Iratxe Zunzunegui Sanz
Research Subjects
Iratxe Zunzunegui Sanz has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Alejandro Rodríguez-González
Universidad Politécnica de Madrid
2 shared publications - Belén Otero-Carrasco
Universidad Politécnica de Madrid
2 shared publications
Latest Publications
- Open Access
Accelerating Drug Repurposing with AI: The Role of Large Language Models in Hypothesis Validation
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.
Open AccessAccelerating Drug Repurposing with AI: The Role of Large Language Models in Hypothesis Validation
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.
- 18 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 147-153
Accelerating Drug Repurposing with AI: The Role of Large Language Models in Hypothesis Validation
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.
- 18 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 147-153
Accelerating Drug Repurposing with AI: The Role of Large Language Models in Hypothesis Validation
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.