CellAgent
---name: cell_agent description: LLM-driven multi-agent framework for automated single-cell analysis. keywords:
SKILL.md
Full skill instructions
"
CellAgent
CellAgent is a multi-agent system capable of autonomously handling the entire single-cell RNA-seq (scRNA-seq) analysis pipeline. It simulates a team of biological experts to process data, annotate cells, and perform downstream analysis.
When to Use This Skill
- Automated Annotation: When you have raw scRNA-seq data and need cell type labels without manual curation.
- Complex Workflows: For multi-step analysis (QC -> Clustering -> Annotation -> DE Analysis).
- Data Integration: When merging multiple datasets (e.g., from different batches).
Core Capabilities
- Planning: Decomposes analysis goals into executable steps.
- Tool Execution: Generates and runs Python code for Scanpy/Seurat.
- Self-Correction: detects errors in execution and attempts to fix them.
Workflow
- Input: User query + scRNA-seq data (H5AD).
- Planner: The Planning Agent breaks the task into sub-tasks.
- Executor: The Coding Agent writes scripts to execute the plan.
- Reviewer: Checks the results and logs outputs.
Example Usage
User: "Process this dataset, filter low-quality cells, and annotate clusters."
Agent Action:
# Assuming a wrapper exists or running the main module from the repo
python3 Skills/Genomics/Single_Cell/CellAgent/repo/main.py --data "./data.h5ad" --goal "annotate"
References
- Mao et al., 2025
- arXiv 2407.09811