Biodata Mining最新文献

{"title":"CME-KGDTI: integrating clustered mutations into knowledge graph embedding for drug-target interaction prediction.","authors":"Jiaming Jin, Xinmiao Zhao, Jiarui Liu, Chengjun Gong, Wanjie Zheng, Guijie Jiang, Changxian Li, Li Guo, Tingming Liang, Xiangcheng Li","doi":"10.1186/s13040-026-00576-8","DOIUrl":"10.1186/s13040-026-00576-8","url":null,"abstract":"<p><strong>Background: </strong>Computational prediction of drug-target interaction (DTI) is critical for drug discovery and precision medicine. Herein, we constructed a biologically enriched heterogeneous knowledge graph (KG) integrating clustered mutations, synthetic lethal interactions, drug structures, protein sequences, and functional annotations. This multi-dimensional framework was designed to enable the identification of actionable diagnostic signatures and precision therapeutic strategies by leveraging multi-layered biological network factors.</p><p><strong>Results: </strong>Entities within the KG were embedded into low-dimensional vectors using various graph embedding techniques (TransE, RotatE, DistMult, Node2vec and R-GCN). These multimodal embeddings served as input for deep learning models (DNN, NFM, AutoInt), with standardization and PCA-based dimensionality reduction applied. Under a challenging protein cold-start scenario, the CME-KGDTI model demonstrated a better performance. These results highlight the multi-source biological information in enhancing positive sample identification and overall model generalization. Additionally, the CME-KGDTI platform ( https://www.tmliang.cn/cmekgdti/#/home ) was developed, integrating resources for clustered mutation identification, cancer-specific SL-based genetic networks, DTI prediction, and multi-omics analysis, enabling users to comprehensively explore mutation detection, target prioritization, and mechanistic insights.</p><p><strong>Conclusions: </strong>By incorporating biological features, the CME-KGDTI model exhibits high accuracy and robust generalization, highlighting its essential complementary role in drug target discovery. The developed CME-KGDTI platform will serve as a flexible, interactive, and implementable technical support platform, contributing to the advancement of precision oncology research.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13501842/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148254086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-omics analysis of genetic drivers linking aortic stenosis and left ventricular diastolic dysfunction in heart failure.","authors":"Zeeshan Ahmed, Prithvi Govindareddy, Jayden Mathew, Naveena Yanamala, Partho P Sengupta","doi":"10.1186/s13040-026-00564-y","DOIUrl":"10.1186/s13040-026-00564-y","url":null,"abstract":"<p><strong>Background: </strong>Aortic stenosis (AS) and left ventricular diastolic dysfunction (LVDD) often coexist in heart failure (HF), but the mechanisms linking them remain unclear. While AS increases afterload and promotes myocardial stiffening, emerging AI-based evidence suggests LVDD can precede the development of AS or progress simultaneously, indicating shared upstream mechanobiological and inflammatory drivers. This study explores the genetic contributors connecting AS and LVDD to identify early molecular markers and convergent pathways in HF.</p><p><strong>Method: </strong>We analyzed Whole Genome Sequence (WGS) and RNA-seq data of the HF patients, generated using their Peripheral Blood Mononuclear Cells (PBMCs) samples. Overall bioinformatics analysis was divided into two modules, 1) gene variant and annotation analysis, and 2) gene expression and enrichment analysis. We utilized our peer review published and open source WGS and RNA-seq pipelines to process Next-Generation Sequence (NGS) data. Furthermore, we performed bioinformatics and statistical analysis to identify genetic variations, expressions, regulation, enrichments, and disease annotations.</p><p><strong>Results: </strong>We identified genetic markers uniquely associated with AS, LVDD, and shared between them. Furthermore, we report genes with significant expression, and functional variations, and discuss their relationship with other cardiovascular diseases (e.g. Vascular and Cardiac Stiffness, Aortic Dissection, Left Atrial Enlargement, Left Ventricular Hypertrophy, Outflow Tract Obstructive Defects, Non-Compaction Coronary Artery Disease, Arrhythmia, Congestive Heart Failure, and Hypertrophic, Dilated, and Ischemic Cardiomyopathy) and non-cardiovascular diseases (non-CVDs) (e.g. Type 1 Diabetes, Diabetic Nephropathy, Skeletal Anomalies, Rheumatoid Arthritis, Atypical Femoral Fractures, Chronic Kidney Disease, Dehydrated Hereditary Stomatocytosis, Schizophrenia, Varicose Veins, High-Altitude Pulmonary Edema, Periodontitis, and Respiratory Disorder) including multiple cancer types (e.g. Breast, Lung, Colorectal, Pancreatic, Hypopharyngeal, Acute Lymphoblastic, and Oral Squamous Cell Carcinomas) and rare genetic disorders (e.g. Hypophosphatasia, Multiple Sclerosis, Campomelic Dysplasia, Lymphatic Malformation). We validated our results through state of science literature, gene-disease annotation databases, and electronic health records.