Article

Language-Grounded Drug Representations for Cold-Start Drug–Drug Interaction Prediction

2026-07-14

Abstract excerpt

<title>Abstract</title> <p>Computational prediction of drug–drug interactions (DDIs) is an important tool for clinical safety, and graph neural networks have become the dominant approach. However, most methods are evaluated transductively: every drug is already embedded in the training interaction graph. This obscures the clinically critical cold-start case, in which a newly approved drug has no recorded interact...

Topics

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

Identifiers and source

Literature Corpus work: 3d2e273c-de26-515f-8307-b93d94f1ad54
DOI: 10.21203/rs.3.rs-10334947/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Language-Grounded Drug Representations for Cold-Start Drug–Drug Interaction PredictionDOI 10.21203/rs.3.rs-10334947/v1Read

BEACON: predicting side effects and therapeutics outcomes to drugs by Bridging knowlEdge grAph with CONtextual language modelSemantic proximity Read

Overcoming Topology Bias and Cold-Start Limitations in Drug Repurposing: A Clinical-Outcome-Aligned LLM FrameworkSemantic proximity Read

ChemBERTaDDI: Transformer Driven Molecular Structures and Clinical Data for predicting drug-drug interactionsSemantic proximity Read

From General-Purpose to Disease-Specific Features: Aligning LLM Embeddings on a Disease-Specific Biomedical Knowledge Graph for Drug RepurposingSemantic proximity Read

Network-principled deep generative models for designing drug combinations as graph setsSemantic proximity Read

MultiGML: Multimodal Graph Machine Learning for Prediction of Adverse Drug EventsSemantic proximity Read

A transformer model explaining mechanisms of drug therapeutic and adverse effectsSemantic proximity Read

A Fused Deep Learning Approach to Transform Novel Drug RepositioningSemantic proximity Read

NetMedGPT - A network medicine foundation model for extensive disease mechanism mining and drug repurposingSemantic proximity Read

<i>MedGraphNet</i> : Leveraging Multi-Relational Graph Neural Networks and Text Knowledge for Biomedical PredictionsSemantic proximity Read

SCREP: Towards Single-Cell Drug Response Prediction by Pharmacogenomic Embedding Enhanced Meta-Pretraining and Few-Shot Transfer LearningSemantic proximity Read

Deep Learning-Based Drug Repurposing Using Knowledge Graph Embeddings and GraphRAGSemantic proximity Read