Frontiers in bioinformatics最新文献

{"title":"Integrating transcriptomic analysis to explore biomarkers and therapeutic targets for rheumatoid arthritis: a case-control and systems biology approach.","authors":"S Aswini, S Mohamed Muzammil, N Raja, S Asha Devi","doi":"10.3389/fbinf.2026.1891543","DOIUrl":"https://doi.org/10.3389/fbinf.2026.1891543","url":null,"abstract":"<p><strong>Background: </strong>Rheumatoid Arthritis (RA) is a highly variable and unpredictable autoimmune disease, relying solely on physical symptoms often leads to delayed treatment and irreversible joint destruction. Therefore, identifying biomarkers in RA is necessary to bridge the gap between a patient's unique biological profile and successful clinical management. This study aims to identify distinct molecular signatures in RA patients by integrating systems biology and case-control methodologies.</p><p><strong>Methods: </strong>Transcriptomic datasets from various sources specifically synovial tissues, macrophages, blood, T-cells, natural killer T-cells, natural killer cells, neutrophils, and monocytes were analysed. Differentially Expressed Genes and functional enrichment pathways were identified, followed by Weighted Gene Co-expression Network Analysis to pinpoint hub genes. Machine learning models were used to extract consensus biomarkers. Two of the predicted biomarkers IL2RG) and Interferon-Gamma (IFNG) were further validated using an Enzyme-Linked Immunosorbent Assay (ELISA) in RA patient serum samples.</p><p><strong>Results: </strong>The analysis revealed that synovial tissues and synovial macrophages exhibited pronounced transcriptomic expression changes. Six consensus biomarkers such as IFNG, PTEN, IL2RG, CDKN2D, VEGFA, and CDKN1A were computationally prioritized in synovial macrophages. Among these, IL2RG and IFNG were selected for preliminary experimental validation by ELISA. IL2RG concentrations were significantly higher in RA patients (1.34 ± 0.11 ng/mL) than in healthy controls (0.83 ± 0.07 ng/mL), while IFNG levels showed only a marginal increase (1.91 ± 0.06 pg/mL) compared to controls (1.69 ± 0.06 pg/mL).</p><p><strong>Conclusion: </strong>By integrating multi-tissue transcriptomic profiling with machine learning, this study mapped critical molecular changes in RA and prioritized six consensus biomarkers within synovial macrophages. Experimental validation confirmed that IL2RG and IFNG are significantly elevated in RA patients compared to healthy controls. These findings offer a promising, minimally invasive molecular markers for diagnosis and personalized clinical management in RA.</p>","PeriodicalId":73066,"journal":{"name":"Frontiers in bioinformatics","volume":"6 ","pages":"1891543"},"PeriodicalIF":3.6,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13677927/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149225532","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":"How AI-based techniques for brain tumour diagnosis can address data variability.","authors":"Paola Lecca, Michela Lecca","doi":"10.3389/fbinf.2026.1916468","DOIUrl":"https://doi.org/10.3389/fbinf.2026.1916468","url":null,"abstract":"<p><p>Data variability in medical imaging of tumors refers to the inconsistencies in Magnetic Resonance Imaging and Computational Tomography scans caused by heterogeneous tumor biology, varying scanner hardware, and subjective human interpretation. This variability creates significant challenges for accurate diagnoses, treatment tracking, and AI model development. Although the variability in medical imaging data for diagnostic and prognostic purposes is a challenge for AI methods applied to other types of tumors as well, it is particularly problematic when the analysis involves gliomas and glioblastomas. Most gliomas are infiltrative and glioblastomas are highly infiltrative tumors with poorly defined margins. They exhibit significant regional variations, including cystic necrosis, localized hemorrhages, and complex microvascular proliferation. Addressing this variability requires a combination of algorithmic innovation, standardized datasets, and a leading-edge computational pipeline including traditional and AI-based data modelling methodologies to ensure diagnostic and prognostic models are robust. In this article, we will identify some AI methods that show promise in the analysis of brain tumor images and that must overcome the challenges posed by data availability. We will also offer some insights into how these challenges can be overcome and propose a possible computational pipeline that utilizes them.