Article

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

2026-01-13

Abstract excerpt

Graph Neural Networks (GNNs) in drug repurposing suffer from two limitations: transductive failure in zero-shot (cold-start) scenarios and popularity bias that misidentifies high-degree nodes as effective drugs. We propose a framework that shifts the optimization objective from graph topology to clinical utility, integrating Knowledge Graph RAG (KG-RAG), Supervised Fine-Tuning (SFT), and Kahneman-Tversky Optimizat...

Topics

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

Identifiers and source

Literature Corpus work: b3a12d0d-a69d-50de-8914-56679c85521a
DOI: 10.64898/2026.01.12.699148

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Overcoming Topology Bias and Cold-Start Limitations in Drug Repurposing: A Clinical-Outcome-Aligned LLM FrameworkDOI 10.64898/2026.01.12.699148Read

Language-Grounded Drug Representations for Cold-Start Drug–Drug Interaction PredictionSemantic proximity Read

DREAM-GNN: Dual-route embedding-aware graph neural networks for drug repositioningSemantic proximity Read

Graph Network-Based Analysis of Disease-Gene-Drug Associations: Zero-Shot Disease-Drug Prediction and Analysis StrategiesSemantic proximity Read

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

A Scalable Sign-Aware Multi-Omics Knowledge Graph Foundation Model for Mechanistic Drug Action and Clinical Response PredictionsSemantic proximity Read

Drug repurposing for rare diseases via a gene-bridged heterogeneous knowledge graph and graph attention networkSemantic proximity Read

BioScientist Agent: Designing LLM-Biomedical Agents with KG-Augmented RL Reasoning Modules for Drug Repurposing and Mechanistic of Action ElucidationSemantic proximity Read

Multi-layer guilt-by-association-based drug repurposing by integrating clinical knowledge on biological heterogeneous networksSemantic proximity Read

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

GALILEO Generatively Expands Chemical Space and Achieves One-Shot Identification of a Library of Novel, Specific, Next Generation Broad-Spectrum Antiviral Compounds at High Hit RatesSemantic proximity Read

Topology-Driven Negative Sampling Enhances Generalizability in Protein-Protein Interaction PredictionSemantic proximity Read

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