SEARCH · Search PubMed

Results for “Multiomics integration”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 271 records · Page 15Linked to original sources

PubMed2025

MNMO: discover driver genes from a multi-omics data based-multi-layer network.

MOTIVATION: Cancer as a public health problem is driven by genomic variations in "cancer driver" genes. The identification of driver genes is critical for the discovery of key biomarkers and the development of personalized therapy. RESULTS: We propose a prediction method MNMO: a multi-layer network model based on multi-omics data. MNMO firstly constructs a dynamically adjusted four-layer network composed of miRNAs and three kinds of genes with different features. Then three kinds of scores, i.e. control capacity, mutation score, and network score, are devised and calculated by harmonic mean to produce the integrated gene score. Experiments were performed on three kinds of real cancer data to compare the identification performance of method MNMO with that of six state-of-the-art ones. The results indicate that method MNMO presents the best identification performance under most circumstances. The genes prioritized by method MNMO not only have a better match to the benchmark ones than those identified by the other methods, but also are all associated with the development and progression of cancers. In addition, some extended versions of method MNMO can further achieve better performance on most evaluation metrics for some specific datasets. They may be more conducive to identifying tissue-specific genes, which has been verified through a number of experiments. AVAILABILITY AND IMPLEMENTATION: The source code and the R package "MNMO" are available at https://github.com/Zheng-D/MNMO. The dataset and code are archived at https://doi.org/10.5281/zenodo.14969986.

Humans↗

PubMed2026

Integrated metabolomic, transcriptomic, and proteomic analyses reveal changes in the non-volatile metabolite profile of LED light-withered oolong tea.

LED light withering is a crucial method for overcoming weather limitations and enhancing the quality of oolong tea. To elucidate the underlying molecular mechanisms, this study simulated solar spectra using multiwavelength LED light and compared the resulting metabolic, transcriptomic, and proteomic profiles during the enzymatic-catalysis process (ECP) in oolong tea processing. Results indicated that LED light withering altered gene expression and protein regulation of secondary metabolism, particularly in the flavonoid biosynthesis pathway. These shifts encompassed key quality-related compounds, including flavonoids (quercetin-3-O-rhamnoside, dihydroquercetin), amino acids (L-asparagine, L-histidine), guanosine 5'-monophosphate (GMP), and carbohydrates. Furthermore, LED light withering accelerated tea leaf water loss, influenced gene expression involved in photosynthetic cellular components (chloroplasts, thylakoids), increased ascorbate peroxidase regulation under stress, and subsequently modulated energy metabolism and signal transduction in tea leaves. This study offers molecular theoretical framework for the controlled light-withering of oolong tea under bad weather and the associated improvements in its quality.

Camellia sinensis↗

PubMed2026

Integrated multi-omics analyses identify an RAS-SLC11A2-associated molecular framework linking iron metabolism with PCOS-related cardiometabolic risk.

INTRODUCTION: PCOS is a common endocrine disorder with elevated cardiometabolic risk, yet the role of the renin-angiotensin system (RAS)-iron metabolism axis in this comorbidity remains unclear. We explored its underlying mechanisms and evaluated the therapeutic potential of gentiopicroside. METHODS: Integrated multi-omics analyses combining transcriptomics, single-cell RNA sequencing, Mendelian randomization, machine learning, molecular docking, and in vitro functional assays were performed to identify shared molecular pathways and therapeutic targets across PCOS, hypertension, NAFLD, and T2DM. RESULTS: SLC11A2 was consistently dysregulated in PCOS transcriptomic datasets, and associated with iron metabolism, inflammatory response and oxidative stress pathways. Genetic analyses validated RAS-related regulation in hypertension susceptibility and revealed shared genetic architecture between PCOS and cardiometabolic traits. Network and single-cell analyses characterized SLC11A2-associated molecular patterns in disease-relevant cell types; machine learning identified disease-classifying molecular signatures. Gentiopicroside alleviated inflammatory and oxidative stress phenotypes, including reduced IL-6 expression and reactive oxygen species accumulation. CONCLUSION: This study defines an RAS-SLC11A2 molecular framework linking iron metabolism dysregulation to PCOS-related cardiometabolic risk, elucidating the mechanisms connecting ovarian dysfunction, inflammation, oxidative stress and hypertension, and supports gentiopicroside as a promising therapeutic candidate.

