LLM-Assisted Functional Gene Annotation

2025/08/09 by C. A. P. Boyce, Clara Pereira, Gyeong Dae Kim +1 · 1 voice
Biochemistry, Genetics and Molecular Biology · #Bioinformatics and Genomic Networks #Gene expression and cancer classification #Machine Learning in Bioinformatics

paper · pdf · doi:10.1101/2025.08.06.668957

openalex publication_date 2025/08/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/14

Abstract

Abstract Functional gene annotation is a highly manual and subjective process that requires analysis of large amounts of statistical and literature results. Here we present Artificial Intelligence Gene Enrichment (AIGE), a careful automation of the current state of the art process used by bioinformatic experts to deter-mine functions enriched in novel or experimentally derived gene lists. In 1206 test cases, AIGE is able to accurately recover 87% of biological functions, path-ways, and cell types, is robust to noise contamination, and accurately assesses its own self-confidence. AIGE reports provide accurate functional annotations and encourage further research in a broad set of contexts.

Citations

• g:Profiler: a web server for functional enrichment analysis and conversions of gene lists (2019 update)
• The Gene Ontology knowledgebase in 2023
• The Reactome Pathway Knowledgebase 2024
• Large language model consensus substantially improves the cell type annotation accuracy for scRNA-seq data
• Comment on The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
• The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
• Reasoning Models Don't Always Say What They Think
• Single-Cell Omics Arena: A Benchmark Study for Large Language Models on Cell Type Annotation Using Single-Cell Data

Discussions

• KIPEs3: Automatic annotation of biosynthesis pathways doi.org/10.1101/2022... LLM-Assisted Functional Gene Annotation doi.org/10.1101/2025... #Genomics #Bioinformatics #Annotation [bsky, 1 points, 0 comments]

Related

• Annotation Enrichment Analysis: An Alternative Method for Evaluating the\n Functional Properties of Gene Sets
• Gene-R1: Reasoning with Data-Augmented Lightweight LLMs for Gene Set Analysis
• A New Deep Learning and XAI-Based Algorithm for Features Selection in Genomics
• Community-Wide Evaluation of Computational Function Prediction
• Does your model understand genes? A benchmark of gene properties for biological and text models