graph neural network

GraphPred: An approach to predict multiple DNA motifs from ATAC-seq data using graph neural network and coexisting probability

GraphPred predicts multiple DNA motifs from ATAC-seq data using a graph neural network and coexisting probability, outperforming existing methods on 88 datasets.

Phylogeny and Metadata Network Database for Epidemiologic Surveillance

The paper creates a graph database to integrate SARS-CoV-2 phylogenetic trees, metadata, and surveillance data for phylodynamic analysis.

Supervised spatial inference of dissociated single-cell data with SageNet

SageNet predicts spatial positions and cell-cell proximities of dissociated single-cell data using a graph neural network trained on spatial references.

A graph neural network approach to molecule carcinogenicity prediction

This paper introduces a graph neural network model for predicting molecule carcinogenicity, showing improved performance over existing methods.

A Graph Convolutional Network-based screening strategy for rapid identification of SARS-CoV-2 cell-entry inhibitors

The paper develops a graph convolutional network to screen compounds for SARS-CoV-2 entry inhibitors, identifying 16 active compounds from 170,000 virtual candidates.

A maximum mean discrepancy approach reveals subtle changes in α-synuclein dynamics

This paper introduces a statistical method to compare biomolecule dynamics across conditions without identifying generating models, showing it detects changes in α-synuclein dynamics during depolarization.

Learning inverse folding from millions of predicted structures

Adding 12 million AlphaFold2-predicted structures to training lifts native sequence recovery on held-out backbones to 51.6%, versus 42.2% for the best experimental-only model; likelihoods score mutation effects zero-shot.

Deciphering spatial domains from spatially resolved transcriptomics with adaptive graph attention auto-encoder

This paper introduces STAGATE, a graph attention auto-encoder for spatial domain detection in spatial transcriptomics, improving accuracy and reducing batch effects across sections.

Prediction of brain functions from structural connectome using graph neural network

This paper uses a graph neural network to predict task-evoked fMRI responses from structural connectome data, revealing the importance of ipsilateral cortical regions for higher cognitive functions.

Neural relational inference to learn allosteric long-range interactions in proteins from molecular dynamics simulations

The paper uses a neural relational inference model to learn long-range interactions in proteins from molecular dynamics simulations, revealing allosteric communication pathways in Pin1, SOD1, and MEK1 systems.

Integrating long-range regulatory interactions to predict gene expression using graph convolutional networks

The paper introduces GC-MERGE, a graph convolutional model that integrates spatial genomic organization and histone modifications to predict gene expression and interpret regulatory factors.

Classification and clustering of RNA crosslink-ligation data reveal complex structures and homodimers

The paper introduces computational tools to analyze crosslink-ligation RNA data, revealing new RNA structures and homodimers.

Reconstructing co-dependent cellular crosstalk in lung adenocarcinoma using REMI

The paper introduces REMI, a graph-based method to reconstruct cell-cell interactions in lung adenocarcinoma by accounting for ligand-receptor dependencies, and validates its findings experimentally.

Robust high-throughput phenotyping with deep segmentation enabled by a web-based annotator

This paper introduces a high-throughput plant phenotyping system with a GUI and SGIOS algorithm to streamline training data generation and improve GWAS for trait variation analysis.

A copula based topology preserving graph convolution network for clustering of single-cell RNA-seq data

This paper introduces sc-CGconv, a graph convolution network for single-cell RNA-seq clustering that improves homogeneity by preserving cell-to-cell variability and handling technical noise.

Protein-Ligand Interaction Graphs: Learning from Ligand-Shaped 3D Interaction Graphs to Improve Binding Affinity Prediction

The paper introduces Protein-Ligand Interaction Graphs (PLIGs) to improve binding affinity prediction by encoding 3D protein-ligand interactions into GNN node features, achieving high performance on the CASF-2016 benchmark.

A cattle graph genome incorporating global breed diversity

The paper creates a graph genome incorporating global cattle diversity, showing it includes more sequence and improves mapping and variant calling.

A Self-attention Graph Convolutional Network for Precision Multi-tumour Early Diagnostics with DNA Methylation Data

The paper introduces a self-attention graph convolutional network to identify key DNA methylation sites for multi-tumor early diagnostics, achieving improved sensitivity in blood-based detection.

Graph theoretical analysis reveals the adaptive role of the left ventral occipito-temporal cortex in the brain networks during speech processing

This study uses graph theoretical analysis to show how the left ventral occipito-temporal cortex adapts its connectivity in brain networks during different speech processing tasks.

Improving Small Molecule pKa Prediction Using Transfer Learning with Graph Neural Networks

The paper develops a graph neural network model for predicting small molecule pKa values, fine-tuned on experimental data and integrated into an open-source tool for accurate protonation state enumeration.

conST: an interpretable multi-modal contrastive learning framework for spatial transcriptomics

conST learns embeddings from gene expression, spatial neighbors, and histology via three-level contrastive learning, reaching adjusted Rand index 0.65 on spatialLIBD slice 151673, with GNNExplainer-based explanations.

Knowledge graph analytics platform with LINCS and IDG for Parkinson's disease target illumination

The paper builds a knowledge graph analytics platform integrating LINCS and IDG to identify and prioritize novel drug targets for Parkinson's disease.

A graph-based framework for multi-scale modeling of physiological transport

The paper introduces a graph-based framework for modeling physiological transport across scales, validated with COMSOL simulations and applied to glucose dynamics in islet vasculature.

Graphic insights into the network basis for heat-gated TRPV1

The paper uses graph theory to model temperature-dependent non-covalent interactions in TRPV1, showing how grid-like networks maintain its structure and govern heat-sensing.

EEG-based Graph Neural Network Classification of Alzheimer's Disease: An Empirical Evaluation of Functional Connectivity Methods

This study evaluates graph neural networks for Alzheimer's disease classification using EEG-based functional connectivity measures, finding that GNNs outperform baselines but no single FC measure consistently dominates.

ProteinPrompt: a webserver for predicting protein-protein interactions

ProteinPrompt predicts protein-protein interactions using machine learning, offering two methods and consensus predictions for reliable results.

Protein Fold Classification using Graph Neural Network and Protein Topology Graph

This paper introduces a graph neural network approach for protein fold classification using protein topology graphs, achieving 82-100% accuracy on SCOPe and CATH datasets.

A graph-theoretical approach to DNA similarity analysis

This paper introduces a graph-theoretical method for DNA similarity analysis, showing comparable accuracy and efficiency across multiple viral and mammalian datasets.

ABCnet : Self-Attention based Atom, Bond Message Passing Network for Predicting Drug-Target Interaction

ABCnet predicts drug-target interactions using a self-attention-based graph model, showing improved performance in classification and comparable regression results to state-of-the-art methods.

Network-guided supervised learning on gene expression using a graph convolutional neural network

This paper introduces Grandline, a graph convolutional neural network that integrates gene expression and protein interaction networks to predict phenotypes with high accuracy and interpretability.