ISIratxe Zunzunegui Sanz

Iratxe Zunzunegui Sanz

*This is an algorithmically generated author record based on publicly available information.

Iratxe Zunzunegui Sanz has a total of 2 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Accelerating Drug Repurposing with AI: The Role of Large Language Models in Hypothesis Validation

    by Iratxe Zunzunegui Sanz, Belén Otero-Carrasco, Alejandro Rodríguez-González

    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.


  • Accelerating Drug Repurposing with AI: The Role of Large Language Models in Hypothesis Validation

    by Iratxe Zunzunegui Sanz, Belen Otero-Carrasco, Alejandro Rodriguez-Gonzalez

    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-40, 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-40 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.