background: </strong>During the COVID-19 pandemic, large-scale sequencing generated millions of SARS-CoV-2 genomes in public repositories including GenBank and GISAID. However, most records lack detailed patient metadata, including demographic information and clinical outcomes. This lack of host-associated information limits their utility for large-scale pathogen genomics analyses. Although sequence records linked to journal publications may contain relevant metadata, systematically extracting and linking this information requires substantial manual effort.</p><p><strong>Objective: </strong>This study aimed to assess host metadata completeness in GenBank SARS-CoV-2 records and to demonstrate, through an exploratory case study, analytical opportunities enabled by enriched clinical and demographic annotations for genomic epidemiology.</p><p><strong>Methods: </strong>The authors searched LitCovid for PubMed Central (PMC) articles published between January 2023 and December 2024 that reported original complete SARS-CoV-2 genome sequences deposited in GenBank with sequence-specific patient metadata from human hosts. Two independent reviewers screened eligible articles and manually extracted metadata on sample collection, demographics, treatments, serology, vaccination status, infection presentation, and clinical outcomes. Enriched metadata were defined as patient information in the publication but absent from GenBank records. Synonymous clinical and demographic terms were standardized using SNOMED CT, and Charlson Comorbidity Index scores were calculated when metadata were available. SARS-CoV-2 genomes were retrieved, assembled, and subjected to quality control using standard bioinformatics tools. To demonstrate enriched metadata's analytical value, we selected a subset of genomes with longitudinal sequencing, comprising 100 genomes from 34 patients across 4 studies for exploratory analysis of within-host viral evolution and patient outcomes.</p><p><strong>Results: </strong>Among 116,600 articles identified through our PMC/LitCovid screening framework, approximately 0.02% (n=21) reported original complete SARS-CoV-2 genomes deposited in GenBank with accessible sequence-specific metadata. Within this eligible set, GenBank records contained on average 22% completeness for host metadata in our extraction schema. Completeness was confined to sample fields (averaging 81%); host demographic and clinical fields averaged 2%. Manual enrichment increased overall completeness by 30% on average, recovering 56% (14/25) of metadata types absent from GenBank records. In the longitudinal subset, enriched metadata enabled host-stratified analyses, showing nominal associations between immunocompromised status and higher within-host evolutionary rates (<i>P</i>=.02) and unique amino acid mutations (<i>P</i>=.04). Models with enriched patient and treatment metadata outperformed mutation-only models for mortality, hospitalization, and infection duration.</p><p>","PeriodicalId":73552,"journal":{"name":"JMIR bioinformatics and biotechnology","volume":"7 ","pages":"e92529"},"PeriodicalIF":0.0,"publicationDate":"2026-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13641315/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of aiAtlas Version 1.2 to Simulate Variant Gene Function Restoration and Rescue Thresholds in Rare Diseases: Validation Case Study.","authors":"Wayne Danter","doi":"10.2196/88672","DOIUrl":"10.2196/88672","url":null,"abstract":"<p><strong>Background: </strong>Xeroderma pigmentosum group D (XPD), caused by ERCC2 gene dysfunction, leads to defective nucleotide excision repair and hypersensitivity to UV radiation. Robust experimental models for variant-level functional assessment remain limited.</p><p><strong>Objective: </strong>This study aimed to use aiAtlas version 1.2, a mechanistic large-concept simulation model, to evaluate the functional consequences of ERCC2 (XPD) variants and identify quantitative thresholds for functional rescue under graded gene function restoration.</p><p><strong>Methods: </strong>We simulated 136 virtual artificially induced pluripotent stem cell-derived cell lines spanning wild-type, single-mutation, multi-mutation, human tumor-derived, and gene fusion ERCC2 states. Twenty-five features encompassing DNA damage and repair, replication stress, pluripotency, and epigenetic remodeling were analyzed using nonparametric statistics with Bonferroni correction, Hodges-Lehmann estimates, and Cliff δ with bootstrap CIs. Graded ERCC2 restoration (0%-100%) was simulated to evaluate rescue thresholds. Cross-validation, bagging, and bootstrap resampling tested robustness.