</p>","PeriodicalId":73066,"journal":{"name":"Frontiers in bioinformatics","volume":"6 ","pages":"1916468"},"PeriodicalIF":3.6,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13677829/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149225466","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":"An integrative meningioma surfaceome atlas and a transferable framework for CAR-T target nomination.","authors":"Vivek Sanker, Dhanya Mahesh, Linda Liverani, Matthew Alexander Abikenari, Zhikai Li, Yi Zhang, Debebe Theodros, Ravi Medikonda, Maria Jose Cavagnaro, Matei Alexandru Banu, Atman Desai, Michael Lim","doi":"10.3389/fbinf.2026.1919802","DOIUrl":"https://doi.org/10.3389/fbinf.2026.1919802","url":null,"abstract":"<p><p>Meningioma is the most common primary intracranial tumor, yet recurrent and high-grade disease has few durable systemic options, and, unlike hematological malignancies, no systematically filtered cell-surface antigen resource exists to guide chimeric antigen receptor (CAR) T development. We address this gap not by nominating a trial-ready target but by building two reusable resources: an integrative meningioma surfaceome atlas and a transferable, gate-based framework that separates transcriptomic discovery from CAR-T target nomination. Analyzing single-cell RNA sequencing from eight meningioma patients (GSE183655; 80,220 quality-controlled cells), patient-aware differential expression followed by a curated surfaceome filter (UniProt plasma-membrane localization; extracellular domain ≥20 aa; exclusion of ribosomal, nuclear, cytoplasmic, and secreted proteins) reduced 83 scored candidates to 13 <i>bona fide</i> plasma-membrane (Tier A) antigens, removing prominent false positives such as the nuclear proteins FOXC1 and MGMT, the cytoplasmic enzyme lactate dehydrogenase A (LDHA), and the secreted protein PTGDS. Because expression ranking establishes discovery but not CAR-T suitability, we then applied explicit nomination gates: a systemic-safety score integrating whole-body GTEx transcriptomics with Human Protein Atlas protein-level evidence; a membrane-topology tractability gate distinguishing antibody-accessible single-pass and GPI-anchored ectodomains from multi-pass transporters and tail-anchored proteins; and a safety × coverage metric. Under stringent thresholds (combined safety ≥0.55, tumor-cell detection fraction ≥50%, safety × coverage ≥0.30), no Tier A antigen qualified. Ubiquitously expressed antigens were correctly demoted, including the tetraspanin CD9 (53.2% tumor-cell coverage but pan-tissue protein expression and high plasma abundance), and the highest-ranked transporter SLC7A2 was demoted by multi-pass topology (largest extracellular loop 38 aa) despite favorable transcriptomic safety. Leukemia inhibitory factor receptor (LIFR), a single-pass type I receptor with a contiguous 789-aa ectodomain, was the only antibody-tractable nominee for experimental follow-up yet remained liability laden (combined safety 0.41; safety × coverage 0.135) and is not a validated target. Cross-dataset expression overlap (93.3%) reflected mRNA reproducibility, not CAR-T validity or clinical validation, and generic-antibody docking was exploratory only. All findings are transcriptomic and require surface-level confirmation. This work contributes a reproducible meningioma surfaceome atlas and a transferable nomination framework and shows that rigorous gating leaves no single antigen with a favorable safety × coverage × tractability profile, motivating bispecific and logic-gated CAR-T strategies.</p>","PeriodicalId":73066,"journal":{"name":"Frontiers in bioinformatics","volume":"6 ","pages":"1919802"},"PeriodicalIF":3.6,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13677907/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149225540","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":"BioGraphBench-PPI enables audit-first evaluation of negative-sampling contracts and structural baselines in protein interaction networks.","authors":"Alejandro Cabrera-Andrade, Jorge Robalino-Díaz, Iván Dueñas-Espín, Ana Karina Zambrano, William Villegas-Ch","doi":"10.3389/fbinf.2026.1966469","DOIUrl":"10.3389/fbinf.2026.1966469","url":null,"abstract":"<p><strong>Introduction: </strong>Biomedical graph-learning results are difficult to compare when source versions, identifier rules, data splits, structural features, and sampled-nonedge contracts are incompletely documented.