Humans↗

PubMed2025

Augmented kurtosis-based projection pursuit: a novel, advanced machine learning approach for multi-omics data analysis and integration.

Due to the heterogeneity of multi-omics data, exacting their maximum information potential remains a challenge. Whereas some solutions have been offered, most cannot overcome the large linear dynamic range associated with such data, while others require large biological effect sizes to produce meaningful models. Here, we (i) perform a comprehensive benchmarking of multi-omics data analysis tools, and (ii) introduce kurtosis-based projection pursuit analysis, augmented with classification and regression trees (kPPA-CART) as a robust, easy-to-implement alternative. Using ground truth data, we demonstrate that kPPA-CART exhibits superiority in inferring biological significance from low-intensity (low-count) features and studies with small biological effect sizes. Applying it to experimental breast cancer data from The Cancer Genome Atlas, we identify novel genes that cluster the samples into subtypes that mimic the canonical PAM50 classes with notable improvements. Validating with external metastatic breast cancer data from the AURORA US consortium, kPPA-CART identifies genes that are associated with poor event-free survival and additional clustering associated with increased tumor mutational burden. Finally, we provide an R package and an online implementation of kPPA-CART.

Humans↗

PubMed2026

Pan-genomics and multi-omics for deciphering genetic variation and accelerating genetic improvement in ruminant livestock.

Livestock reference genomes have transformed the discovery of variants associated with production, reproduction, health, and environmental adaptation. Nevertheless, a single linear reference represents only one mosaic haplotype and incompletely captures sequence diversity within a species, particularly structural variants, copy-number changes, repeat-rich regions, and breed-specific sequences. Pangenomes address this limitation by integrating multiple high-quality assemblies or population-scale variants into a unified sequence or graph representation. Concurrently, multi-omics approaches connect genomic variation with transcriptomic, epigenomic, manuscriptproteomic, metabolomic, and microbiome responses, thereby improving biological interpretation of genotype-phenotype relationships. This review synthesizes recent progress in livestock pangenomics and multi-omics, with emphasis on cattle, goats, sheep, water buffalo, and chickens. It describes advances in long-read and haplotype-resolved sequencing, graph construction, structural-variant discovery and genotyping, functional annotation, and integrative analysis. Recent pangenome studies have uncovered substantial non-reference sequence, reduced reference bias, identified breed- and population-specific structural variants, and resolved candidate variants underlying pigmentation, body size, tail morphology, cashmere production, altitude adaptation, and other economically relevant traits. However, translation into routine breeding remains constrained by uneven population representation, inconsistent structural-variant definitions, limited functional annotation, computational demands, and insufficient validation across environments. Future progress will depend on diverse near-complete assemblies, graph-aware imputation and genomic prediction, long-read transcriptomics, single-cell and spatial omics, rigorous causal validation, and open, interoperable resources. Together, these developments can support more accurate, resilient, and biologically informed livestock improvement. Importantly, current dairy-cattle evidence indicates that pangenome-derived structural variants can substantially improve variant discovery and functional interpretation while yielding only marginal average gains in routine genomic prediction, favoring targeted augmentation rather than wholesale replacement of established SNP-based evaluations.

Animals↗

PubMed2026

CMAtlas: a comprehensive DNA methylation atlas for exploring epigenetic alterations in 34 human cancer types.

MOTIVATION: Aberrant DNA methylation is a fundamental epigenetic hallmark of cancer. However, existing resources often lack technological diversity and comprehensive cancer coverage. Furthermore, most platforms fail to achieve deep multi-omics integration and tend to ignore cancer-type-specific methylation features, limiting their utility in precision oncology and drug discovery. RESULTS: We developed Cancer Methylation Atlas (CMAtlas), a comprehensive platform integrating 13 753 samples across 34 cancer types. By applying technology-tailored pipelines to data from various profiling technologies, we identified 830 725 tumor-specific differentially methylated elements (DMEs) and 1 480 098 differentially methylated regions (DMRs), alongside 1 154 256 cancer-type-specific DMEs and 329 154 DMRs. The platform demonstrates high cross-platform consistency and strong concordance between tumor tissues and cell lines, ensuring the robustness of our findings. All DMEs and DMRs are annotated with multi-omics data (RNA expression, somatic mutations, and chromatin accessibility) and clinical relevance (survival associations and cell-free DNA profiling). We further demonstrate the utility of CMAtlas by identifying prognostic aberrant methylation in colorectal cancer driver genes. AVAILABILITY AND IMPLEMENTATION: CMAtlas is freely accessible at {{https://cmatlas.renlab.cn/}}. The platform offers an intuitive web interface supporting gene-centric and cancer-centric queries, alongside customizable analysis modules designed to facilitate user-specific research needs.

