mLLMCelltype

cafferychen777/mLLMCelltype is ranked 15,347 among these 8 peers; cassandre-tech/cassandre-trading-bot is ranked 15,348.

The framework integrates multiple large language models including OpenAI GPT-5. 5, and OpenRouter to improve annotation accuracy through consensus-based predictions. Abstract mLLMCelltype is an open-source tool for single-cell transcriptomics analysis that uses multiple large language models to identify cell types from gene expression data. The software implements a consensus approach where multiple models analyze the same data and their predictions are combined, which helps reduce errors and provides uncertainty metrics. This methodology offers advantages over single

-model approaches through integration of multiple model predictions. mLLMCelltype integrates with single-cell analysis platforms such as Scanpy and Seurat, allowing researchers to incorporate it into existing workflows. The method does not require reference datasets for annotation. The mLLMCelltype paper was published online in *Communications Biology* on June 8, 2026. Across 49 benchmark datasets (Yang et al. 2% mean accuracy, improving on the best single-LLM baseline (61. Table of Contents Key Features Repository Layout Installation Usage Examples Visualization Example

Citation Contributing **Web Application**: A browser-based interface is available at mllmcelltype. Repository Layout This repository is the single source of truth for the complete project: contains the maintained R package. contains the web application and deployment configuration. contains the published article's analysis code, manuscript sources, and the history-preserving public reproducibility workspace. Large paper datasets and generated results remain local under and and are excluded from Git. Historical package copies are intentionally not retained; the top-level packages are

authoritative. Key Features **Multi-LLM Consensus**: Integrates predictions from multiple LLMs to reduce single-model limitations and biases **Model Support**: Compatible with 10+ LLM providers including OpenAI, Anthropic, Google, and others **Iterative Discussion**: LLMs evaluate evidence and refine annotations through multiple rounds of discussion **Uncertainty Quantification**: Provides Consensus Proportion and Shannon Entropy metrics to identify uncertain annotations **Cross-Model Validation**: Reduces incorrect predictions through multi-model comparison **Noise Tolerance**: Maintains accuracy with imperfect marker gene lists **Hierarchical Annotation**: Supports multi

-resolution analysis with consistency checks **Reference-Free**: Performs annotation without pre-training or reference datasets **Documentation**: Records complete reasoning process for transparency **Integration**: Compatible with Scanpy/Seurat workflows and marker gene outputs **Extensibility**: Supports addition of new LLMs as they become available For changelog and updates, see NEWS. Installation R Version Python Version **Quick Start**: Try mLLMCelltype in Google Colab without any installation. Click the badge above to open an interactive notebook with examples and step-by-step guidance. Important

Note on Dependencies mLLMCelltype uses a modular design where different LLM provider libraries are optional dependencies. Depending on which models you plan to use, you'll need to install the corresponding packages: If you encounter errors like , it means you need to install the corresponding provider package. For example: Supported Models **OpenAI**: GPT-5. 4-mini (API Key) **Anthropic**: Claude-Opus-4. 1-Pro-Preview/Gemini-3-Flash-Preview/Gemini-3. 1-Flash-Lite (API Key) **Alibaba**: Qwen3. 6-Max-Preview

(API Key) **DeepSeek**: DeepSeek-V4-Flash/DeepSeek-V4-Pro (API Key) **Minimax**: MiniMax-M2. 7-highspeed (API Key) **Stepfun**: Step