graph neural network

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

GnnDebugger uses Graph Neural Networks to correct errors in De Bruijn Graphs, improving genome assembly accuracy for diploid genomes with low coverage.

Pillbox predicts cancer drug response using foundation models and evaluates lineage ceiling through residual correlation analysis.

This paper introduces GAFM and HBP methods to improve GWAS fine-mapping by leveraging biological structure, achieving higher accuracy and speed across multiple species and datasets.

SMLMFlow enhances structural resolution in single molecule localization microscopy by combining graph neural networks and hierarchical transformers with flow matching.

This study evaluates urban green spaces connectivity in 28 European capitals using Earth observation and graph theory, finding that network metrics better capture functional connectivity than traditional metrics.

This study uses graph signal processing to analyze structural and functional brain connectivity in healthy aging, revealing distinct age-related patterns in cognitive systems.

This study uses AI to discover small molecules that rejuvenate hair follicles by targeting complementary pathways, showing increased cell viability and suppression of follicular miniaturization.

This paper introduces STAMO, a spatially aware integration method for unpaired spatial multi-omics data, showing improved alignment and domain detection compared to existing methods.

This paper introduces a hypergraph neural network to predict antimicrobial combination effects across bacterial targets, achieving high accuracy and F1-scores in classifying synergy, antagonism, and non-interaction.

The paper introduces OMNI, a graph neural network framework for biomedical interaction prediction, achieving high accuracy in chemical-gene interaction prediction.

This paper introduces HydroMap and FastHydroMap models to predict hydrophobicity from water features, enabling rapid and accurate computation of dewetting free energy for proteins and surfaces.

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.

APOSM improves generative small-molecule design by using pairwise preference learning to enhance surrogate model reliability and active candidate selection.

This paper introduces a graph-based scoring function for predicting protein-ligand binding energies, achieving high accuracy across multiple datasets.

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

This paper introduces a stereochemistry-aware framework for drug-target affinity prediction, showing improved accuracy in distinguishing enantiomer affinities.

This study develops a framework for predicting protein function and domain annotation at isoform resolution using structural and sequence data, showing strong performance in benchmark tests and capturing domain changes across isoforms.

CytoGem-XAI combines hypergraph neural networks with interpretable analysis to improve metabolic modeling and prediction in E. coli, outperforming existing methods and revealing new essential nutrients.

This paper introduces a dual-channel fusion graph convolutional network to reconstruct gene regulatory networks and identify key regulators from single-cell RNA sequencing data, showing improved accuracy and robustness.

This study defines the spatial architecture of intrahepatic cholangiocarcinoma using single-cell spatial proteomics and a graph-based deep learning framework to identify multicellular spatial patterns and their association with patient outcomes.

This study evaluates a pretrained graph neural network for predicting P-glycoprotein substrate status using a benchmark dataset, achieving high AUROC scores.

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

The paper uses AI and thermal proteomics to identify a natural product's direct target and shows its therapeutic effect in a psoriasis model.

This paper uses Bayesian optimisation and graph-based rheology to model DNA materials by linking sequence design to material properties.

This study identifies network reorganization patterns in postoperative cognitive decline using static and dynamic connectivity measures from resting-state fMRI.

SSPSPredictor predicts phase-separating proteins using sequence and structure data, showing higher LLPS propensity in intrinsically disordered proteins and pathogenic variants.

This paper introduces ProtEGNN, a model combining protein language models with geometric equivariance to improve protein property and function prediction with fewer parameters than fine-tuned PLMs.

The paper develops a deep learning tool to analyze endometrial histology and identifies morphological correlates of miscarriage risk.

GraphTME predicts immune checkpoint inhibitor response by analyzing spatial cell-cell interactions in tumor microenvironments using spatial transcriptomics data.