Skip to content
DraconiticResearch
Search Sources API
188,932 studies31 sourcesUpdated 26 min ago
Peer-reviewedCC BYGenome biology

LLM-based cell type annotation harmonization across single-cell studies using GCTHarmony.

  • Xingyuan Zhang1,2
  • Zhicheng Ji3,4
4 affiliations
  1. 1Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC, USA.
  2. 2Computational Biology and Bioinformatics Program, Duke University School of Medicine, Durham, NC, USA.
  3. 3Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC, USA. [email protected].
  4. 4Computational Biology and Bioinformatics Program, Duke University School of Medicine, Durham, NC, USA. [email protected].
Read full textPDFDOICite

Abstract

A major challenge in integrating previously analyzed single-cell RNA-seq studies is the inconsistency of cell type annotations. To address this, we developed GCTHarmony, an LLM-based method for harmonizing cell type annotations across single-cell studies. Utilizing OpenAI's text embedding model, GCTHarmony accurately maps arbitrary cell type annotations to standardized cell ontology terms and reconciles discrepancies in annotation hierarchies across studies. In real data examples, we show that GCTHarmony substantially improves the consistency of cell type annotations across single-cell studies.

Related

  1. Single Molecule Diffusion Studies Reveal Rapid Translations Across Target Membrane Surfaces for both p40Phox PX domain and Class III PI3K VPS34 Complex 1, the Autophagy Lipid Kinase
    L. Lizardos, Y. Ohashi, A. M. McCombs +3
    bioRxivPreprintAll rights reservedFull textBiophysicsbioRxiv
  2. scBOA: Bayesian optimization of single-cell analysis pipelines for robust annotation and discovery
    Qiang Su, Yi Long, Fuyu Duan +1
    Nature CommunicationsPeer-reviewedCC BY-NC-ND 4.0Full textMolecular biology & gene regulationCrossref
  3. LipidOracle: Ambiguity-aware lipid annotation across fragmentation methods
    Vincen Wu, Abraham Moyal, Adriano Rutz +1
    ChemRxivPreprintCC BYFull textMolecular biology & gene regulationChemRxiv
  4. scGlycoAI: machine learning analysis of single-cell glycan and RNA sequencing data for cell-type annotation and malignancy-associated glycan discovery
    Dinh Xuan Tuan Anh, Hiroaki Tateno
    GlycobiologyPeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationPMC
  5. Annotation-aware multidomain validation of NucS and MutS-MutL across 23,435 prokaryotic reference genomes
    Kiarash Sadeghian Esfahani
    BMC GenomicsPeer-reviewedCC BY 4.0Molecular biology & gene regulationCrossref

Cite

BibTeXRIS
BibTeX
@article{zhang2026llmbased,
  title = {{LLM-based cell type annotation harmonization across single-cell studies using GCTHarmony.}},
  author = {Xingyuan Zhang and Zhicheng Ji},
  journal = {Genome biology},
  year = {2026},
  month = aug,
  doi = {10.1186/s13059-026-04231-7},
  url = {https://europepmc.org/article/MED/42958419},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - LLM-based cell type annotation harmonization across single-cell studies using GCTHarmony.
AU  - Xingyuan Zhang
AU  - Zhicheng Ji
PY  - 2026
DA  - 2026/08/04
JO  - Genome biology
DO  - 10.1186/s13059-026-04231-7
UR  - https://europepmc.org/article/MED/42958419
AB  - A major challenge in integrating previously analyzed single-cell RNA-seq studies is the inconsistency of cell type annotations. To address this, we developed GCTHarmony, an LLM-based method for harmonizing cell type annotations across single-cell studies. Utilizing OpenAI's text embedding model, GCTHarmony accurately maps arbitrary cell type annotations to standardized cell ontology terms and reconciles discrepancies in annotation hierarchies across studies. In real data examples, we show that GCTHarmony substantially improves the consistency of cell type annotations across single-cell studies.
SN  - 1474-7596
SN  - 1474-760X
ER  -