</p><p><strong>Conclusions: </strong>AS and LVDD share both clinical and genomic associations, with overlapping genetic drivers that are enriched in pathways related to inflammation, extracellular matrix remodeling, and vascular stress responses. This work supports the potential of blood-based multi-omics profiling to uncover early, systemic molecular signals of cardiac dysfunction and lays the groundwork for future tissue-specific studies to guide precision diagnosis, risk stratification, and targeted therapeutics in HF.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13430796/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148228837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TENTACLES: a consensus machine learning tool for robust biomarker discovery in heterogeneous data.","authors":"Giorgio Montesi, Gabriel Dos Santos Mouta, Maria Novedrati, André F Cunha, Alessandro Fuschi, Simone Lucchesi, Chiara Sonnati, Annalisa Ciabattini, Francesco Santoro, Donata Medaglini, Helder I Nakaya","doi":"10.1186/s13040-026-00568-8","DOIUrl":"10.1186/s13040-026-00568-8","url":null,"abstract":"<p><strong>Background: </strong>Transcriptomic biomarker discovery often fails to produce reproducible gene signatures across independent cohorts due to model-specific biases and dataset heterogeneity. While single-algorithm approaches may perform well on training data, they frequently fail to generalize effectively. Ensemble methods have proven effective in general machine learning applications, yet their systematic integration for consensus-based feature prioritization remains underexplored in transcriptomics.</p><p><strong>Results: </strong>We developed TENTACLES (Transcriptomic Exploration Tool through Aggregation of Classifiers), an open-source modular framework for robust biomarker discovery through multi-algorithm consensus. The tool is an open-source R package that integrates up to 15 supervised learning algorithms and 6 unsupervised clustering methods. The tool utilizes a modular architecture to automate data preprocessing, multi-algorithm feature prioritization, and cross-cohort validation. By aggregating variable importance across multiple models, TENTACLES identifies gene signatures resilient to algorithm-specific biases. We validated the framework using Crohn's disease as a high-heterogeneity case study across 689 samples from four independent publicly available RNA-seq cohorts. TENTACLES identified a 28-gene consensus panel that achieved superior cross-cohort generalizability compared to single-algorithm-derived signatures and conventional differential expression methods while using, compared to the latter, 95% fewer features. This signature was further refined to a minimal 5-gene core that maintained robust discriminatory power in completely unsupervised validation. These results confirm the tool's ability to extract stable biological signals from complex, noisy datasets.</p><p><strong>Conclusions: </strong>TENTACLES provides a scalable, disease-agnostic solution for identifying minimal reproducible gene signatures from heterogeneous transcriptomic data. By bridging the gap between complex ensemble modeling and practical biomarker discovery, the software could serve as a versatile resource for researchers aiming to derive reproducible biomarkers across diverse disease contexts.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13480257/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148220498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhance autism spectrum disorder detection using stacking ensemble learning model with explainable AI.","authors":"Tao Song, Usama Jabbar, Valentin Marian Antohi, Costinela Fortea, Monica-Laura Zlati","doi":"10.1186/s13040-026-00570-0","DOIUrl":"10.1186/s13040-026-00570-0","url":null,"abstract":"<p><p>Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that is manifested by sensory abnormalities such as hypersensitivity to sound and touch. Autistic children often have problems with communication, social interaction, and behavioral patterns, which are also affected by media or cartoon characters, sometimes leading to unpredictable or dangerous behavior. Timely