graph neural network

DRUGSYNC: Prediction of Synergistic Drug Combinations Using GCN Graph Convolutional Network based and Pre-learned Drug-induced Gene Expression Profiles

DRUGSYNC predicts synergistic drug combinations using pre-learned gene expression profiles and a GCN model, achieving high accuracy for unseen drug pairs.

Drug Response Modeling across Cancers: Proteomics vs. Transcriptomics

This study compares proteomics and transcriptomics for drug response prediction in cancer cell lines, finding proteomics provides better performance.

Cell Type Differentiation Using Network Clustering Algorithms

This study compares clustering algorithms for cell type annotation in scRNA-seq data, finding that Infomap outperforms others in identifying cell types in PBMC and ROSMAP datasets.

MetaGXplore: Integrating Multi-Omics Data with Graph Convolutional Networks for Pan-cancer Patient Metastasis Identification

MetaGXplore uses graph convolutional networks to predict tumor metastasis likelihood and identify key genes across pan-cancer multi-omics data.

Tokenvizz: GraphRAG-Inspired Tokenization Tool for Genomic Data Discovery and Visualization

Tokenvizz is a tool that uses graph-based modeling and tokenization to improve genomic data discovery and visualization, outperforming traditional methods in promoter-enhancer interaction prediction.

Video tracking of single cells to identify clustering behaviour

This paper introduces a graph theory-based single-cell tracking method to identify clustering behavior in PC3 cells, finding that co-cultured cells form persistent clusters while monocultured cells do not.

CGMFinder Identifies Correlated Gene Modules from 3H scRNA-seq Data

CGMFinder identifies correlated gene modules from 3H scRNA-seq data, outperforming existing methods in detecting biologically relevant modules.

Knowledge Graph and Machine Learning Help the Research of Drugs Aimed at Neurological Diseases

This study introduces PATHOS, a knowledge graph, and LOGOS, a graph embedding model, to advance drug research for neurological diseases through three case studies.

Leveraging the Human Panproteome to Enhance Peptide and Protein Identification in Proteomics and Metaproteomics

This paper introduces a panproteome graph to enhance peptide and protein identification in proteomics and metaproteomics by leveraging the human pangenome.

GRNIX: A Graph Neural Network Framework for Explainable Gene Regulatory Network Inference in Autoimmune Diseases Using XAI

GRNIX infers gene regulatory networks in autoimmune diseases using a graph neural network framework with explainable AI to improve interpretability and predictive accuracy.

Inferring single-cell resolution spatial gene expression via fusing spot-based spatial transcriptomics, location and histology using GCN

This paper introduces scstGCN, a method that fuses histology, spatial transcriptomics, and spatial location data to infer single-cell resolution gene expression from spot-based spatial transcriptomics data.

Graph Contrastive Learning of Subcellular-resolution Spatial Transcriptomics Improves Cell Type Annotation and Reveals Critical Molecular Pathways

Focus improves cell type annotation by modeling subcellular RNA distribution in spatial transcriptomics data and identifies cell type-specific molecular pathways.

ProAffinity-GNN: A Novel Approach to Structure-based Protein-Protein Binding Affinity Prediction via a Curated Dataset and Graph Neural Networks

This paper introduces ProAffinity-GNN, a deep learning framework for predicting protein-protein binding affinities using graph neural networks and a curated dataset of protein complexes with experimentally determined affinities.

ICoN: Integration using Co-attention across Biological Networks

ICoN integrates multiple protein-protein association networks using co-attention and denoising to improve downstream tasks like gene module detection and protein function prediction.

Integration of molecular coarse-grained model into geometric representation learning framework for protein-protein complex property prediction

The paper introduces MCGLPPI, a geometric representation learning framework that combines graph neural networks with a molecular coarse-grained model to predict PPI properties efficiently.

AlloPool: An Adaptive Graph Neural Network for Dynamic Allosteric Network Prediction in Protein Systems

AlloPool predicts dynamic allosteric networks in proteins using a graph neural network, outperforming existing models in trajectory reconstruction.

A Variational Graph Partitioning Approach to Modeling Protein Liquid-liquid Phase Separation

This paper introduces a Graph Partitioned GNN (GP-GNN) to predict protein liquid-liquid phase separation by focusing on subgraphs containing intrinsically disordered regions.

Learning allosteric interactions in Gα proteins from molecular dynamics simulations

This study develops DMFormer, a Transformer-based graph neural network, to analyze Gα protein conformational dynamics, identifying Switch II as a critical motif for activation.

Generating Multi-state Conformations of P-type ATPases with a Diffusion Model

The paper introduces a diffusion model to generate diverse conformations of P-type ATPases, demonstrating high accuracy in capturing functional states.

Functionally Important Residues from Graph Analysis of Coevolved Dynamic couplings

This paper introduces DyNoPy, a method combining coevolution analysis and molecular dynamics to predict functionally important residues in proteins, demonstrating its application on beta-lactamases.

SpatialPPI 2.0: Enhancing Protein-Protein Interaction Prediction through Inter-Residue Analysis in Graph Attention Networks

SpatialPPI 2.0 predicts protein-protein interactions using graph neural networks and inter-residue analysis, outperforming existing methods and working with AlphaFold-predicted structures.

Estimating protein-ligand interactions with geometric deep learning and mixture density models

This paper develops a geometric deep learning method with mixture density models to predict protein-ligand binding conformations, showing improved performance over existing scoring functions.

Flowtigs: safety in flow decompositions for assembly graphs

This paper introduces flowtigs, a characterization of safe walks for flow decompositions in general graphs, and demonstrates their application to improve metagenomic assembly contiguity.

EuDockScore: euclidean graph neural networks for scoring protein-protein interfaces

This paper introduces EuDockScore, a scoring model for protein-protein interfaces using euclidean graph neural networks, and provides variants for antibody-antigen docking and re-ranking AlphaFold-Multimer outputs.

Knowledge Graphs and Explainable AI for Drug Repurposing on Rare Diseases

This paper introduces rd-explainer, a graph-based explainable AI method for drug repurposing in rare diseases, which provides interpretable predictions and explanations through semantic graphs.

Attentive graph neural network models for the prediction of blood-brain barrier permeability

This study benchmarks machine learning models for predicting blood-brain barrier permeability, showing attentive graph neural networks outperform traditional methods.

GrapHiC: An integrative graph based approach for imputing missing Hi-C reads

GrapHiC improves Hi-C read imputation by integrating Hi-C and ChIP-seq data in a graph framework, enhancing performance on sparse and cross-cell-type inputs.

Exploring the Efficiency of Deep Graph Neural Networks for RNA Secondary Structure Prediction

This study benchmarks graph neural networks for RNA secondary structure prediction, showing they outperform traditional energy-based methods.

Pair-EGRET: enhancing the prediction of protein-proteininteraction sites through graph attention networks and protein language models

Pair-EGRET predicts protein-protein interaction sites using graph attention networks and protein language models, outperforming existing methods on experimental data.

BRDKRM: An Explainable Framework for Disease Modifying Drug Identification

BRDKRM classifies drugs as disease-modifying or symptomatic using a graph-based framework, achieving 86.78% accuracy and identifying 530 genes involved in both categories.