</p><p><strong>Results: </strong>Simulations identified 3 nonlinear ERCC2 (XPD) rescue thresholds: approximately 20% to 30% (initial stabilization of repair), approximately 50% (near normalization), and more than 80% (full convergence). Reduced-function variants required substantially less restoration than strict loss-of-function variants to cross each threshold. Group comparisons across variant classes showed consistent differences in DNA repair, replication stress, and epigenetic remodeling features supported by effect size metrics and CIs.</p><p><strong>Conclusions: </strong>aiAtlas version 1.2 provides a simulation-based mechanistic framework for variant-level functional modeling in ERCC2 (XPD). The simulations identified quantitative thresholds that support mechanistic hypothesis generation regarding variant-dependent restoration of function. These findings provide a computational basis for future studies and require independent validation before clinical application.</p>","PeriodicalId":73552,"journal":{"name":"JMIR bioinformatics and biotechnology","volume":"7 ","pages":"e88672"},"PeriodicalIF":0.0,"publicationDate":"2026-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13597013/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149026779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Generative and Graph-Based Representation Learning for Multiomics Survival Stratification in Ovarian Cancer: Secondary Analysis.","authors":"Carlos Marino, Claudia Diaz Paz","doi":"10.2196/89069","DOIUrl":"10.2196/89069","url":null,"abstract":"<p><strong>Background: </strong>Ovarian cancer remains one of the most lethal gynecologic malignancies, largely due to pronounced molecular heterogeneity, nonspecific clinical presentation, and frequent diagnosis at advanced stages. Multiomics profiling-including genomics, transcriptomics, and epigenomics-offers a powerful avenue for characterizing this complexity and enabling more precise patient stratification.</p><p><strong>Objective: </strong>This study aimed to address key challenges in multiomics analysis, including high dimensionality, cross-modality heterogeneity, limited sample size, and the lack of effective approaches for survival stratification of patients with ovarian cancer through deep representation learning.</p><p><strong>Methods: </strong>We analyzed multiomics data from The Cancer Genome Atlas and developed a 5-stage deep learning pipeline centered on variational autoencoders (VAEs) for nonlinear dimensionality reduction and latent representation learning. A graph convolutional neural network component is described as a proposed extension for modeling interaction-aware representations but was not empirically evaluated in this study. Latent embeddings derived from the VAE were clustered using k-means, and their prognostic relevance was assessed using Cox proportional hazards modeling and Kaplan-Meier survival analysis.</p><p><strong>Results: </strong>Following correction of a clinical-molecular harmonization issue, the final matched cohort comprised 291 patients. Silhouette analysis identified k=2 as the optimal clustering solution (silhouette=0.272). Kaplan-Meier analysis demonstrated significantly different overall survival between the two clusters (log-rank <i>χ</i>²₁=10.0; <i>P</i>=.002). Cox proportional hazards modeling estimated a hazard ratio of 0.519 (95% CI 0.343-0.785; <i>P</i>=.002), indicating that patients assigned to cluster 1 exhibited an approximately 48% lower hazard of death than those in cluster 0. These results demonstrate that the learned latent representations capture prognostically relevant structure within the integrated multiomics data.</p><p><strong>Conclusions: </strong>The proposed VAE-based framework identified 2 prognostically distinct patient subgroups with significantly different overall survival. These findings demonstrate the potential of deep generative representation learning for multiomics-based survival stratification in ovarian cancer and provide a foundation for future validation in independent cohorts and the evaluation of graph-based extensions.</p>","PeriodicalId":73552,"journal":{"name":"JMIR bioinformatics and biotechnology","volume":"7 ","pages":"e89069"},"PeriodicalIF":0.0,"publicationDate":"2026-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13592661/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149018987","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Readability of AI-Generated Patient Information on Glucagon-Like Peptide-1 Receptor Agonists.","authors":"Tyler Williams, Ines Bilic-Curcic, Jonathan Hurley, Harisankeerth Mummareddy, Maja Cigrovski Berkovic, Silvija Canecki Varzic, Marina Gradiser","doi":"10.2196/90572","DOIUrl":"10.2196/90572","url":null,"abstract":"<p><strong>Unlabelled: </strong>Artificial intelligence (AI)-generated content on glucagon-like peptide-1 receptor agonists (GLP-1RAs) gave informationally detailed responses, but its readability remains suboptimal for many patients. Incorporating literacy-sensitive design principles into AI health communication is essential to ensure equitable access to digital medical information.