MétaCan
Menu
Back to cohort
Record W4414598938 · doi:10.1101/2025.09.10.25334730

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

2025· preprint· en· W4414598938 on OpenAlexafffund
Vinícius Furlan, Julian Moran, Nelson Bautista Salazar, Olivia Rennie, Ny Hoang, Marla Mendes de Aquino, Worrawat Engchuan, Jacob Vorstman, Stephen W. Scherer

Bibliographic record

VenuemedRxiv · 2025
Typepreprint
Languageen
FieldBiochemistry, Genetics and Molecular Biology
TopicBiomedical Text Mining and Ontologies
Canadian institutionsUniversity of TorontoSickKids FoundationHospital for Sick Children
FundersUniversity of TorontoHospital for Sick ChildrenAutism Speaks
KeywordsWorkflowAutismAutism spectrum disorderSet (abstract data type)Data curationComponent (thermodynamics)Data setGenomics

Abstract

fetched live from OpenAlex

We previously developed the Evaluation of Autism Gene Link Evidence (EAGLE) curation framework and used it 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.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.619
Threshold uncertainty score0.861

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.001
Research integrity0.0010.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.021
GPT teacher head0.339
Teacher spread0.318 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes2
Has abstractyes

Explore more

Same venuemedRxivSame topicBiomedical Text Mining and OntologiesFrench-language works237,207