EAGLE-AI: A large language model workflow for automated extraction and scoring of literature evidence linking genes to autism spectrum disorder

We previously developed the Evaluation of Autism Gene Link Evidence (EAGLE) curation framework and usit to characterise 219 autism-associated genes. However, this took years of human work. We present EAGLE-AI, an automated curation system incorporating large language models (LLMs). On screened paper sets, it achieves F1 91% and scoring error 17.2%, near human performance. EAGLE-AI performs worse on unscreened papers due to table parsing and context overload, which we address using if-else scoring and computer vision tools. Handling of supplementary materials remains an unsolved problem. Our findings demonstrate proof-of-concept for automating most of a clinical genomics curation process.