</p><p><strong>Methods: </strong>We developed BioGraphBench-PPI as an audit-first benchmark for protein-protein interaction (PPI) link prediction using STRING v12.0, BioGRID 5.0.260, and two cross-resource no-overlap ablations. For each PPI task, we generated 10 predefined seeds and three balanced sampled-nonedge contracts: random, degree-matched, and two-hop. We compared local heuristics, logistic regression, random forest, histogram gradient boosting (HGB), an auditable node2vec-compatible random-walk baseline, and a two-layer GCN link-prediction baseline, reporting ranking, calibration, runtime, and confidence intervals.</p><p><strong>Results: </strong>Random sampled nonedges yielded high HGB AUPRC values (0.942-0.964), but degree-matched sampled nonedges reduced AUPRC by 0.049-0.259. The GCN baseline showed signal under random negatives in selected graphs (AUPRC 0.526-0.717) but approached chance under degree-matched and two-hop contracts (AUPRC 0.500-0.515).</p><p><strong>Discussion: </strong>BioGraphBench-PPI shows that PPI benchmark conclusions depend strongly on sampled-nonedge design and graph source. The benchmark therefore contributes an auditable evaluation contract rather than a claim that PPI prediction is solved.</p>","PeriodicalId":73066,"journal":{"name":"Frontiers in bioinformatics","volume":"6 ","pages":"1966469"},"PeriodicalIF":3.6,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13669192/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149217542","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":"Characteristics of predicated pathogenic missense variants in human genes for Mendelian disorders.","authors":"Ruocen Song, Xiaofei Bai, Xiao Fan","doi":"10.3389/fbinf.2026.1947929","DOIUrl":"10.3389/fbinf.2026.1947929","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Missense variants represent a major class of genetic variation and contribute substantially to the cause of Mendelian disorders. However, the genetic and protein properties governing their pathogenicity remain incompletely characterized. Existing variant pathogenicity databases, such as ClinVar, are enriched for variants in well-studied genes and therefore may not provide a representative view of pathogenic missense variants across the genome. Meanwhile, recent advances in computational pathogenicity prediction have significantly improved their predictive accuracy, enabling large-scale genome-wide analysis. In this study, we investigated the genetic and protein properties associated with the predicted pathogenicity of missense variants in Mendelian disease genes.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We collected all possible missense variants in Mendelian genes curated from the Online Mendelian Inheritance in Man (OMIM). Each variant was annotated with pathogenicity predictions from gMVP and a range of properties, including evolutionary conservation, physicochemical substitution characteristics, and functional and structural genetic and protein features. Using multiple linear regression models, we investigated the relationships between the various properties and the predicted pathogenicity of the missense variants. Interaction effects among those properties were also examined. We first validated the quality of gMVP by comparing the effects of each property in the linear regression, fitting to either gMVP pathogenicity predictions or ClinVar pathogenicity labels, on the ClinVar dataset. Then, we extended the analyses to the entire missense dataset to fit gMVP pathogenicity scores. In addition, gene set and robustness analyses were further performed to validate the study findings.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;In 655,859 missense variants from ClinVar, 7.1% were labeled as pathogenic/likely pathogenic compared with 6.4% predicted as pathogenic using a gMVP threshold of 0.9. Regression analyses revealed a high degree of concordance between ClinVar and gMVP pathogenicity annotations, with most predictors showing associations in the same direction and of similar magnitude. The genome-wide dataset includes 23,339,549 missense variants in 4,709 Mendelian disease genes, with 31.8% predicted to be pathogenic using a default gMVP threshold of 0.75. Evolutionary conservation, solvent accessibility, and intrinsic disorder were strongly associated with gMVP pathogenicity scores. Other features, including functional annotations and amino acid biochemical properties, also contributed to the predicted pathogenicity with moderate effect sizes. Feature interactions support an integrative model in which conservation and local protein structure jointly influence the variant impact. GO-stratified and other gene-set analyses indicated that these associations were broadly conserved across gene functional contexts and inheritance patterns.