Humans↗

PubMed2026

PEARL: integrative multi-omics classification and omics feature discovery via deep graph learning.

MOTIVATION: Integrating multi-omics data provides valuable insights into biological processes by capturing information across multiple molecular layers, enabling a comprehensive understanding of complex diseases and driving advancements in precision medicine. However, existing computational methods for multi-omics integration face significant challenges, such as low reliability and poor generalizability, due to the high dimensionality and low sample size nature of omics data. RESULTS: To address these challenges, we present PEARL (Pearson-Enhanced spectrAl gRaph convoLutional networks), a novel deep graph learning method for biomedical classification and functional important omics features identification. PEARL leverages a simple yet effective learning architecture to achieve superior and robust performance in high-dimensional, low-sample-size multi-omics settings. Our results demonstrate that PEARL significantly outperforms existing state-of-the-art methods on both synthetic and real biomedical datasets. Furthermore, applied to Alzheimer's disease (AD) brain multi-omics data, features prioritized by PEARL lead to functionally important genes that demonstrate significant enrichment in AD-related pathways. These findings highlight PEARL's practical utility in biomedical research and its potential to enhance biological interpretability in multi-omics studies. AVAILABILITY AND IMPLEMENTATION: The source code of our computational framework is available at https://github.com/zqq121017/PEARL.

Multiomics↗

PubMed2026

Association between the gut microbiome and plasma metabolites linked to vocalization-based temperament in Merino sheep.

BACKGROUND: Temperament, as a determinant of behavioural and emotional responses, has a substantial adaptive value in different environments. This study aims to investigate the association between the gut microbiota and temperament plasticity, and clarify the potential metabolic mechanism that underpins that association by running a multi-omics study in sheep. METHODS: The TrackSheep research cohort was generated using 200 healthy juvenile Merino ewes, and the rumen microbiota, plasma metabolome, and temperament phenotype was measured. RESULTS: Rumen metagenomic analysis identified 25 microbial species and 16 MetaCyc pathways that explained 37.5% and 11.1%, respectively, of the variation in temperament as estimated using the vocal reactivity to stress. Among these, the γ-aminobutyric acid (GABA) shunt and allantoin degradation pathways showed the strongest associations with vocal behaviour. Multi-omic integration linked these microbial pathways to plasma metabolites that are involved in neurotransmission, antioxidant defense, and energy metabolism, including acetyl-L-carnitine (ALCAR) and urocortisone, which partially mediated the effects of microbial pathways on vocalisations. Notably, functional genomic and mediation analyses indicated that the abundance of Cryptobacteroides sp902761655 was associated with the activity of GABA shunt pathway, where GABA co-occurred with succinate production, in turn correlating with reduced inhibitory effects of ALCAR on stress-susceptible temperament. Although plasma metabolite shifts observed immediately after behavioural tests reflected stress exposure, their associations with rumen microbiota highlight microbiome-metabolite interplay that could underly behavioural variation. CONCLUSIONS: Our study provides the first large-scale multi-omics evidence linking the rumen microbiome to a dimension of emotional reactivity in livestock, while underscoring the need for longitudinal and experimental validation to establish causal mechanisms. Video Abstract.

Animals↗

PubMed2026

Transcriptomic and Metabolomic Profiling Identifies a Core Gene-Metabolite Axis Driving African Swine Fever Virus Replication in the Soft Tick Ornithodoros lahorensis.

