Making large language models reliable data science programming copilots for biomedical research.
other · Level V
Where this comes from
- Record sourced from PubMed, PMID 41571796.
- Also identified by DOI 10.1038/s41551-025-01587-2.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
Large language models (LLMs) can generate impressive data visualizations from simple requests, yet their accuracy remains underexplored. Here we present a benchmark of 293 coding tasks derived from 39 studies across 7 biomedical research areas, including biomarkers, integrative analysis, genomic profiling, molecular characterization, therapeutic response, translational research and pan-cancer analysis. Benchmarking eight proprietary and eight open-source LLMs under various prompting strategies reveals an overall accuracy below 40%. This low accuracy raises serious concerns about the risk of propagating incorrect scientific findings when blindly relying on AI-generated analyses. Therefore, we develop an AI agent that begins with and iteratively refines an analysis plan before generating code, achieving 74% accuracy. We embody this insight in a platform that enables users to codevelop analysis plans with LLMs and execute them within an integrated environment. In a user study with five medical researchers, the platform enabled users to complete over 80% of the analysis code for three studies.