graph neural network

Amira: detection of AMR genes directly from long reads using gene-space de Bruijn graphs

Amira detects AMR genes directly from long reads using gene-space de Bruijn graphs, achieving high recall and accuracy compared to assembly-based methods.

MAGELLAN: Automated Generation of Interpretable Computational Models for Biological Reasoning

MAGELLAN constructs interpretable computational models from pathway data and experimental rules, demonstrating predictive accuracy in breast cancer and NSCLC signalling.

Riemann-GNN: Causal Reasoning on Hyperbolic Riemannian Manifolds for Interpretable Drug-Disease Prediction

Riemann-GNN uses hyperbolic geometry and causal inference to predict drug-disease associations with high accuracy and interpretability.

Advancements in Ligand-Based Virtual Screening through the Synergistic Integration of Graph Neural Networks and Expert-Crafted Descriptors

This paper evaluates combining graph neural networks with expert descriptors for ligand-based virtual screening, finding that simpler GNNs with descriptors perform comparably to complex ones and that expert descriptors excel in scaffold-split scenarios.

Quantitative RNA pseudouridine landscape reveals dynamic modification patterns and evolutionary conservation across bacterial species

This study maps pseudouridine modifications across bacterial species, revealing dynamic patterns and evolutionary conservation, and develops a deep learning framework for predicting modified sites.

FISHnet: Detecting chromatin domains in single-cell sequential Oligopaints imaging data

FISHnet detects chromatin domains in single-cell sequential Oligopaints imaging data using graph theory and network modularity optimization.

A Multimodal Graph Learning Framework for Versatile Spatial Transcriptomics Analysis with SpatialModal

SpatialModal integrates gene expression and histological images in spatial transcriptomics to improve spatial analysis and domain identification.

Characterizing Spatially Continuous Variations in Tissue Microenvironment through Niche Trajectory Analysis

ONTraC uses a graph neural network to analyze spatial transcriptomics data, improving trajectory reconstruction and revealing microenvironment-dependent changes in gene regulation and cell interactions during development.

Discovering disease genetic variation impacting gene expression in 103 brain tissues with the Brain Ontology Expression (BRONTE) graph neural network model

The paper imputes gene expression in 103 brain tissues using BRONTE, a graph neural network, and identifies new genes and tissues affected by genetic variants linked to brain-related traits.

Improving plant functional annotation from knowledge graphs using Graph Neural Networks

This paper develops a knowledge graph and uses graph neural networks to improve gene functional annotation in plants, outperforming orthology-based methods in transferring knowledge between species.

Predicting Inhibitors of OATP1B1 via Heterogeneous OATP-Ligand Interaction Graph Neural Network (HOLIgraph)

This paper introduces HOLIgraph, a graph neural network model that predicts OATP1B1 inhibitors by integrating ligand features and protein-ligand interactions, achieving over 90% balanced accuracy.

Separable Spatial Single-cell Transcriptome Representation Learning via Graph Transformer and Hyperspherical Prototype Clustering

S3RL improves spatial transcriptomics analysis by enhancing resolution, clustering, and ligand-receptor detection across multiple datasets.

EpiMII: Integrating Structure and Graph Neural Networks for MHC-II Epitope and Neoantigen Design

EpiMII improves MHC-II epitope and neoantigen design by integrating structural features with graph neural networks, achieving higher accuracy and in vivo efficacy in tumor models.

G2VTCR: predicting antigen binding specificity by Weisfeiler-Lehman graph embedding of T cell receptor sequences

G2VTCR predicts TCR-antigen binding using graph embeddings of TCR sequences and antigens, outperforming existing methods in classification and clustering.

Mechanistic basis for GPCR phosphorylation-dependent allosteric signaling specificity of β-arrestin 1 and 2

This study maps how phosphorylation patterns shape β-arrestin structure and function using simulations and machine learning, revealing isoform-specific allosteric responses and effector engagement.

GenVS TBDB: A Target-Aware AI-Generated and Virtual Screened Small-Molecule Library for Tuberculosis Drug Discovery

This paper introduces GenVS-TBDB, an AI-generated and virtual-screened small-molecule library targeting Mycobacterium tuberculosis, identifying bioactive compounds with potential for tuberculosis drug discovery.

Accurate PROTAC targeted degradation prediction with DegradeMaster

DegradeMaster predicts PROTAC-targeted protein degradation using a semi-supervised E(3)-equivariant graph neural network, achieving improved accuracy over existing methods.

Accurate Predictions of Molecular Properties of Proteins via Graph Neural Networks and Transfer Learning

This paper introduces GSnet, a graph neural network for predicting protein molecular properties, and shows it outperforms existing methods for solvent-accessible surface area prediction.

STING: A Graph Neural Network Approach for Computational Inference of Spatial Transcriptomic Profiles

STING uses graph neural networks to predict spatial gene expression from histological images, achieving high accuracy in spatial transcriptomics inference.

Integration of multi-source gene interaction networks and omics data with graph attention networks to identify novel disease genes

This study introduces DGP-AMIO, a graph attention network-based method that integrates multi-omics and gene interaction data to identify novel disease genes, achieving high performance across 20 disease datasets.

Multiple Targets, One Goal: Compounding life-extending effects through Polypharmacology

The paper uses graph neural networks to predict polypharmacological compounds that extend lifespan in C. elegans, finding 70% of selected compounds significantly increase lifespan.

Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning

This paper introduces scRegNet, a framework combining single-cell foundation models with graph-based learning to predict gene regulatory links, achieving state-of-the-art results on benchmark datasets.

MPBind: Multitask Protein Binding Site Prediction by Protein Language Models and Equivariant Graph Neural Networks

MPBind predicts protein binding sites for multiple partners using protein language models and equivariant graph neural networks, outperforming existing methods.

Graph-Based Modeling of Alzheimer's Protein Interactions via Spiking Neural, Hyperdimensional Encoding, and Scalable Ray-Based Learning

This paper introduces a computational framework for predicting Alzheimer's protein interactions using graph-based learning, spiking neural networks, and hyperdimensional encoding.

BRIDGE: A Coarse-Grained Architecture to Embed Protein-Protein Interactions for Therapeutic Applications

BRIDGE is a graph neural network that embeds protein-protein interactions for therapeutic applications, achieving state-of-the-art performance in predicting Ab-Ag affinity and antibody viscosity.

Chromatin Structures from Integrated AI and Polymer Physics Model

The paper develops a framework combining polymer physics and machine learning to estimate chromatin structures from Hi-C data with high accuracy.

An unsupervised map of excitatory neurons' dendritic morphology in the mouse visual cortex

The paper uses graph-based machine learning to analyze dendritic morphology of excitatory neurons in mouse visual cortex, finding a continuous morphological landscape rather than discrete types.

A knowledge graph and topological data analysis framework to disentangle the tomato-multi pathogens complex gene regulatory network

The paper constructs a knowledge graph and uses topological data analysis to uncover the gene regulatory network of tomato's response to multiple pathogens, identifying key transcription factors and regulatory hubs.

GLASS: A Graph Learning Algorithm for Screening Splice-Aware Alignments of Long-Read RNA-seq

GLASS filters erroneous splice-aware alignments from long-read RNA-seq data, improving transcriptome reconstruction accuracy across multiple species.

Taurine pangenome uncovers a segmental duplication upstream of KIT associated with depigmentation in white-headed cattle

The paper identifies a structural variant upstream of KIT associated with facial depigmentation in white-headed cattle using pangenome analysis and long-read sequencing.