Abstract
Drug repurposing accelerates drug discovery by identifying new therapeutic uses for existing drugs, but validating computational predictions remains a challenge. Large Language Models (LLMs) offer a potential solution by analyzing biomedical literature to assess drug-disease associations. This study evaluates four LLMs (GPT-4o, Claude-3, Gemini-2, and DeepSeek) using ten prompt strategies to validate repurposing hypotheses. The best-performing prompts and models were tested on 30 pathway-based cases and 10 benchmark cases. Results show that structured prompts enhance LLM accuracy, with GPT-4o and DeepSeek emerging as the most reliable models. Benchmark cases achieved significantly higher accuracy, precision, and F1-score (p < 0.001), while recall remained consistent across datasets. These findings highlight LLMs’ potential in drug repurposing validation while emphasizing the need for structured prompts and human oversight.
Funding Information
  • The work is a result of the project “Data-driven drug repositioning applying graph neural networks (3DR-GNN)” that is being developed under grant “PID2021-122659OB-I00” from the Spanish Ministry of Science and Innovation.

This publication has 16 references indexed in Scilit: