graph neural network

SpatialZoomer: multi-scale feature analysis of spatial transcriptomics

SpatialZoomer identifies disease progression signals and spatially heterogeneous niches in spatial transcriptomics data by analyzing features at multiple scales.

Performance and Robustness of Parameter Estimation from Phylogenetic Trees Using Neural Networks

This paper introduces a neural network ensemble method for estimating diversification parameters from phylogenetic trees, showing improved performance and robustness compared to maximum likelihood estimation.

Capturing the Mutational Dynamics of SARS-CoV-2 with Graphs

This paper introduces MLG, a graph-based framework for modeling SARS-CoV-2 mutation dynamics, showing its effectiveness in lineage classification and mutation prediction.

Hyperbolic Wavelet Interaction Network (HyWinNet): Multi-Scale Geometric Learning for Interpretable Protein-Protein Interaction Prediction

HyWinNet predicts protein-protein interactions by integrating hyperbolic geometry and wavelet transforms to model multi-scale biological networks, outperforming existing methods in recovering known interactions and predicting functional sites.

CASTER-DTA: Equivariant Graph Neural Networks for Predicting Drug-Target Affinity

CASTER-DTA predicts drug-target affinity using equivariant graph neural networks, achieving state-of-the-art performance and generating a resource of binding affinities for all FDA-approved drugs against the human proteome.

EXPRESSION GRAPH NETWORK FRAMEWORK FOR BIOMARKER DISCOVERY

The paper introduces EGNF, a graph-based framework for biomarker discovery that outperforms traditional methods in classification accuracy and interpretability across cancer datasets.

Unveiling causal regulatory mechanisms through cell-state parallax

The paper introduces GrID-Net, a graph neural network that detects causal locus-gene associations using cell-state parallax, uncovering noncoding mechanisms affecting 132 genes in schizophrenia.

Genetic regulation of cell type-specific chromatin accessibility shapes immune function and disease risk

The paper maps chromatin accessibility and genetic variation in immune cells, showing how integrating cell-type-specific data improves disease risk understanding.

Predicting Organ-Specific Toxicity of Selective Androgen Receptor Modulators, using Transfer Learning on Graph Convolutional Networks

This paper develops GCN-based QSAR models to predict toxicity of SARMs, finding mixed success with transfer learning and moderate accuracy in predicting DILI, DIRI, and DICT.

Enhancing Protein Binding Site Residue Prediction with Graph Neural Networks: Impacts of Cutoff Distance and Feature Selection

This study evaluates how cutoff distance and feature selection affect protein binding site residue prediction using graph neural networks across four eukaryotic organisms.

The Oviposition Inhibitory Neuron is a potential hub of multi-circuit integration in the Drosophila brain

The paper identifies the Oviposition Inhibitory Neuron as a hub in the Drosophila oviposition circuit by analyzing its inputs using network analysis and graph theory.

Energy-Regularized Graph Learning for Multiscale Spatial Representation

Glimmer improves spatial representation learning by adaptively learning graphs that balance molecular similarity and spatial proximity across scales, outperforming existing methods in clustering and spatial conservation.

GraphVelo allows for accurate inference of multimodal velocities and molecular mechanisms for single cells

GraphVelo extends RNA velocity inference to multimodal data by using graph-based machine learning to preserve vector information across different data representations.

AI-Based Comparative Transcriptomics and Gene Network Profiling of Staphylococcus aureus in Astronaut-Associated Missions

This study identifies conserved transcriptomic signatures and metabolic reprogramming in Staphylococcus aureus across spaceflight-associated conditions using comparative transcriptomics and gene network analysis.

STARNet enables spatially resolved inference of gene regulatory networks from spatial multi-omics data

STARNet infers gene regulatory networks from spatial multi-omics data, revealing domain-specific regulatory interactions in tissues.

SCRIPT: Predicting Single-cell Long-range Cis-regulation Based on Pretrained Graph Attention Networks

SCRIPT predicts single-cell cis-regulatory relationships using graph attention networks, achieving high accuracy and improving long-range prediction.

Graph Neural Networks for Likelihood-Free Inference in Diversification Models

This paper shows that graph neural networks with a new pooling method can accurately estimate diversification parameters in complex models where likelihoods are intractable.

Causality-aware graph neural networks for functional stratification and phenotype prediction at scale

The paper develops causality-aware graph neural networks to classify gene regulatory networks and predict phenotypes across cancer types and TP53 mutation states.

Deep Generative Models for Discrete Genotype Simulation

This study evaluates deep generative models for simulating discrete genotype data, showing their ability to capture genetic patterns and preserve genotype-phenotype associations.

PreMode predicts mode-of-action of missense variants by deep graph representation learning of protein sequence and structural context

PreMode predicts the mode-of-action of missense variants using graph neural networks, achieving state-of-the-art performance in mode-of-action classification.

Decoding stress specific transcriptional regulation by causality aware Graph-Transformer deep learning

The paper introduces CTF-BIND, a deep learning framework that detects TF binding from RNA-seq data without ChIP-seq, achieving 93% accuracy in plant stress response analysis.

Pangenomic context reveals the extent of intraspecific plant NLR evolution

The paper analyzes NLR gene diversity in Arabidopsis thaliana using pangenomic methods to show that multiple mutational processes contribute to NLR variation without a single metric capturing all diversity.

Hybrid protein-ligand binding residue prediction with protein language models: Does the structure matter?

This study evaluates a hybrid model combining protein language models and graph neural networks for predicting protein-ligand binding sites, showing that structural information improves performance but complex pLMs can achieve good results without it.

GeoGAT-site: A Face-Centered Geometric Graph Attention Network for Protein-Protein Interface Prediction

GeoGAT-site predicts protein-protein interaction sites using a geometric graph attention network, achieving high accuracy and efficiency compared to existing methods.

Hypergraph Neural Networks Reveal Spatial Domains from Single-cell Transcriptomics Data

This paper introduces hypergraph neural networks for spatial domain detection in single-cell transcriptomics, achieving high performance on a mouse brain dataset.

Deep Learning Prediction of Intact N-/O-Glycopeptide Tandem Mass Spectra Enhances Glycoproteomics

This study introduces DeepGPO, a deep learning framework that accurately predicts N- and O-glycopeptide MS/MS spectra, enhancing glycoproteomics analysis.

NetTCR-struc, a structure driven approach for prediction of TCR-pMHC interactions

The paper introduces NetTCR-struc, a GNN-based method to improve TCR-pMHC interaction modeling by enhancing docking quality scoring and structural model selection.

ATOMIC: A graph attention neural network for ATOpic dermatitis prediction on human gut MICrobiome

ATOMIC predicts atopic dermatitis using a graph attention network incorporating microbial co-expression networks and genomic data from gut microbiome samples.

MACGA: Multi-scale Adaptive Convolution with Graph Attention for LncRNA-Disease Association Prediction

MACGA predicts lncRNA-disease associations using a graph attention network with multi-scale adaptive convolution, outperforming existing methods in cross-validation and validated by case studies.

Mapping the Metalloproteome of Deinococcus indicus DR1 through Integrative Structure and Function Annotation

The paper maps the metalloproteome of Deinococcus indicus DR1 by integrating structural and functional annotations to identify proteins involved in heavy-metal tolerance.