Assessing GPT-4 for cell type annotation in single-cell RNA-seq analysis
Open accessPublished version of a preprint
Abstract
Here we demonstrate that the large language model GPT-4 can accurately annotate cell types using marker gene information in single-cell RNA sequencing analysis. When evaluated across hundreds of tissue and cell types, GPT-4 generates cell type annotations exhibiting strong concordance with manual annotations. This capability can considerably reduce the effort and expertise required for cell type annotation. Additionally, we have developed an R software package GPTCelltype for GPT-4’s automated cell type annotation.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Text embeddings integrate omics data with various biological entities such as pathways, functional annotations and cell types, extending the model's capabilities beyond tissue alignment and decomposition, making it adaptable to a broader range of biological tasks.
“First, text embeddings integrate omics data with various biological entities such as pathways, functional annotations68 and cell types69, extending the model’s capabilities beyond tissue alignment and decomposition, making it adaptable to a broader range of biological tasks.”
From A visual–omics foundation model to bridge histopathology with spatial transcriptomics (2025) · cites this paper as [69]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 55 · Cited by 277
- Authors
- Hou, W., & Ji, Z.
- Affiliations
- Columbia University (US)
- Duke University (US)
- Corresponding author
- Hou, Wenpin
- Ji, Zhicheng
- Venue
- Nature Methods
- Published
- 2024-03-25
- Volume
- 21
- Issue
- 8
- Pages
- 1462-1465
- ISSN
- 1548-7091 (ISSN-L)
- 1548-7105
- PMC
- PMC11310073
- OpenAlex
- W4393153069
- Cited by
- 277
- References
- 55
- Citations by year
- 2026: 100 · 2025: 117 · 2024: 52 · 2023: 7
- FWCI
- 36.62
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Nature Methods (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc)
- Research Square (acceptedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (submittedVersion, cc-by-nc-nd)
- PubMed Central (submittedVersion, cc-by)
- Funders
- National institute of health
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Single-cell and spatial transcriptomics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Biophysics › Cell Image Analysis Techniques
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene expression and cancer classification
- Keywords
- GPT-4, large language models, cell type annotation, single-cell RNA sequencing, marker genes, automatic annotation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
