Article

Topology-Driven Negative Sampling Enhances Generalizability in Protein-Protein Interaction Prediction

2024-04-29

Abstract excerpt

Unraveling the human interactome to uncover disease-specific patterns and discover drug targets hinges on accurate protein-protein interaction (PPI) predictions. However, challenges persist in machine learning (ML) models due to a scarcity of quality hard negative samples, shortcut learning, and limited generalizability to novel proteins. Here, we introduce a novel approach for strategic sampling of protein-protei...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 8eb4e075-f500-5007-b784-cb3c52cfde6a
DOI: 10.1101/2024.04.27.591478

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Topology-Driven Negative Sampling Enhances Generalizability in Protein-Protein Interaction PredictionDOI 10.1101/2024.04.27.591478Read

Effectiveness and efficiency: label-aware hierarchical subgraph learning for protein-protein interactionSemantic proximity Read

HGNNPIP: A Hybrid Graph Neural Network framework for Protein-protein Interaction PredictionSemantic proximity Read

Pitfalls of machine learning models for protein-protein interactionsSemantic proximity Read

DualNetGO: A Dual Network Model for Protein Function Prediction via Effective Feature SelectionSemantic proximity Read

Hierarchical Deep Learning Framework Integrating Structural Interaction Potentials and Evolutionary Information for Protein-Protein Interaction Affinity PredictionSemantic proximity Read

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

Protein-protein interaction prediction for targeted protein degradationSemantic proximity Read

Mutual interactors as a principle for phenotype discovery in molecular interaction networks.Semantic proximity Read

MORGaN: self-supervised multi-relational graph learning for drug target discoverySemantic proximity Read

Protein Interaction Network-based Deep Learning Framework for Identifying Disease-Associated Human ProteinsSemantic proximity Read

HPODNets: deep graph convolutional networks for predicting human protein-phenotype associations.Semantic proximity Read

LNGCN: a distance-aware continuous-time graph framework for PPI prioritization in experimental screeningSemantic proximity Read