graph neural network

Learning Dynamic Protein Representations at Scale with Distograms

Adding Boltz2 distogram edges and features to protein and RNA graph networks beats MD-correlation graphs on binding tasks and improves stability, interaction and RNA predictions without simulation.

Reliable Evaluation of Transductive Population Graph Neural Networks for Multisite Autism fMRI

Site-aware population GNN on ABIDE-I: cohort AUC about 0.94 (kept with site-only edges) was not reproduced by a site-prior classifier (0.506); a directed-edge support gain (+0.252) vanished when symmetrised (−0.003).

Spanning-Tree Thermostatistics of Protein Allostery: An Exact Kirchhoff Framework with Application to Oncogenic KRAS

Kirchhoff matrix-tree evaluation of residue-contact spanning-tree ensembles yields exact allosteric thermodynamics; KRAS G12D conserves global and channel heat capacity but reroutes paths via Q61 and F156.

A pangenome-graph approach for mapping and imputing barley sequences

Pan20, a Practical Haplotype Graph of 20 barley genomes, assigns sequences MorexV3 coordinates and imputes genotyping-by-sequencing (GBS) reads at 0.06% base-call error versus 0.32% for variant calling.

CellAwareGNN: Single-Cell Enhanced Knowledge Graph Foundation Model for Drug Indication Prediction

Adding OneK1K immune cell-type expression edges to an updated PrimeKG modestly improved drug-indication link prediction, AUPRC 0.816 to 0.826 overall and 0.847 to 0.864 for 40 autoimmune diseases.

Modeling protein-small molecule conformational ensembles with PLACER

An atom-level graph neural network that denoises corrupted structures generates small-molecule and protein-ligand conformational ensembles, and its active-site pre-organization metric enriched for more active designed retroaldolases.

Peptide Design through Binding Interface Mimicry

PepMimic, an all-atom latent diffusion model guided by a contrastive interface encoder, designs peptides mimicking known binders; 8% of tested peptides across five targets reached 10^-8M KD.

Image-based spatial transcriptomics identifies molecular niche dysregulation associated with distal lung remodeling in pulmonary fibrosis

Xenium profiling of 343 genes in 1,126,820 nuclei from 19 human lungs maps fibrosis niches and orders alveolar remodeling from alveolar-capillary disruption to SPP1+ macrophage accumulation.

Caliban: Accurate cell tracking and lineage construction in live-cell imaging experiments with deep learning

Human-in-the-loop labeling of nuclear live-cell movies produced DynamicNuclearNet (over 2,621 divisions); Caliban, a tracker trained on it, beat four published trackers at division detection.

ADMET-AI: A machine learning ADMET platform for evaluation of large-scale chemical libraries

ADMET-AI, a Chemprop-RDKit graph neural network trained on 41 TDC datasets, has the best average leaderboard rank and scores one million molecules in 3.1 hours.

Automated model building and protein identification in cryo-EM maps

ModelAngelo combines convolutional and graph neural networks with protein language model embeddings and hidden Markov model searches to automate atomic model building and identify unknown proteins in cryo-EM maps.

Deep learning based kcat prediction enables improved enzyme constrained model reconstruction

A substrate graph neural network plus protein-sequence CNN predicts enzyme kcat (test Pearson r 0.71), tracks mutation effects, and parameterizes enzyme-constrained models for 343 yeast/fungi species.

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.

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.

GraphDTA: Predicting drug-target binding affinity with graph neural networks

Representing drugs as molecular graphs, GraphDTA lowers drug-target affinity prediction error to MSE 0.229 on Davis and 0.139 on Kiba versus deep learning baselines.

ProteinGCN: Protein model quality assessment using GraphConvolutional Networks

Graph convolutions on atom graphs with distance, orientation and bond edge features predict per-residue and global lDDT of protein models, outperforming VoroMQA and retrained Ornate while using about 100k parameters.

neuPrint: Analysis Tools for EM Connectomics

neo4j-based graph data model, web explorer and HTTP/Python API for EM connectomes; on an unpublished dataset with 10s of millions of synaptic elements, most queries finish under a second.