African swine fever virus (ASFV) causes an incurable swine disease with nearly 100% mortality, posing a catastrophic threat to global pig production. The soft tick Ornithodoros lahorensis acts as a critical biological vector that sustains persistent ASFV replication and mediates long-distance viral transmission, yet the molecular mechanisms governing ASFV-tick interplay remain poorly understood. Here, we integrated transcriptomics and metabolomics to systematically dissect molecular changes in O. lahorensis across three infection stages: Uninfected control, early infection (7 days post-infection, dpi), and late persistent infection (21 dpi). Multi-omics integration revealed that ASFV extensively remodels tick host metabolism, predominantly activating purine/pyrimidine metabolism, lipid biosynthesis, and energy metabolism. We further characterized a conserved regulatory module consisting of 12 core genes and 8 signature metabolites that collectively support ASFV genome replication and virion assembly. Three hub metabolic genes (TK1, ATP5F1B, and IMPDH) were selected for functional validation via siRNA silencing in ticks; individual gene silencing suppressed ASFV loads by 89.2%, 91.5%, and 87.8%, respectively (p < 0.001***). This work represents the first comprehensive multi-omics investigation of ASFV infection in O. lahorensis. We identified tick-specific molecular targets to block vector-mediated ASFV spread and established a standardized multi-omics analytical pipeline for tick-virus interaction research. Our findings elucidate the mechanistic basis of long-term ASFV persistence in soft ticks and deliver novel actionable clues for developing vector-targeted ASF intervention strategies.

Animals↗

PubMed2025

Composition-on-composition regression analysis for multi-omics integration of metagenomic data.

MOTIVATION: Compositional data are frequently encountered in many disciplines, such as in next-generation sequencing experiments widely used in biomedical studies. Regression analysis with compositional data as either responses or predictors has been well studied. However, when both responses and predictors are compositional, the inventory of analysis tools is surprisingly limited, especially in the high-dimensional setting. Among the few existing methods, most of them rely on a log-ratio transformation to move compositional data from the simplex to real numbers. Yet, a serious weakness of these methods is their failure to handle the substantial fraction of zeroes observed in data collected from next-generation sequencing experiments. RESULTS: To investigate associations between two high-dimensional multi-omics compositions, we propose a composition-on-composition (COC) regression analysis method which does not require log-ratio transformations and hence can handle zeroes in the data. To account for high dimensionality, we estimate regression coefficients using a penalized estimation equation approach. Finally, inference procedures for COC regression are also proposed. Superior performance of COC is demonstrated through both comprehensive numerical simulations and case studies. AVAILABILITY AND IMPLEMENTATION: Source R codes to implement COC method is available at https://github.com/nrios4/COC.

Regression Analysis↗

PubMed2026

Region-Resolved Integrative Multi-Omic Characterization Reveals Diverse Tumor and Microenvironment Features of Pituitary Neuroendocrine Tumors.

Pituitary neuroendocrine tumors are frequently invasive, with cavernous sinus invasion leading to poor treatment outcomes and high recurrence. Regional differences within these tumors remain poorly understood, hindering targeted therapy development. Here, we present the first integrative multi-omics analysis combining proteomics, metabolomics and single-cell transcriptomics to characterize tumors from the cavernous sinus and saddle regions. Our results reveal profound regional and cellular heterogeneity: cavernous sinus tumors exhibit significantly enhanced cell proliferation, driven by cancer-associated fibroblasts through the IGF1-IGF1R-MAPK1 axis. Cancer-associated fibroblasts in the cavernous sinus secrete IGF1 under regulation of the transcription factor FOXO1, which binds to receptors on tumor cells to activate proliferation. Metabolomic profiling identifies proline as a key enriched metabolite that stimulates cancer-associated fibroblasts to produce collagen fibers, reinforcing a pro-tumorigenic microenvironment. Single-cell transcriptomics further delineates a distinct subpopulation of receptor-positive malignant cells and a high abundance of cancer-associated fibroblasts in the cavernous sinus. These findings establish core mechanisms underlying the aggressive behavior of cavernous sinus-invading tumors, providing novel actionable targets for precision therapeutic strategies tailored to distinct tumor regions.

Humans↗

PubMed2026

Urinary multi-omics reveal non-invasive diagnostic biomarkers in clear cell renal cell carcinoma.

