check_consensus

Check if consensus is reached among models

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

check_consensus function

<dl><dt>round_responses</dt>
<dd>A vector of model responses to check for consensus</dd>
<dt>api_keys</dt>
<dd>A list of API keys for different providers</dd>
<dt>controversy_threshold</dt>
<dd>Threshold for consensus proportion (default: 2/3)</dd>
<dt>entropy_threshold</dt>
<dd>Threshold for entropy (default: 1.0)</dd>
<dt>consensus_check_model</dt>
<dd>Model to use for consensus checking (default: NULL, will try available models in order)</dd></dl>

Arguments

Check if consensus is reached among models — check_consensus

<dl>

<dt>round_responses</dt>
<dd>A vector of model responses to check for consensus</dd>


<dt>api_keys</dt>
<dd>A list of API keys for different providers</dd>


<dt>controversy_threshold</dt>
<dd>Threshold for consensus proportion (default: 2/3)</dd>


<dt>entropy_threshold</dt>
<dd>Threshold for entropy (default: 1.0)</dd>


<dt>consensus_check_model</dt>
<dd>Model to use for consensus checking (default: NULL, will try available models in order)</dd>

</dl>

check_consensus: Check if consensus is reached among models

Description

Usage

Arguments