</p>","PeriodicalId":73552,"journal":{"name":"JMIR bioinformatics and biotechnology","volume":"7 ","pages":"e90572"},"PeriodicalIF":0.0,"publicationDate":"2026-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13143154/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147847339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Random Survival Forest Versus Elastic-Net Regularized Cox Regression for Survival Prediction in Acute Myeloid Leukemia at Distinct Treatment Time Points: Model Performance Comparison Study.","authors":"Oisín Brady, Sean Johnson, Peter Giles, Caroline Alvares, Joanna Zabkiewicz, Carolina Fuentes","doi":"10.2196/75678","DOIUrl":"10.2196/75678","url":null,"abstract":"<p><strong>Background: </strong>Risk group stratification based on the prediction of survival of patients with acute myeloid leukemia (AML) is complex. Despite common risk group categorization guidelines, the overall prognosis remains poor. Machine learning techniques have been shown to provide more accurate risk group stratification than conventional approaches using trial data. However, many time-to-event (TTE) models do not use training sets constrained to specific time windows, instead using aggregations of trial data.</p><p><strong>Objective: </strong>This study aimed to evaluate the performance of (1) random survival forest (RSF) and (2) Cox proportional hazard regression with elastic net regularization (CoxNet) for survival prediction of patients with AML within a censoring window trained with available data recorded at discrete time points during the United Kingdom National Cancer Research Institute Acute Myeloid Leukaemia 17 randomized controlled trial (AML17).</p><p><strong>Methods: </strong>For each stage in the AML17 trial, separate models were trained for each exhaustive k-choice combination of available AML17 data subsets. Data combinations for each model were further constrained according to the respective trial stage to avoid data leakage. Preliminary Pearson correlation methods were used to remove directly correlating features with the TTE prediction (time-to-death/5-y censoring point). Repeated k-fold stratified cross-validation was used on each dataset ablation to find candidate models. Permutation importance and elastic net regularization were used to monitor stability across validation folds and reduce the feature set of the highest performing stage RSF and Cox proportional hazard regression models, respectively. Finally, selected ablated models were re-evaluated using the nested, k-fold, stratified sampling cross-validation method with bootstrapping.</p><p><strong>Results: </strong>Concordance index ranked the best models for data constricted up to the end of induction (RSF=0.68, CoxNet=0.67), stages 1 (RSF=0.69, CoxNet=0.68), 2 (RSF=0.68, CoxNet=0.66), and 3 (RSF=0.69, CoxNet=0.63) of the trial.</p><p><strong>Conclusions: </strong>This study details the high prediction accuracy for time-to-survival-event predictions when training sets of CoxNet and RSF models, which are sequentially constricted to data measured up to the end of respective AML17 trial stages. The performance of these sequential TTE models is intended to justify their use as part of a wider digital twin system simulating multiple TTE outcomes for patients with AML.</p>","PeriodicalId":73552,"journal":{"name":"JMIR bioinformatics and biotechnology","volume":"7 ","pages":"e75678"},"PeriodicalIF":0.0,"publicationDate":"2026-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13128161/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147791159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Temporal Reproducibility of a Genetic Algorithm-Derived Health Risk Score: Standardized Out-of-Fold Validation Framework (2021-2023).","authors":"Yoichiro Aoki, Hiroki Takeda, Kinichi Yokota, Ryoko Yoshida","doi":"10.2196/85659","DOIUrl":"10.2196/85659","url":null,"abstract":"<p><strong>Background: </strong>Genetic algorithm (GA)-based scoring has been proposed as a data-driven approach for health risk stratification . However, performance estimates may be inflated when preprocessing, optimization, and evaluation are not strictly separated within a prespecified validation framework. Demonstrating temporal reproducibility under a standardized out-of-fold (OOF) evaluation framework with transparent uncertainty quantification is therefore essential for ensuring translational reliability in preventive health screening.