intervention and detection are important for enhancing development. In this study, we propose a data-driven machine learning (ML) framework to detect early autism in children. The proposed approach starts with overall data processing, which involves the handling of missing values, categorical data processing, and feature selection based on Information Gain and Pearson Correlation to identify the most important attributes. The Synthetic Minority Oversampling Technique (SMOTE) is used to overcome the imbalance between classes. The proposed model uses a stacked ensemble approach in which KNN, RF, SVM, NB, and DT are used as base learners, while Random Forest works as the meta-classifier. Hyper parameter optimization is performed to further optimize the performance of the model. The models are evaluated using accuracy, precision, recall, and F1-score. The experimental outcomes revealed that the proposed ensemble model is more effective than individual classifiers, achieving 99% accuracy on the Toddler Saudi dataset, 98% accuracy on Q-CHAT, and 99% accuracy on the Nao and fused datasets. Moreover, the Shapley explanation method is applied to determine the importance of features and the impact of these features on the model predictions. The results indicate that the proposed framework may assist healthcare workers in autism screening and decision-making, serving as a promising and efficient alternative means of early autism detection.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13474861/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148206794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TASC: a time-aware sequence clustering framework with uncertainty quantification for electronic health record trajectories.","authors":"April Yujie Yan, Thomas K M Cudjoe, Casey Overby Taylor","doi":"10.1186/s13040-026-00569-7","DOIUrl":"10.1186/s13040-026-00569-7","url":null,"abstract":"&lt;p&gt;&lt;p&gt;Longitudinal electronic health record (EHR) trajectories are highly heterogeneous, sparse, and irregular, making unsupervised temporal pattern discovery and uncertainty quantification challenging. We developed a Time-Aware Sequence Clustering (TASC) framework that integrates temporal spacing, clinical semantic similarity, and probabilistic subtype characterization to identify longitudinal trajectory patterns from EHR data. We demonstrate the framework using pre-surgical musculoskeletal care trajectories preceding total knee replacement (TKR). As a proof-of-concept application, we applied TASC to EHR and survey data from 2,052 patients undergoing primary TKR in the All of Us Research Program. Using electronic health records and survey data, we constructed their temporally ordered sequences of musculoskeletal-related diagnoses and comorbidities. We applied a weighted edit-distance algorithm that incorporates both clinical semantic similarity and inter-event time gaps, followed by K-Medoids clustering and subsampling-based stability analysis. Clusters were compared across sociodemographic variables, quality-of-life measures, prevalence of musculoskeletal-related diagnostic events, time to surgery, and pre- and post-surgical opioid use. We further quantified cluster membership uncertainty by computing probability-based subtype assignments from distances between partial or full trajectories and cluster medoids using a SoftMax transformation. TASC identified stable and interpretable trajectory structures from heterogeneous longitudinal EHR data in patients undergoing TKR. A five-cluster solution achieved the best silhouette score of 0.22 and demonstrated good stability under subsampling with mean Adjusted Rand Index of 0.71. The resulting trajectory clusters demonstrated distinct sociodemographic profiles, diagnostic/comorbidity patterns, and time-to-surgery distributions, supporting the framework's ability to capture heterogeneous longitudinal care-utilization patterns. Patients with fast progression (median = 252 days) to surgery were younger (mean = 53.6 years, SD =16.5 years) and had minimal comorbidity, whereas joint pain-obesity (median = 766 days) and joint pain-fracture (median = 1154 days) subtypes showed intermediate progression timelines. The soft-tissue-dominant subtype was characterized by prolonged pre-surgical trajectories (median = 2900 days) and elevated chronic opioid use, while the complex, chronic subtype comprised older patients (mean = 62.7 years, SD = 10.0 years) with multimorbidity, long delays to surgery (median = 5457 days), and the lowest post-surgical quality-of-life scores. Opioid use declined after surgery across all clusters, with the largest reductions observed in clusters with less complexity and