Queries and analyzes large-scale single-cell genomics data from the CZ CELLxGENE Census repository.
This skill provides Claude with specialized capabilities to interact with the CZ CELLxGENE Census, a massive collection of standardized single-cell genomics data covering over 61 million cells across human and mouse organisms. It enables researchers and bioinformaticians to efficiently filter data by cell type, tissue, or disease, retrieve gene expression matrices, and integrate findings into established workflows like Scanpy or PyTorch for machine learning. By providing standardized code patterns for out-of-core processing and reproducible versioning, it simplifies complex population-scale biological analyses directly within the development environment.
主要功能
01Access to pre-calculated embeddings and raw expression matrices
02Filter by cell type, tissue, disease, and donor metadata
03Query 61M+ standardized single-cell genomics records
040 GitHub stars
05Support for out-of-core processing of massive datasets
06Seamless integration with Scanpy and PyTorch frameworks
使用场景
01Exploring gene expression patterns across different cell types and developmental stages
02Performing cross-dataset integration for specific diseases or tissues
03Training machine learning models on population-scale single-cell data