</p><p><strong>Objective: </strong>This study aimed to evaluate the temporal reproducibility of a GA-derived composite health risk score across three consecutive annual cohorts (2021-2023) under a standardized OOF validation pipeline and to assess robustness to policy-driven structural HbA1c missingness through a prespecified ON/OFF sensitivity analysis.</p><p><strong>Methods: </strong>Annual health examination datasets from 2021 (n=3744), 2022 (n=5153), and 2023 (n=5352) were analyzed using an identical preprocessing and modeling pipeline. Thirteen clinical indicators and eight lifestyle questionnaire variables were included as predictors. The outcome was based on an A-D grading framework and binarized using an OR rule across domains (grade ≥B in any domain). Continuous variables were median-imputed and standardized within each training fold to prevent information leakage. GA optimization was performed using fixed random seeds, and fitness estimation employed stratified K-fold cross-validation. Predicted probabilities were obtained by fitting logistic regression models to GA-derived composite scores within the OOF framework. Discrimination and overall predictive performance were quantified using the area under the receiver operating characteristic curve (AUC) and the Brier score calculated from OOF predicted probabilities. Uncertainty was estimated using 2,000-replicate percentile bootstrap resampling. A prespecified sensitivity analysis excluded HbA1c while maintaining an identical evaluation framework.</p><p><strong>Results: </strong>OOF AUC values were stable across cohorts (2021: 0.810; 2022: 0.814; 2023: 0.812), with overlapping 95% percentile bootstrap confidence intervals. Brier scores ranged from 0.172 to 0.176. Exclusion of HbA1c resulted in small changes in discrimination (median ΔAUC was ≤0.007), consistent with the prespecified ON/OFF sensitivity analysis.</p><p><strong>Conclusions: </strong>Under a harmonized OOF validation framework, the GA-derived composite risk score showed stable temporal discrimination and consistent overall predictive performance across three consecutive annual cohorts. These findings underscore the methodological importance of prespecified, standardized evaluation procedures and transparent uncertainty quantification when assessing reproducibility of risk stratification models in routine health screening data.</p>","PeriodicalId":73552,"journal":{"name":"JMIR bioinformatics and biotechnology","volume":"7 ","pages":"e85659"},"PeriodicalIF":0.0,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13099121/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147791246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The AudioGene Translational Dashboard for Diagnosing Autosomal Dominant Nonsyndromic Hearing Loss: Phenotypic Data Visualization and Analysis Study.","authors":"Benjamin DeSollar, Nathan Schaefer, Daniel Walls, Amanda M Odell, Kevin T A Booth, Hela Azaiez, Michael Schnieders, Richard J H Smith, Terry Braun, Thomas Casavant","doi":"10.2196/85212","DOIUrl":"10.2196/85212","url":null,"abstract":"<p><strong>Background: </strong>Autosomal dominant nonsyndromic hearing loss (ADNSHL) is highly heterogeneous, with more than 64 genes implicated in its etiology. This complexity limits the diagnostic power of clinical examinations and audiometry alone, while existing computational approaches have achieved only moderate accuracy and often lack interpretability. As precision medicine increasingly emphasizes genotype-phenotype correlations, there is a recognized need for diagnostic tools that provide clinicians with transparent, interpretable outputs.</p><p><strong>Objective: </strong>This study aimed to develop and evaluate the AudioGene Translational Dashboard, an interpretable clinical informatics tool that integrates machine learning models and interactive visualizations to enhance genotype-phenotype correlations and support diagnostic decision-making in ADNSHL.</p><p><strong>Methods: </strong>We developed the AudioGene Translational Dashboard, integrating 2 machine learning models (AudioGene version 4 and AudioGene version 9.1) with 6 interactive visualization tools. AudioGene version 4 uses a multi-instance support vector machine classifier for patients with multiple audiograms, while AudioGene version 9.1 combines adaptive boosting, k-nearest neighbors, random forest models, and logistic regression for patients with a single audiogram. Visualizations include audiometric profile plots, audioprofile surfaces, clustering analyses, and data distribution charts designed to facilitate clinical interpretation.</p><p><strong>Results: </strong>The AudioGene Translational Dashboard was developed to address the \"70/30\" phenomenon, indicating a 74% likelihood that the causative gene is among the top 3 predicted genes, thereby providing clinicians with a clear confidence indicator (\"green flag\") or a caution alert (\"red flag\") during diagnosis. While this level of performance is well suited for hypothesis generation, the remaining uncertainty underscores the need for interpretive context in clinical decision-making. Visualization tools enhanced clinicians' ability to interpret and correlate phenotypic data with predicted genetic outcomes, improving diagnostic confidence and interpretability.