Abstract Integrating multi-omics profiles with molecular interaction networks enables biologically informed representation learning by combining molecular measurements with prior biological knowledge. Although graph neural networks (GNNs) are well suited for modeling molecular interaction networks, existing multi-omics methods often rely on shallow representation learning or incomplete fusion strategies, which fail to fully capture complementary information and complex dependencies across heterogeneous omics layers, resulting in suboptimal performance and limited generalizability in cancer classification tasks. Here, we propose GONet, a hierarchical GNN framework that integrates omics expression profiles, including mRNA, miRNA, and protein data, with molecular interaction networks, where nodes represent omics features and edges represent molecular interactions. GONet learns global omics representations via an autoencoder, captures local structural dependencies using Deep Graph Infomax (DGI), and enhances omics-specific representations through an attention mechanism. A gated fusion module further enables adaptive integration of heterogeneous features, improving cancer subtype and stage classification. GONet was systematically evaluated on 13 publicly available benchmark datasets used in prior studies, covering 10 cancer types, ensuring fair comparison across methods. Across mRNA and miRNA datasets, GONet achieved an average AUROC of 0.9262, outperforming representative GNN- and non-GNN-based methods by 13.77% and 6.35%, respectively. On an independent CPTAC cohort spanning seven cancer types, it improved performance by 25.22% and 13.91%, respectively. Incorporating proteomics further improved cancer stage classification by 5.56%, demonstrating complementary predictive value. Ablation studies confirmed the effectiveness of the DGI-based module. Overall, GONet provides a unified framework for biologically informed multi-omics graph representation learning and cancer classification.
Background The precise molecular delineation of the interface between the Subiculum (Sub) and cornu ammonis 1 (CA1) is a challenge in hippocampal research, as conventional cytoarchitectural boundaries are often ambiguous and limit reproducible regional annotation. Here, we developed a molecularly anchored spatial transcriptomic framework to define CA1-Sub regional identities using high-definition spatial transcriptomics (Stereo-seq) and single-nucleus RNA sequencing (snRNA-seq) references.Findings Using a human hippocampal Stereo-seq dataset from 12 donors, we established a data-driven parcellation framework that defines reproducible molecular features distinguishing CA1 and Sub while capturing the transition between these regions. FN1 was identified as a Sub-enriched marker in a subset of EX_Sub and, together with ETV1 and additional regional markers, enabled molecular assignment of CA1 and Sub identities across datasets. The Sub association of FN1 and ETV1 was further supported by human 10X Genomics spatial transcriptomics, mouse in situ hybridization data, and a mouse spatial transcriptomic dataset. Applying this framework to Alzheimer's disease tissues revealed region-specific transcriptional alterations across CA1 and Sub, including enrichment of mitochondrial energy metabolism-related transcripts in the Sub, suggesting exploratory transcriptional associations of altered metabolic function.Conclusions This study provides a molecularly anchored framework for human CA1-Sub parcellation that complements conventional annotation. By defining regional molecular states while preserving the biological continuum across CA1-Sub interface, this approach enables more consistent regional analysis of human hippocampus tissue across donors, datasets, and disease conditions.
Abstract Multiple single nuclei RNA-sequencing (snRNA-seq) studies of the vulnerable brain regions of Parkinson’s Disease (PD) have revealed alterations in brain cell populations and cell type specific transcriptomes. However, a systematic analysis of cell-type–resolved gene regulatory architecture in PD is lacking. Here, we develop an integrative, meta-cell based multiscale network analysis (MCMNA) of snRNA-seq data from the substantia nigra to systematically uncover molecular mechanisms and identify potential therapeutic targets for PD. MCMNA overcomes the inherent sparsity of single cell data by leveraging metacell-based aggregation, enabling construction of robust gene regulatory networks. Gene co-expression network analysis identifies cell-type specific gene modules associated with PD. Integration of meta-cell based differential gene expression and a Bayesian causal network systematically reveals putative driver genes and their hierarchies. Our multiscale network models provide a framework for prioritizing candidate molecular regulators and pathways for further investigation of disease mechanisms and therapeutic targets.
Background: Personalized neoantigen discovery requires tools that not only identify putative epitopes but also prioritize candidates using biological features relevant to tumor fitness and immune escape. Here, we present Epitope Generation Gateway (EGG), a containerized pipeline that streamlines discovery and prioritization across variant types and human leukocyte antigen (HLA) contexts. EGG coordinates established components, Mutect2 for somatic single nucleotide variations (SNVs) and indels, STAR-Fusion for fusion events, ArcasHLA for HLA typing, and pVACtools for epitope sequence prediction, then augments peptide-level scores with biological context. For each patient, EGG builds co-expression and protein-protein interaction networks, uses centrality measures and CRISPR dependency data (DepMap) to flag genes important for tumor fitness, and annotates source genes with gene ontology terms, Hallmarks of Cancer processes, and IntOGen driver status. Results: This multi-layer information supports ranking of candidates that are predicted to be presented and that arise from genes essential to tumor fitness or embedded in key pathways, providing a framework to nominate epitopes whose source genes may be less dispensable under immune pressure. As a case study, we applied EGG to 30 TCGA skin cutaneous melanoma patients, demonstrating end-to-end execution and producing prioritized epitopes that emphasize peptides and alterations in high-centrality, dependency-supported essential genes. Conclusions: Overall, EGG links epitope prioritization to tumor systems biology and evolutionary rationale, prioritizing biologically contextualized cancer vaccine candidates from SNVs, indels, fusions, and splicing-derived epitopes while streamlining dataset analysis. EGG is available from GitHub at https://github.com/fhaive/epitope_generation_gateway.