Clear cell renal cell carcinoma (ccRCC) is the most common kidney malignancy. Yet, no rapid, non-invasive biomarkers are available for diagnosis or screening. Urine represents an ideal analyte matrix due to its accessibility, low invasiveness, longitudinal sampling, and the kidney's central role in filtration. Here, we integrated proteomic, lipidomic, and metabolomic analyses of urine from ccRCC patients and controls to identify diagnostic biomarkers. Multi-omics profiling revealed urogenital metabolic dysregulation in ccRCC, including increased lipid metabolism, altered mitochondrial respiration signatures, and elevated urinary lipid content. We identified three urinary protein biomarkers: serum amyloid A1 (SAA1), haptoglobin (HP), and lipocalin 15 (LCN15). Using a parallel reaction monitoring mass spectrometry workflow, we developed a rapid and sensitive assay and combined these markers into a diagnostic UrineScore. The UrineScore achieved 0.96 in an area under the receiver operating characteristic curve analysis in the discovery cohort, and 0.95 in an independent validation cohort. Together, these results support the feasibility of multi-omics-guided urinary biomarker discovery and represent a step toward accessible diagnostic platforms for ccRCC.

Humans↗

PubMed2026

AI proteomics: from protein identification to virtual cells.

Artificial intelligence (AI) is transforming scientific research, including proteomics. In this Perspective, we highlight key mass spectrometry (MS)-based proteomics areas where AI is driving innovation, ranging from protein identification to building AI virtual cells. These include improving peptide and protein identification and quantification; characterizing protein-protein interactions and protein complexes; advancing spatial and perturbation proteomics; integrating multi-omics data; and, ultimately, enabling AI virtual cells. Finally, we call for global collaboration among data producers, data consumers and other stakeholders to establish an AI-friendly ecosystem for MS-based proteomics, laying the foundation for transformative advancements in proteomics driven by AI.

Proteomics↗

PubMed2025

AI-driven multi-omics modeling of myalgic encephalomyelitis/chronic fatigue syndrome.

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a chronic illness with a multifactorial etiology and heterogeneous symptomatology, posing major challenges for diagnosis and treatment. Here we present BioMapAI, a supervised deep neural network trained on a 4-year, longitudinal, multi-omics dataset from 249 participants, which integrates gut metagenomics, plasma metabolomics, immune cell profiling, blood laboratory data and detailed clinical symptoms. By simultaneously modeling these diverse data types to predict clinical severity, BioMapAI identifies disease- and symptom-specific biomarkers and classifies ME/CFS in both held-out and independent external cohorts. Using an explainable AI approach, we construct a unique connectivity map spanning the microbiome, immune system and plasma metabolome in health and ME/CFS adjusted for age, gender and additional clinical factors. This map uncovers altered associations between microbial metabolism (for example, short-chain fatty acids, branched-chain amino acids, tryptophan, benzoate), plasma lipids and bile acids, and heightened inflammatory responses in mucosal and inflammatory T cell subsets (MAIT, γδT) secreting IFN-γ and GzA. Overall, BioMapAI provides unprecedented systems-level insights into ME/CFS, refining existing hypotheses and hypothesizing unique mechanisms-specifically, how multi-omics dynamics are associated to the disease's heterogeneous symptoms.

Humans↗

PubMed2025

Multi-omic integration with human dorsal root ganglia proteomics highlights TNFα signalling as a relevant sexually dimorphic pathway.

The peripheral nervous system (PNS) plays a critical role in pathological conditions, including chronic pain disorders, that manifest differently in men and women. To investigate this sexual dimorphism at the molecular level, we integrated quantitative proteomic profiling of human dorsal root ganglia (hDRG) and peripheral nerve tissue into the expanding omics framework of the PNS. Using data-independent acquisition (DIA) mass spectrometry, we characterized a comprehensive proteomic profile, validating tissue-specific differences between the hDRG and peripheral nerve. Through multi-omic analyses and in vitro functional assays, we identified sex-specific molecular differences, with TNFα signalling emerging as a key sexually dimorphic pathway with higher prominence in men. Genetic evidence from genome-wide association studies further supports the functional relevance of TNFα signalling in the periphery, while clinical trial data and meta-analyses indicate a sex-dependent response to TNFα inhibitors. Collectively, these findings underscore a functionally sexual dimorphism in the PNS, with direct implications for sensory and pain-related clinical translation.

Humans↗

PubMed2025

A pancreatic cancer organoid biobank links multi-omics signatures to therapeutic response and clinical evaluation of statin combination therapy.