</p><p><strong>Conclusions: </strong>The AudioGene Translational Dashboard advances clinical informatics in genetic diagnosis of ADNSHL by integrating explainable artificial intelligence with interactive visualizations, enhancing clinical interpretability and diagnostic accuracy. This approach facilitates informed clinical decision-making, highlights the translational potential of genotype-phenotype computational models, and supports precision medicine in hearing loss diagnostics. Future enhancements will target improving class balance and incorporating additional user-customizable features to further optimize clinical applicability.</p>","PeriodicalId":73552,"journal":{"name":"JMIR bioinformatics and biotechnology","volume":"7 ","pages":"e85212"},"PeriodicalIF":0.0,"publicationDate":"2026-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13078402/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147694015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Strategic Partnership to Advance AI Applications in Genomics and Bioinformatics for Health Innovation.","authors":"Aik Choon Tan, Ece Dilber Gamsiz Uzun","doi":"10.2196/93272","DOIUrl":"10.2196/93272","url":null,"abstract":"<p><strong>Unlabelled: </strong>JMIR Bioinformatics and Biotechnology announced a strategic partnership with the MidSouth Computational Biology and Bioinformatics Society (MCBIOS) in late 2025; this partnership establishes JMIR Bioinformatics and Biotechnology as the official journal of MCBIOS. This collaboration reflects a shared commitment to advancing computational biology, bioinformatics, and biotechnology through open science, interdisciplinary collaboration, and real-world data. By connecting MCBIOS' community-building and professional development initiatives with JMIR Publications' open-access publishing platform, this partnership aims to support emerging researchers, accelerate the dissemination of innovative computational methods and artificial intelligence applications, and strengthen data-driven research across medicine and biology.</p>","PeriodicalId":73552,"journal":{"name":"JMIR bioinformatics and biotechnology","volume":"7 ","pages":"e93272"},"PeriodicalIF":0.0,"publicationDate":"2026-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13030907/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147535043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prevalence and Associated Risk Factors of Bovine Fasciolosis in Bahir Dar, Ethiopia: Cross-Sectional Study.","authors":"Tesfaye Mesfin, Theobesta Solomon, Abraham Belete Temesgen","doi":"10.2196/81219","DOIUrl":"10.2196/81219","url":null,"abstract":"<p><strong>Background: </strong>Cattle are among the most important livestock resources in Ethiopia, contributing significantly to the agricultural economy and rural livelihoods. They provide meat, milk, hides, draft power for crop production, and serve as a major source of income for farmers. Despite their vital role, cattle productivity is often constrained by various diseases, particularly parasitic diseases. One of the most significant of these is bovine fasciolosis, a condition caused by ingestion of metacercariae of liver flukes belonging to the genus Fasciola.</p><p><strong>Objective: </strong>This study aimed to assess the prevalence and associated risk factors of bovine fasciolosis in Bahir Dar, Ethiopia.</p><p><strong>Methods: </strong>A cross-sectional study was conducted from November 2021 to April 2022. A total of 384 cattle were randomly selected from different locations within the study area. Animals of all age groups and both sexes were included. Fecal samples were collected directly from the rectum of each animal using clean, labeled containers. The samples were examined using standard coprological techniques, specifically the sedimentation method, to detect liver fluke eggs. All findings were recorded, and the data were analyzed using descriptive statistical methods.</p><p><strong>Results: </strong>The overall prevalence of fasciolosis was 49.21% (n=189). Based on origin, Sebatamit had the most incidence at 61.84% (n=47), followed by Kebele 11 at 59.37% (n=57), Tikurit at 50% (n=59), and Latammba at 27.65% (n=26). Statistical analysis revealed significant disparities in occurrence among areas. Cattle in poor condition had the largest prevalence (n=80, 64%), followed by medium condition (n=85, 50%) and fat cattle (n=24, 26.96%). This variation was statistically significant. Age-group analysis revealed comparable prevalence rates, with young cattle at 50.38% (n=65), adults at 47.33% (n=71), and elderly cattle at 50.47% (n=53), with no significant differences found. There were no significant sex-related variations in prevalence, with males exhibiting a prevalence of 49.73% (n=93) and females 48.73% (n=96). Local cattle had a slightly higher prevalence (n=111, 51.62%) than crossbreeds (n=78, 46.15%), although the difference was not statistically significant (P=.29).