ReCellTy: Domain-specific knowledge graph retrieval-augmented LLMs workflow for single-cell annotation

2025/04/24 by Han, Dezheng, Jia, Yibin, Chen, Ruxiao +3
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Databases (cs.DB) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2505.00017

Abstract

To enable precise and fully automated cell type annotation with large language models (LLMs), we developed a graph structured feature marker database to retrieve entities linked to differential genes for cell reconstruction. We further designed a multi task workflow to optimize the annotation process. Compared to general purpose LLMs, our method improves human evaluation scores by up to 0.21 and semantic similarity by 6.1% across 11 tissue types, while more closely aligning with the cognitive logic of manual annotation.

Citations

• MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot
• KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosis
• Learning the rules of peptide self-assembly through data mining with large language models
• Cell2Sentence: Teaching Large Language Models the Language of Biology
• Objectively Evaluating the Reliability of Cell Type Annotation Using LLM-Based Strategies
• Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation
• From Local to Global: A Graph RAG Approach to Query-Focused Summarization
• Fine-tuning Large Language Models for Domain-specific Machine Translation
• Seven Failure Points When Engineering a Retrieval Augmented Generation System
• An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
• Sparks of Artificial General Intelligence: Early experiments with GPT-4
• CellMarker 2.0: an updated database of manually curated cell markers in human/mouse and web tools based on scRNA-seq data
• Language Models are Few-Shot Learners
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Putative cell type discovery from single-cell gene expression data
• Eleven grand challenges in single-cell data science
• The Human Cell Atlas White Paper
• Attention Is All You Need
• The human genome project: big science transforms biology and medicine

Related

• Miiyuu/scAgent: Universal Cell Type Annotation via a LLM
• Benchmarking Cell Type and Gene Set Annotation by Large Language Models with AnnDictionary
• CellMaster: Collaborative Cell Type Annotation in Single-Cell Analysis
• Single-Cell Omics Arena: A Benchmark Study for Large Language Models on Cell Type Annotation Using Single-Cell Data
• BRAINCELL-AID: An Agentic AI Created Brain Cell Type Resource for Community Annotation