shorter pre-surgical trajectories (e.g., fast progression to surgery and joint pain-obesity subtypes, 38% and 31% reduction, respectively). Probability-based analysis showed that fast progression subtype was identifiable ","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13455125/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148165208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Discovery of postoperative clinical states linked to cardiac surgery-associated acute kidney injury.","authors":"Motahare Shabestari, Vinod Kumar Chauhan, Mohammadtaghi Sarebanhassanabadi, Seyed Jalil Mirhosseini","doi":"10.1186/s13040-026-00572-y","DOIUrl":"10.1186/s13040-026-00572-y","url":null,"abstract":"<p><strong>Background: </strong>Cardiac surgery-associated acute kidney injury (AKI) remains a common postoperative complication and is associated with adverse short- and long-term outcomes. Conventional risk scores may have limited performance in complex and dynamically evolving postoperative courses. This study aimed to identify data-driven postoperative clinical states from time-series electronic medical record (EMR) data and characterize how state occupancy evolves before AKI onset.</p><p><strong>Methods: </strong>We conducted a retrospective cohort study of adults undergoing major open-heart surgery at a tertiary cardiovascular center. AKI was defined using the modified Kidney Disease Improving Global Outcomes criteria. Each postoperative day was represented as a patient-day vector comprising laboratory and static clinical features. An internal benchmark guided preprocessing decisions, including feature normalization and selection. Principal component analysis was used for dimensionality reduction, and multiple clustering algorithms were evaluated using validity, resampling-based stability, and reproducibility metrics.</p><p><strong>Results: </strong>Among 3,526 patients, 567 developed AKI. Five clinically interpretable postoperative states were identified. C5 represented an evolving or near-established AKI state, characterized by older age, hyperglycemia, elevated urea and creatinine, hyperkalemia, and hypocalcemia. C4 represented a near-term alarm state, marked by relatively higher hemoglobin, hematocrit, RBC count, calcium, and sodium. C3 reflected a microcytic-hypochromic erythrocyte phenotype with lower MCV, MCH, and MCHC. C1 was characterized by relatively prolonged PT and elevated INR, whereas C2 reflected an overall stable postoperative profile. In patients who developed AKI, state occupancy shifted toward C4 in the immediate pre-onset period and increased further in C5 around the day of AKI diagnosis. By contrast, patients without AKI showed increasing occupancy of the stable C2 state and the relatively protective C1 state as the endpoint approached.</p><p><strong>Conclusions: </strong>Phenotyping of postoperative EMR data identified five interpretable states with distinct laboratory profiles and temporal relationships to cardiac surgery-associated AKI. The AKI trajectory was characterized by transition from an alarm state to an evolving AKI state, whereas the Non-AKI trajectory converged toward stable or protective postoperative states. These findings suggest that dynamic phenotyping may provide a framework for postoperative AKI risk stratification and trajectory monitoring.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13455266/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148151771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Parallel AI-driven framework for post-quantum secure medical image communication using swin-transformer restoration.","authors":"Emad Alsuwat","doi":"10.1186/s13040-026-00567-9","DOIUrl":"https://doi.org/10.1186/s13040-026-00567-9","url":null,"abstract":"<p><p>Reliable and secure transmission of medical images is essential for telemedicine, remote diagnosis, and distributed healthcare systems. However, medical image communication over heterogeneous networks often suffers from packet loss, channel noise, and privacy risks, which may compromise diagnostic accuracy and patient confidentiality. Traditional solutions relying on Reed-Solomon error correction and conventional encryption provide limited resilience and are increasingly inadequate for modern high-resolution medical imaging environments. This study proposes a next-generation AI-assisted communication framework for privacy-preserving medical image transmission that integrates recent advances in hybrid Transformer architectures, neural communication coding, and post-quantum cryptography. First, image corruption detection and restoration are performed using a Restormer/Swin-Transformer hybrid reconstruction network, which