Single-cell annotation skills with omicverse
CommunityAutomate single-cell type annotation.
Education & Research#LLM#AI#bioinformatics#cell type#single-cell annotation#omicverse#label transfer#ontology mapping
AuthorStarlitnightly
Version1.0.0
Installs0
System Documentation
What problem does it solves? Accurately annotating cell types in single-cell RNA-seq data is a critical but often manual and complex step. This Skill provides a comprehensive suite of automated and AI-powered annotation methods to streamline this process.
Core Features & Use Cases
- Automated Cluster Annotation: Utilize SCSA, MetaTiME, and GPTAnno for rapid, AI-driven cell type assignments.
- Consensus & Ontology Mapping: Achieve robust labels with CellVote consensus and align to ontologies using CellMatch.
- Label Transfer: Propagate annotations across different single-cell modalities using weighted KNN.
- Use Case: Annotate a complex single-cell dataset from a developing organ, combining multiple methods like SCSA for initial labels, CellMatch for ontology alignment, and CellVote for consensus, then transfer these labels to a related ATAC-seq dataset.
Quick Start
Run SCSA with CellMarker on my PBMC3k data, then use CellVote to get consensus labels, and finally map them to Cell Ontology terms.
Dependency Matrix
Required Modules
omicversescanpyanndatapandasnumpymatplotlibpertpyscvi-toolssentence-transformersopenaitorch
Components
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: Single-cell annotation skills with omicverse Download link: https://github.com/Starlitnightly/omicverse/archive/main.zip#single-cell-annotation-skills-with-omicverse Please download this .zip file, extract it, and install it in the .claude/skills/ directory.