</p><p><strong>Conclusions: </strong>These findings underscore the need for targeted, location-specific control strategies and highlight the importance of improved nutritional and health management practices to reduce the burden of fasciolosis in cattle populations.</p>","PeriodicalId":73552,"journal":{"name":"JMIR bioinformatics and biotechnology","volume":"7 ","pages":"e81219"},"PeriodicalIF":0.0,"publicationDate":"2026-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12995036/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147476656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unpacking Genomic Biomarkers for Programmed Cell Death Receptor-1 Immunotherapy Success in Non-Small Cell Lung Cancer Using Deep Neural Networks: Quantitative Study.","authors":"Rayan Mubarak, Fahim Islam Anik, Jean T Rodriguez, Nazmus Sakib, Mohammad A Rahman","doi":"10.2196/70553","DOIUrl":"10.2196/70553","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Non-small cell lung cancer (NSCLC) is one of the leading causes of cancer-related mortality. Programmed cell death receptor-1 (PD-1) immunotherapy has shown results in the treatment of NSCLC; however, not all patients respond effectively to it. Identifying predictive biomarkers for PD-1 therapy response is critical to improving patient outcomes and treatment strategies. Traditional methods of biomarker discovery often fall short in terms of accuracy and comprehensiveness. Recent advancements in deep learning provide a powerful approach to analyze complex genomic data to resolve this issue.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aims to leverage deep neural networks (DNNs) to identify genomic biomarkers predictive of patient responses to PD-1 immunotherapy in NSCLC. DeepImmunoGene is a model designed using a reduced feature set to identify the most critical biomarkers. We use feature selection to reduce the space and apply deep learning to identify the highly predictive gene subset.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Differentially expressed genes were identified in RNA-seq data from 355 patients with NSCLC using the LIMMA package in R, followed by preprocessing with log2 transformation, removing outliers, and detecting easily identified genes. Machine learning models, including support vector machines, extreme gradient boosting (XGBoost), and DNNs, were applied to gene expression data to predict patient responses to immunotherapy. Key predictive genes were identified through model interpretation techniques, and differences in model performance were assessed for statistical significance. Primarily, the metric used identifies which genes serve as key biomarkers in regard to immunotherapy detection.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Initially, we identified 1093 differentially expressed genes from RNA-seq data of 355 patients. We then trained models using SVM, XGBoost, and DNN to predict immunotherapy response. The DNN model outperformed both SVM and XGBoost with an accuracy of 82%, an area under the curve of 90%, and recall of 85%. To identify key biomarkers, we performed a permutation importance analysis, narrowing down the gene set to 98 genes. DeepImmunoGene, trained on these 98 genes, showed superior results, with an accuracy of 87% and an area under the curve of 95%. The top 36 upregulated genes in responders and 62 upregulated genes in nonresponders were identified, which could serve as potential biomarkers for predicting response to PD-1 inhibitors. These findings suggest that DeepImmunoGene can reliably forecast immunotherapy outcomes and aid in biomarker discovery, supporting the development of more personalized treatment strategies in NSCLC.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The DeepImmunoGene predictive model identified 36 upregulated genes that may represent candidate genomic biomarkers associated with response to PD-1 immunotherapy in patients with NSCLC. Notably, the 10 most significant genes offer v","PeriodicalId":73552,"journal":{"name":"JMIR bioinformatics and biotechnology","volume":"7 ","pages":"e70553"},"PeriodicalIF":0.0,"publicationDate":"2026-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12799089/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145967632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}