demonstrates superior performance in recovering corrupted regions compared with conventional GAN-based repair models. Second, to enhance transmission robustness, the framework incorporates Deep Joint Source-Channel Coding (DeepJSCC) and Neural Error Correction Codes (NECC) that jointly optimize image representation and channel robustness through deep neural networks. Third, communication security is strengthened using lattice-based post-quantum cryptographic primitives, including CRYSTALS-Kyber for key encapsulation and CRYSTALS-Dilithium for authentication, ensuring resilience against quantum computing attacks. To support real-time medical applications, the proposed framework employs a parallel GPU-accelerated processing pipeline with CUDA-based model inference and distributed training strategies. Additionally, federated learning with secure aggregation and differential privacy enables collaborative model training across healthcare institutions while preserving sensitive patient data. Experimental evaluation on benchmark medical imaging datasets demonstrates that the proposed framework significantly improves image reconstruction fidelity, transmission robustness, and cryptographic security compared with traditional ECC-based communication systems and recent AI-assisted transmission methods.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":6.1,"publicationDate":"2026-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148007286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning multi-omics integration identifies new molecular subtypes of lung cancer.","authors":"Bianca Gonda, Derek Wang, Sayed Mehedi Azim, Gabriele Romano, Iman Dehzangi","doi":"10.1186/s13040-026-00563-z","DOIUrl":"10.1186/s13040-026-00563-z","url":null,"abstract":"<p><p>Cancer is a heterogeneous disease, with numerous subtypes differing in molecular profiles, risk factors, clinical outcomes, and tumor locations. Lung cancer, the third most diagnosed cancer in the United States, is driven by a complex combination of molecular alterations, which influence tumor behavior and patient outcomes. Large-scale consortia such as The Cancer Genome Atlas (TCGA) have generated comprehensive data sets encompassing genomic, transcriptomic, proteomic, and clinical data that present a unique opportunity to uncover novel subtypes through multi-omics integration. While clustering methods have been used to identify subtypes in lung cancer, many integrations and avenues remain underexplored. Previous studies mostly focused on a single data type for this task, potentially limiting biological insight. To address this issue, we propose a novel analytical pipeline that combines gene expression and somatic mutation data in lung cancer to identify distinct molecular subtypes. We also use an autoencoder deep neural network, as well as model-based clustering for feature extraction and clustering purposes. Integrating gene expression data, representing dynamic tumor processes with somatic mutation data, reflecting invariant genomic characteristics, enables a more comprehensive understanding of the molecular profile. We identify molecularly defined subtypes, enhancing our understanding of lung cancer's molecular heterogeneity. All source code, figures, latent features, cluster labels, and instructions for data download from the GDC are available at https://github.com/MLBC-lab/LungClust . We believe this serves as a reliable tool that offers valuable biological and clinical insights to advance precision oncology approaches in lung cancer, specifically biomarker discovery, which will aid in patient stratification and treatment response prediction.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13371118/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147989618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel Vector-Symbolic Architecture for graph encoding and its application to viral pangenome-based species classification.","authors":"Fabio Cumbo, Kabir Dhillon, Jayadev Joshi, Davide Chicco, Sercan Aygun, Daniel Blankenberg","doi":"10.1186/s13040-026-00561-1","DOIUrl":"10.1186/s13040-026-00561-1","url":null,"abstract":"<p><p>Viral species classification is crucial for understanding viral evolution, epidemiology, and developing effective diagnostics and treatments. Traditional methods often rely on sequence similarity, which can be challenging for rapidly evolving viruses. Pangenomes, offering a comprehensive representation of species' genomic diversity, provide a richer perspective, but their analysis often requires advanced computational methods. We investigate the use of Hyperdimensional Computing (HDC), also known as Vector-Symbolic Architecture (VSA), an