Application of large language models to the annotation of cell lines and mouse strains in genomics data

Accurate, consistent and comprehensive metadata are essential for the reuse of functional genomics data deposited in repositories such as the Gene Expression Omnibus (GEO), however, achieving this often requires careful manual curation that is time-consuming, costly and prone to errors. In this paper, we evaluate the performance of Large Language Models (LLMs), specifically OpenAI's GPT-4o, as an assistive tool for entity-to-ontology annotation of two commonly encountered descriptors in transcriptomic experiments - mouse strains and cell lines. Using over 9,000 manually curated experiments from the Gemma database and over 5,000 associated journal articles, we assess the model's ability to identify relevant free-text entries and map them to appropriate ontology terms. Using zero-shot prompting and retrieval-augmented generation (RAG) to incorporate domain-specific ontology knowledge, GPT-4o correctly annotated 77% of mouse strain and 59% of cell line experiments, and uncovered manual curation errors in Gemma for over 200 experiments. GPT-4o substantially outperformed a regular expression-based string-matching method, which correctly annotated only 6% of mouse strain experiments due to low precision. Model errors often arose from typographical mistakes or inconsistent naming in the GEO record or publication, and resembled those made by human curators. Along with annotations, our approach requests that the model output supporting context and quotes from the sources. These were typically accurate and enabled rapid curator verification. These findings suggest that LLMs are not ready to fully replace manual curators, but can already effectively support them. A human-in-the-loop workflow, in which LLM's annotations are provided to human curators for validation, may improve the efficiency and quality of large-scale biomedical metadata curation.