ArticleNature methods2025
Evaluation of large language models for discovery of gene set function.
Article in Nature methods, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 57 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
57 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Transitioning from wet lab to artificial intelligence: a systematic review of AI predictors in CRISPR.Journal of translational medicine · 2025Pooled it
- MAPA: A Semantic Network Framework for Functional Module Discovery and Interpretation in Multi-Omics Data.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026Article
- GENIUS-LLM: An evidence-traceable, gene-centered multi-omics inference framework for plant gene function analysis.Plant communications · 2026Article
- From Cluster to Claim: Calibrating Interpretation in Single-Cell Transcriptomics.Advanced genetics (Hoboken, N.J.) · 2026Article
- Aberrant mucin expression and keratinization distinguishing severe from mild asthma revealed by interpretable machine learning.JCI insight · 2026Article
- Systematic detection of predictive gene sets by semantics-based selection.BMC bioinformatics · 2026Article
- Biotech's digital twin dilemma.Nature biotechnology · 2026Article
- Multimodal Integration of Protein Interactomes With Genomic and Molecular Data Discovers Distinct Rheumatoid Arthritis Endotypes.Arthritis & rheumatology (Hoboken, N.J.) · 2026Article
- Unveiling the comorbidity hub: WT1 drives renal cancer progression in chronic kidney disease and confers sirolimus vulnerability.Experimental and therapeutic medicine · 2026Article
- Tracing the rise of biomedical foundation models.Nature biotechnology · 2026Article
- GeneInsight: Condensing gene set knowledge via language models.PLoS computational biology · 2026Article
- High-Quality Predicted Metabolite-Pathway Annotations Expand Pathway Coverage and Increase Enriched Pathway Detection Across Metabolomics Datasets.Metabolites · 2026Article
- An embedding-based framework enables statistical testing of gene-set function hypotheses inferred by large language models.Nature communications · 2026Article
- Knowledge-guided contextual gene set analysis with large language models.Bioinformatics (Oxford, England) · 2026Article
- Review
- Emergence and evolution of protein-coding de novo genes.Nature reviews. Genetics · 2026Review
- Dissecting and directing pathology foundation models.bioRxiv : the preprint server for biology · 2026Article
- Brieflow: an integrated computational pipeline for high-throughput analysis of optical pooled screening data.Nature communications · 2026Article
- Lense: Optimizing data preprocessing in single-cell omics using LLMs.bioRxiv : the preprint server for biology · 2026Article
- Lense: optimizing data preprocessing in single-cell omics using large language models.Briefings in bioinformatics · 2026Article
Corrections and comments
- Update of
- Update of
Authors and funding
9 authors.
Funding
Abstract
Gene set enrichment is a mainstay of functional genomics, but it relies on gene function databases that are incomplete. Here we evaluate five large language models (LLMs) for their ability to discover the common functions represented by a gene set, supported by molecular rationale and a self-confidence assessment. For curated gene sets from Gene Ontology, GPT-4 suggests functions similar to the curated name in 73% of cases, with higher self-confidence predicting higher similarity. Conversely, random gene sets correctly yield zero confidence in 87% of cases. Other LLMs (GPT-3.5, Gemini Pro, Mixtral Instruct and Llama2 70b) vary in function recovery but are falsely confident for random sets. In gene clusters from omics data, GPT-4 identifies common functions for 45% of cases, fewer than functional enrichment but with higher specificity and gene coverage. Manual review of supporting rationale and citations finds these functions are largely verifiable. These results position LLMs as valuable omics assistants.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.