emerging computing paradigm that relies on vectors in high-dimensional spaces to encode a multi-species viral pangenome.We develop a new method for encoding graph-structured viral pangenomes using high-dimensional vectors. Pangenomes are represented as weighted de Bruijn graphs constructed using sequences of consecutive k-mers from the genomes, while information about the genome species (their taxonomic label) is encoded as specific high-dimensional vectors (species hypervectors) that act as weights on the edges of the graph. The weighted de Bruijn graph representation is encoded into a single high-dimensional vector. We tested three classification strategies: a flat model at the species level, a flat model at the genus level, and a two-step hierarchical model.We applied our method to a pangenome comprising 542 viral species from NCBI GenBank. Our results reveal a complex relationship between model architecture and classification accuracy. The flat species-level model achieved the highest accuracy, correctly classifying 87.08% of test genomes. Counter-intuitively, simplifying the problem to the genus level or using a hard-routing hierarchical approach degraded performance, with accuracies dropping to 60.51% and 33.57% respectively. Rather than revealing an inherent flaw in hierarchical modeling, these outcomes highlight critical architectural limitations of our current routing strategy, reflecting the interaction between routing errors and downstream error propagation in multi-step models. The model's reconstruction rate proved to be a measure of model-internal coherence, rather than a direct predictor of correctness.This novel approach offers a promising new direction for viral classification, not only for its predictive power but its ability to reveal underlying challenges in genomic taxonomy.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13361823/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147965219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated candidate confounder scoping for adjustment in clinical research: a retrieval-augmented generation approach.","authors":"Jingjing Li, Kesong Wu, Xiao Wang, Ruolin Tao, Yinyao Ma, Hanlin Lv, Xueqian Zhao, Yu Lan, Lei Li, Lei Wang","doi":"10.1186/s13040-026-00562-0","DOIUrl":"10.1186/s13040-026-00562-0","url":null,"abstract":"<p><strong>Background: </strong>Identifying confounding variables is fundamental for robust observational studies, yet the traditional manual process is a time-consuming and subjective barrier for researchers. Recent advances in Retrieval-Augmented Generation (RAG) offer a promising solution, but most existing systems rely on full-text access, cloud-hosted APIs, or manually curated knowledge graphs, raising concerns about privacy, copyright, and computational cost, and making local deployment difficult.</p><p><strong>Objective: </strong>This study developed and evaluated a heuristic tool to scope candidate confounders for adjustment in observational studies. Using a locally deployed, abstract-only RAG architecture, our tool generates a traceable shortlist of candidate confounders from PICO (Population, Intervention, Comparison, Outcome) queries over medical abstracts.</p><p><strong>Methods: </strong>We implemented a three-stage architecture for PICO-based scoping of candidate confounder. The pipeline was deployed on an all-in-one local server and evaluated using 1,000 expert-curated PICO queries spanning 20 clinical specialties. Performance was assessed along four dimensions-internal consistency, output volume, efficiency, and clinical acceptance-by a multi-institutional clinician panel, and was compared with a graph-only SemMedDB baseline.</p><p><strong>Results: </strong>Across repeated runs, the pipeline showed high internal consistency (candidate confounder list consistency 94.6%±8.7%; PMID set consistency 79.4%±23.5%). It suggested a median of 6 candidate confounders (IQR 8) for adjustment and retrieved a median of 33 unique PMIDs (IQR 7) per query. Median processing time was 44.50 s (IQR 31.72). Expert review yielded an overall clinical acceptance rate of 87.12%.</p><p><strong>Conclusions: </strong>In an exploratory capacity, a locally deployed, abstract-only RAG workflow can generate clinically interpretable and traceable candidate confounder suggestions to support early-stage observational study design, particularly in settings with privacy constraints or limited access to full texts and cloud resources.</p><p><strong>Trial registration: </strong>NA.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13295572/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147960472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}