summarize_discussion

NOTE: This function is currently not in use. The consensus_annotation.R file
now directly extracts the majority_prediction from the last round of discussion.
This function is kept for potential future use or reference.

internal

Automated cell type annotation for single-cell RNA sequencing data
using consensus predictions from multiple large language models (LLMs). LLMs are
artificial intelligence models trained on vast text corpora to understand and
generate human-like text. This package integrates with 'Seurat' objects and
provides uncertainty quantification for annotations. Supports various LLM
providers including 'OpenAI', 'Anthropic', and 'Google'. The package leverages
these models through their respective APIs (Application Programming Interfaces)
<https://platform.openai.com/docs>, <https://docs.anthropic.com/>, and
<https://ai.google.dev/gemini-api/docs>.
For details see Yang et al. (2025) <doi:10.1101/2025.04.10.647852>.

Chen Yang

mLLMCelltype

Cell Type Annotation Using Large Language Models

summarize_discussion function

<dl><dt>discussion_log</dt>
<dd>Discussion log for a cluster</dd>
<dt>cluster_id</dt>
<dd>Cluster identifier</dd>
<dt>model</dt>
<dd>Model to use for summary</dd>
<dt>api_key</dt>
<dd>API key for the model</dd></dl>

Arguments

Summarize discussion and determine final cell type — summarize_discussion

<dl>

<dt>discussion_log</dt>
<dd>Discussion log for a cluster</dd>


<dt>cluster_id</dt>
<dd>Cluster identifier</dd>


<dt>model</dt>
<dd>Model to use for summary</dd>


<dt>api_key</dt>
<dd>API key for the model</dd>

</dl>

summarize_discussion: Summarize discussion and determine final cell type

Description

Usage

Value

Arguments