create_annotation_prompt

Create prompt for cell type annotation

Automated cell type annotation for single-cell RNA sequencing data
using consensus predictions from multiple large language models. Integrates
with Seurat objects and provides uncertainty quantification for annotations.
Supports various LLM providers including OpenAI, Anthropic, and Google.
For details see Yang et al. (2025) <doi:10.1101/2025.04.10.647852>.

Chen Yang

mLLMCelltype

Cell Type Annotation Using Large Language Models

create_annotation_prompt function

<dl><dt>input</dt>
<dd>Either a data frame from Seurat's FindAllMarkers() or a list for each cluster
where each element is either a character vector of genes or a list containing a <code>genes</code> field
Cluster IDs in named inputs are preserved as-is; unnamed list input receives sequential IDs starting at "0".</dd>
<dt>tissue_name</dt>
<dd>Tissue context for the annotation (e.g., 'human PBMC', 'mouse brain')</dd>
<dt>top_gene_count</dt>
<dd>Number of top genes to use per cluster when input is from Seurat. Default: 10</dd></dl>

Arguments

Create prompt for cell type annotation — create_annotation_prompt

<dl>

<dt>input</dt>
<dd>Either a data frame from Seurat's FindAllMarkers() or a list for each cluster
where each element is either a character vector of genes or a list containing a <code>genes</code> field
Cluster IDs in named inputs are preserved as-is; unnamed list input receives sequential IDs starting at "0".</dd>


<dt>tissue_name</dt>
<dd>Tissue context for the annotation (e.g., 'human PBMC', 'mouse brain')</dd>


<dt>top_gene_count</dt>
<dd>Number of top genes to use per cluster when input is from Seurat. Default: 10</dd>

</dl>

create_annotation_prompt: Create prompt for cell type annotation

Description

Usage

Value

Arguments