&lt;/","PeriodicalId":73066,"journal":{"name":"Frontiers in bioinformatics","volume":"6 ","pages":"1947929"},"PeriodicalIF":3.6,"publicationDate":"2026-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13662176/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186611","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":"Towards a holistic epidemiology of <i>Streptococcus agalactiae</i> using the BakRep repository.","authors":"Linda Fenske, Oliver Schwengers, Alexander Goesmann","doi":"10.3389/fbinf.2026.1924154","DOIUrl":"https://doi.org/10.3389/fbinf.2026.1924154","url":null,"abstract":"<p><strong>Background: </strong><i>Streptococcus agalactiae</i> is a versatile multi-host pathogen that can cause severe neonatal disease in humans and mastitis in dairy animals. Its ability to infect a wide range of hosts is largely driven by its high genomic plasticity and the acquisition of distinct accessory genes. The global population of <i>S. agalactiae</i> is characterized by multiple capsular serotypes and clonal complexes that differ in their propensity to cause invasive disease, including hypervirulent CC17 (often serotype III) associated with neonatal meningitis, whereas CC1/CC19/CC23 are more often colonizing lineages. Although widely studied, most research is limited to particular regions or single outbreak events, offering only fragmented snapshots rather than a comprehensive global picture.</p><p><strong>Methods: </strong>To move beyond region- or outbreak-limited studies, this work has analyzed 37970 <i>S. agalactiae</i> genomes from BakRep, integrating serotypes, MLST, AMR genes, lineage-specific genes, and descriptive metadata to map current trends and identify potential gaps in public data.</p><p><strong>Results: </strong>The dataset largely matched the known population structure with serotype III, Ia, and V most common and stable serotype/clonal complex lineages (e.g., III-2/CC17, Ia/CC23, CC1/V), while also increasing serotype diversity. Lineages differed in their accessory-gene profiles, with III-2/CC17 being enriched for virulence and adhesion genes, while other groups showed either greater genomic plasticity (mobile/phage genes) or niche specialization. AMR was widespread with very high tetracycline resistance (>80%), frequent MLSB resistance determinants, and emerging aminoglycoside resistance in some genomes.</p><p><strong>Conclusions: </strong>Overall, it became evident that the associated metadata contained substantial gaps. Missing or incomplete information limits biological interpretation, pointing out the importance of rigorously curated, structured metadata for maximizing the value of ongoing sequencing efforts.</p>","PeriodicalId":73066,"journal":{"name":"Frontiers in bioinformatics","volume":"6 ","pages":"1924154"},"PeriodicalIF":3.6,"publicationDate":"2026-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13662052/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149198210","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":"STRIVE: interpretable multimodal subtype discovery in Women's cancers using an attention-weighted joint variational autoencoder.","authors":"Zunaira Mehmood, Divya Sharma","doi":"10.3389/fbinf.2026.1901464","DOIUrl":"https://doi.org/10.3389/fbinf.2026.1901464","url":null,"abstract":"<p><strong>Background: </strong>Breast, endometrial, and cervical cancers share a common challenge: molecular heterogeneity that single-modality profiling cannot fully resolve. Gene expression and DNA methylation capture distinct and partially non-overlapping regulatory programs, yet most subtyping frameworks treat them independently or merge them without accounting for modality-specific noise and scale.</p><p><strong>Objective: </strong>To develop an interpretable multimodal framework that integrates transcriptomic and epigenomic signals for principled molecular subtype discovery and molecular patient stratification with exploratory assessment of outcome associations across women's cancers.</p><p><strong>Methods: </strong>We developed STRIVE (Stratification via Integrated Variational Embeddings), an attention-based joint variational autoencoder that learns modality-aware embeddings, fuses them into a shared latent space, and supports <i>post hoc</i> feature attribution. Subtypes were defined by K-means clustering on latent embeddings, cluster-defining signatures were derived using standardized mean differences (q < 0.05), and within-subtype survival prediction was assessed via permutation feature importance across multiple classifiers.