Chemotherapy remains the primary treatment for pancreatic ductal adenocarcinoma (PDAC), but most patients ultimately develop resistance. Here, we established 260 pancreatic cancer organoid lines, followed by extensive multi-omics profiling and therapeutic sensitivity assessments. Integrated analyses uncovered 6 novel coding and 35 noncoding driver candidates. We discovered 2,794 multi-omics features associated with drug sensitivity and 322 features linked to radiation sensitivity. Pharmacogenomic analyses revealed that chemoresistant organoids exhibited enrichment in protein glycosylation and cholesterol metabolism pathways. Notably, statins effectively targeted chemoresistant PDAC organoids. Statin treatment attenuated protein glycosylation, cholesterol levels, and the epithelial-to-mesenchymal transition (EMT) signature in PDAC organoids. We conducted a single-center, single-arm, phase 2 clinical trial (NCT06241352) combining atorvastatin with chemotherapy in patients with advanced pancreatic cancer. Among 37 patients, 26 (70.3%) demonstrated a response, with tumor markers decreasing by more than 20%, suggesting durable responses and potential clinical benefits in this challenging patient population.

Humans↗

PubMed2025

Anticancer drug response prediction integrating multi-omics pathway-based difference features and multiple deep learning techniques.

Individualized prediction of cancer drug sensitivity is of vital importance in precision medicine. While numerous predictive methodologies for cancer drug response have been proposed, the precise prediction of an individual patient's response to drug and a thorough understanding of differences in drug responses among individuals continue to pose significant challenges. This study introduced a deep learning model PASO, which integrated transformer encoder, multi-scale convolutional networks and attention mechanisms to predict the sensitivity of cell lines to anticancer drugs, based on the omics data of cell lines and the SMILES representations of drug molecules. First, we use statistical methods to compute the differences in gene expression, gene mutation, and gene copy number variations between within and outside biological pathways, and utilized these pathway difference values as cell line features, combined with the drugs' SMILES chemical structure information as inputs to the model. Then the model integrates various deep learning technologies multi-scale convolutional networks and transformer encoder to extract the properties of drug molecules from different perspectives, while an attention network is devoted to learning complex interactions between the omics features of cell lines and the aforementioned properties of drug molecules. Finally, a multilayer perceptron (MLP) outputs the final predictions of drug response. Our model exhibits higher accuracy in predicting the sensitivity to anticancer drugs comparing with other methods proposed recently. It is found that PARP inhibitors, and Topoisomerase I inhibitors were particularly sensitive to SCLC when analyzing the drug response predictions for lung cancer cell lines. Additionally, the model is capable of highlighting biological pathways related to cancer and accurately capturing critical parts of the drug's chemical structure. We also validated the model's clinical utility using clinical data from The Cancer Genome Atlas. In summary, the PASO model suggests potential as a robust support in individualized cancer treatment. Our methods are implemented in Python and are freely available from GitHub (https://github.com/queryang/PASO).

Deep Learning↗

PubMed2026

engGNN: a dual-graph neural network for omics-based disease classification and feature selection.

Omics data, such as transcriptomics, proteomics, and metabolomics, provide critical insights into disease mechanisms and clinical outcomes. However, their high dimensionality, small sample sizes, and intricate biological networks pose major challenges for reliable prediction and meaningful interpretation. Graph neural networks offer a promising way to integrate prior knowledge by encoding feature relationships as graphs. Yet, existing methods typically rely solely on either an externally curated feature graph or a data-driven generated graph, which limits their ability to capture complementary information. To address this, we propose the external and generated Graph Neural Network (engGNN), a dual-graph framework that jointly leverages both external biological networks and data-driven generated graphs. Specifically, engGNN constructs a biologically informed undirected feature graph from established network databases and complements it with a directed feature graph derived from tree-ensemble models. This dual-graph design produces more comprehensive representations, thereby improving predictive performance and interpretability. Through extensive simulation studies and real-world applications to three independent gene expression datasets, engGNN consistently demonstrates strong classification performance compared with competitive baselines. Beyond classification, engGNN provides feature- and source-level interpretability, enabling biologically meaningful analyses such as pathway enrichment analysis. Taken together, these results highlight engGNN as a robust, flexible, and interpretable framework for disease classification and biomarker discovery in high-dimensional omics contexts.

Graph Neural Networks↗