CZ CELLxGENE Discover Census

Description

CZ CELLxGENE Discover (cellxgene.cziscience.com) is a free-to-use platform for the exploration, analysis, and retrieval of single-cell data. CZ CELLxGENE Discover hosts the largest aggregation of standardized single-cell data from the major human and mouse tissues, with modalities that include gene expression, chromatin accessibility, DNA methylation, and spatial transcriptomics. This year, CZ CELLxGENE Discover has made available all of its human and mouse RNA single-cell data through Census (https://chanzuckerberg.github.io/cellxgene-census/) – a free-to-use service with an API and data that allows for querying its single-cell data corpus directly from Python or R. The API uses a new technology, TileDB-SOMA, that allows for efficient and low-latency querying. The data are fully standardized and hosted publicly for free access, and they are composed by a count matrix of tens of millions of cells (observations) by >60 k genes (features) accompanied by standard cell metadata variables (e.g. cell type, tissue, sequencing technology, donor id, etc) and gene metadata that includes GENCODE-based IDs and gene names. While these data are built from hundreds of datasets, the APIs enable convenient cell- and gene-based filtering to obtain any slice of interest in a matter of seconds. All data can be quickly transformed to NumPy, Pandas, Anndata, Seurat, or R base objects. We created data loaders for the data to be directly used by PyTorch for modeling at scale. In addition, all the source dataset files in H5AD format are also available for retrieval.

Update Frequency

New releases are published weekly. Long-term supported (LTS) releases are published every 6 months.

License

CC BY license

Documentation

https://chanzuckerberg.github.io/cellxgene-census/

Managed By

Chan Zuckerberg Initiative Foundation

See all datasets managed by Chan Zuckerberg Initiative Foundation.

Contact

cellxgene@chanzuckerberg.com

How to Cite

CZ CELLxGENE Discover Census was accessed on DATE from https://registry.opendata.aws/czi-cellxgene-census.

Usage Examples

Tutorials

• Computing on the cell by gene matrix using online (incremental) algorithms by CZI
  
  
• Experimental Highly Variable Genes API by CZI
  
  
• Exploring all data from a tissue by CZI
  
  
• Exploring pre-calculated summary cell counts by CZI
  
  
• Exploring the Census Datasets table by CZI
  
  
• Genes measured in each cell (dataset presence matrix) by CZI
  
  
• Integrating multi-dataset slices of data by CZI
  
  
• Learning about the CZ CELLxGENE Census by CZI
  
  
• Normalizing full-length gene sequencing data by CZI
  
  
• Out-of-core (incremental) mean and variance calculation by CZI
  
  
• Querying and fetching the single-cell data and cell/gene metadata. by CZI
  
  
• Querying data using the gget cellxgene module by CZI
  
  
• Summarizing cell and gene metadata by CZI
  
  
• Training a PyTorch Model by CZI
  
  
• Understanding and filtering out duplicate cells by CZI
  
  

Tools & Applications

• Census Python API by CZI
  
• Census R API by CZI
  

Publications

• CZ CELLxGENE Discover: A single-cell data platform for scalable exploration, analysis and modeling of aggregated data by CZI Single-Cell Biology et al.
  
• scGPT: Towards Building a Foundation Model for Single-Cell Multi-omics Using Generative AI. by Haotian Cui, et al.