</p><p><strong>Results: </strong>In TCGA-BRCA (n = 866), STRIVE identified six molecular subtypes with coherent multimodal signatures, with DNA-methylation features prominently represented in specific cluster signatures. Within-subtype survival-status prediction showed variable performance across classifiers and subtypes. Replication in TCGA-UCEC (n = 454) and TCGA-CESC (n = 296) recapitulated key signature patterns, with DNA-methylation features prominently represented in specific cluster signatures and more consistent predictive performance in UCEC than CESC.</p><p><strong>Conclusion: </strong>STRIVE demonstrates that attention-weighted multimodal integration surfaces molecularly coherent subtypes in which cluster-defining signatures frequently included epigenomic features, a structure that single-modality approaches would obscure. These findings position STRIVE as a framework for multimodal molecular stratification and future evaluation of subtype-specific clinical associations.</p>","PeriodicalId":73066,"journal":{"name":"Frontiers in bioinformatics","volume":"6 ","pages":"1901464"},"PeriodicalIF":3.6,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13658565/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186543","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":"Patient classification using single-cell RNA-sequencing data with deep learning convolutional neural networks.","authors":"Anastasis Oulas, Nestoras Karathanasis, Theodosios Lampadarios, Raphael Antartis, George M Spyrou","doi":"10.3389/fbinf.2026.1919127","DOIUrl":"https://doi.org/10.3389/fbinf.2026.1919127","url":null,"abstract":"<p><strong>Introduction: </strong>Single-cell RNA sequencing (scRNA-seq) enables gene expression profiling at the resolution of individual cells, revealing cellular heterogeneity that is obscured in bulk RNA-seq. While this offers a powerful lens to study disease-specific changes, leveraging scRNA-seq data for patient phenotype classification remains challenging due to limited sample numbers, cell count variability, high dimensionality, and dependence on cell-type annotations. Existing tools attempt to address these issues using probabilistic models or attention mechanisms, but face limitations in scalability, interpretability, or representational power.</p><p><strong>Methods: </strong>In this work, we introduce DeepCelllify, a novel deep learning-based framework that harnesses convolutional neural networks (CNNs) to classify patients using their individual cell expression profiles. Our approach converts tabular gene expression data into image-like representations, enabling CNNs to learn spatial feature relationships between genes. Each cell is treated as an independent input labeled by its originating patient's condition (e.g., disease or control), allowing us to sidestep the limitations posed by small patient cohorts and heterogeneous cell counts. The DeepCelllify pipeline includes a transformation module for data preprocessing and a classification module, culminating in CNN models trained through cross-validation to differentiate between disease states based on single-cell inputs.</p><p><strong>Results: </strong>Our method demonstrates competitive performance compared to state-of-the-art approaches, with added benefits in scalability, interpretability, and practical applicability. DeepCelllify further addresses critical bottlenecks in scRNA-seq-based phenotype prediction, including overfitting from low patient counts, challenges in feature matrix construction, and dimensionality issues. Additionally, our method provides interpretability by assigning weights to individual cells, helping to down-weight misclassified or noisy cells.</p><p><strong>Discussion: </strong>This work introduces deep learning framework for patient phenotype prediction from scRNA-seq data, with potential applications in precision medicine and biomarker discovery.