graph neural network

The paper introduces a model to classify brain dynamics based on chronnectome complexity, showing high accuracy in distinguishing cognitive states and age-related changes.

This paper introduces HHRM, a hierarchical model for tumor subtype classification, achieving high accuracy in pan-cancer and breast cancer subtyping with interpretable biomarker identification.

This paper introduces dreems, a graph neural network that efficiently estimates effective migration surfaces from genetic data, achieving lower error and faster computation than existing methods.

This paper introduces CircuitGNN, a graph neural network that infers neural connectivity from population activity, showing high accuracy and robustness across different circuit sizes and recording conditions.

The paper develops a multi-layered GCN to identify TME-guided PDAC subtypes, revealing seven subtypes with distinct molecular and prognostic features.

The paper introduces SPInfer, a workflow for spatial proteomic inference that improves cell segmentation in human brain tissue, enabling better biological discovery at population scale.

GenDiMug is a multigraph framework for analyzing genomic organization and multi-omics data across scales, revealing gene expression clumping and circadian regulation in a photosynthetic alga.

The paper introduces scProfiterole, a framework for clustering single-cell proteomic data using graph contrastive learning with spectral filters, showing improved cell type identification.

Site-aware population GNN on ABIDE-I: cohort AUC about 0.94 (kept with site-only edges) was not reproduced by a site-prior classifier (0.506); a directed-edge support gain (+0.252) vanished when symmetrised (−0.003).

This paper develops a region-specific AI model for mammal classification using graph attention contrastive learning, achieving high accuracy in recognizing local species and improving data cleaning efficiency.

Himito is a graph-based toolkit for analyzing mitochondrial genomes using long reads, achieving superior performance in assembly and variant calling and revealing age-related patterns in the All of Us dataset.

This paper introduces a network-based method to detect neuronal assemblies from spike train data using the van Rossum distance and Louvain algorithm, validated on synthetic and real datasets.

DNA2Graph automates the identification of non-linear DNA molecules in electron microscopy images, significantly reducing the need for manual review and improving structure detection.

PGD improves visualization of single-cell trajectories by smoothing cell-level features along pseudotime, enhancing continuity and structure in complex biological processes.

The paper introduces STORM, a method to identify recurrent spatial motifs in colorectal cancer without cell-type labels, finding a fibroblast barrier linked to immune exclusion and prognosis.

This paper introduces st-Xprop, a graph learning method for spatial domain detection in multi-modal spatial transcriptomics, improving clustering accuracy and biological relevance.

This paper introduces Gene Program Negotiation (GPN), a framework to analyze regulatory interactions in single-cell transcriptomes, revealing new regulatory states and their association with cellular plasticity.

This paper develops a self-supervised framework for learning structure-connectivity representations in dense connectomes, revealing neuronal organization beyond canonical labels.

The paper introduces synteny-aware pangenome graphs to visualize genomic variation in marine bacteria, revealing structured continua of variability across genomes.

This paper introduces STACAME, a framework for analyzing cross-species spatial transcriptomics data to identify shared and divergent tissue architectures across species.

GATHeR reconstructs full-length, paired B-cell receptor sequences from scRNA-seq data, improving subclass, allele, and isoform resolution, especially in naive and memory B cells.

This study shows that chronic stress worsens microvascular network dysfunction after brain trauma, reducing capillary coordination and vascular reactivity.

HyperNiche improves clustering and biological interpretability of spatial transcriptomics data by modeling higher-order cellular niches with hypergraph neural networks.

This paper introduces HAST, a framework for spatial transcriptomics that adapts graph learning scales to tissue heterogeneity, improving spatial structure identification and tumor region characterization.

GatorSC improves single-cell transcriptomic analysis by integrating multi-scale cell and gene graphs with a Mixture-of-Experts fusion framework, outperforming existing methods in clustering, imputation, and annotation.

ARGMix uses a graph transformer to infer local ancestry from ancient DNA, showing continuity between Otzi the Iceman and present-day Europeans.

This paper introduces BrainMetaGCN, a memory-augmented graph learning framework for AMDD diagnosis using rs-fMRI, achieving better performance than baseline models.

GraphHDBSCAN* performs hierarchical clustering on scRNA-seq data, recovering biologically meaningful hierarchies and improving flat partition quality.

SpotGraphs provides a flexible R package for directly interacting with spatially resolved transcriptomic data through graph analysis, offering tools for quality filtering and adjacency editing.