</p>","PeriodicalId":73066,"journal":{"name":"Frontiers in bioinformatics","volume":"6 ","pages":"1919127"},"PeriodicalIF":3.6,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13658557/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186562","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":"TNRSim - a simulator of truncated oxford nanopore direct RNA long reads for isoform analysis.","authors":"Anna Kozlova, Artemiy Sakharov, Svetlana Tarbeeva, Ekaterina Ilgisonis, Elena Ponomarenko","doi":"10.3389/fbinf.2026.1694068","DOIUrl":"https://doi.org/10.3389/fbinf.2026.1694068","url":null,"abstract":"<p><strong>Introduction: </strong>Nanopore sequencing opens up new opportunities in transcriptome research due to the possibility of generating full-length isoform reads. However, currently available simulation software does not fully reproduce read truncation, a key feature of transcriptomic nanopore libraries.</p><p><strong>Methods: </strong>We developed TNRSim (Truncated Nanopore Reads Simulator), a nanopore transcriptome library simulator designed to reproduce realistic read-length distributions, sequencing errors, and quality scores. We further used simulated datasets with known isoform abundances to benchmark widely used isoform quantification tools.</p><p><strong>Results: </strong>TNRSim reproduced characteristic read-truncation patterns observed in empirical direct RNA sequencing datasets and provided improvements in read-length distribution, mismatch, and quality-score simulation compared with existing approaches. In a closed-set benchmark of isoform quantification methods, oarfish achieved the highest quantification accuracy among the tested tools.</p><p><strong>Discussion: </strong>TNRSim provides a framework for realistic simulation of transcriptomic nanopore sequencing data and enables controlled benchmarking of computational methods for isoform-level analysis.</p>","PeriodicalId":73066,"journal":{"name":"Frontiers in bioinformatics","volume":"6 ","pages":"1694068"},"PeriodicalIF":3.6,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13658594/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186560","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 comparative analysis of graph neural networks and classical machine learning for carbapenem-resistance prediction and genomic interpretation in <i>Acinetobacter baumannii</i>.","authors":"Irfan Sharif Shaik, Morteza Sarmadi","doi":"10.3389/fbinf.2026.1885813","DOIUrl":"10.3389/fbinf.2026.1885813","url":null,"abstract":"<p><strong>Introduction: </strong>Carbapenem-resistant <i>Acinetobacter baumannii</i> is a hospital-associated pathogen linked to high mortality and limited treatment options. Although many resistance determinants have been identified, how they organize into coordinated systems remains unclear.</p><p><strong>Methods: </strong>Using a final binary modeling dataset of 2,448 genomes, we benchmarked machine-learning and graph-based models and developed a framework that pairs accurate prediction with systems-level genomic interpretation.</p><p><strong>Results: </strong>Across five random seeds and 10-fold stratified cross-validation, a Random Forest classifier achieved the strongest internal performance using a bag-of-genes representation, with an accuracy of 0.9328 ± 0.0175 and ROC-AUC of 0.9650 ± 0.0138. Random Forest also generalized best in an independent BV-BRC Asia validation cohort of 2,500 genomes, achieving an accuracy of 0.7728 and ROC-AUC of 0.8392. In parallel, a Graph Convolutional Network trained on gene-adjacency graphs enabled interpretation through <i>post hoc</i> explainability, prioritizing genes consistent with a candidate three-layer resistance architecture: (i) canonical rapid-response resistance genes, (ii) a cell-surface \"Sugar Shield\" centered on GDP/UDP-epimerase, and (iii) a metabolic \"Command Center\" involving regulators such as DnaA and quinone oxidoreductase 1. Explanation-stability analysis identified a reproducible consensus subset while supporting cautious interpretation of individual rankings. Complementary computational analyses, including protein-protein interaction enrichment, Gene Ontology enrichment, structural modeling, and molecular docking, supported the biological coherence and structural plausibility of the proposed architecture.</p><p><strong>Discussion: </strong>Together, these findings suggest that carbapenem resistance may reflect a coordinated, multi-layer defense system and nominate GDP/UDP-epimerase and quinone oxidoreductase 1 as candidates for future experimental investigation.</p>","PeriodicalId":73066,"journal":{"name":"Frontiers in bioinformatics","volume":"6 ","pages":"1885813"},"PeriodicalIF":3.6,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13655062/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149169254","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}