Python tutorials

API

• Computing on X using online (incremental) algorithms
  • Incremental count and mean calculation.
  • Incremental variance calculation
  • Counting cells per gene, grouped by dataset_id
• Genes measured in each cell (dataset presence matrix)
  • Opening the Census
  • Fetching the IDs of the Census datasets
  • Fetching the dataset presence matrix
  • Identifying genes measured in a specific dataset.
  • Identifying datasets that measured specific genes
  • Identifying all genes measured in a dataset
• Exploring the Census Datasets table
  • Fetching the datasets table
  • Fetching the expression data from a single dataset
  • Downloading the original source H5AD file of a dataset.
• Understanding and filtering out duplicate cells
  • Why are there duplicate cells in the Census?
  • An example: duplicate cells in the Tabula Muris Senis data
  • Filtering out duplicate cells
• Querying data using the gget cellxgene module
  • Install gget and set up cellxgene module
  • Fetch an AnnData object by selecting gene(s), tissue(s) and cell type(s)
  • Plot a dot plot similar to those shown on the CZ CELLxGENE Discover Gene Expression
  • Fetch only cell metadata (corresponds to AnnData.obs)
  • Use gget cellxgene from the command line
• Querying and fetching the single-cell data and cell/gene metadata.
  • Opening the census
  • Querying cell metadata (obs)
  • Querying gene metadata (var)
  • Querying expression data
• Exploring pre-calculated summary cell counts
  • Fetching the census_summary_cell_counts dataframe
  • Creating summary counts beyond pre-calculated values.

Analysis

• Learning about the CZ CELLxGENE Census
  • Opening the Census
  • Census organization
  • Cell metadata
  • Gene metadata
  • Census summary content tables
  • Understanding Census contents beyond the summary tables
• Integrating multi-dataset slices of data
  • Finding and fetching data from mouse liver (10X Genomics and Smart-Seq2)
  • Gene-length normalization of Smart-Seq2 data.
  • Integration with scvi-tools
• Exploring all data from a tissue
  • Learning about the lung data in the Census
  • Fetching all single-cell human lung data from the Census
  • Calculating QC metrics of the lung data
  • Creating a normalized expression layer and embeddings
• Normalizing full-length gene sequencing data
  • Opening the census
  • Fetching full-length example sequencing data (Smart-Seq)
  • Normalizing expression to account for gene length
  • Validation through clustering exploration
• Summarizing cell and gene metadata
  • Opening the Census
  • Summarizing cell metadata
  • Full Census metadata stats

Experimental

• Experimental Highly Variable Genes API
  • get_highly_variable_genes
  • highly_variable_genes
• Out-of-core (incremental) mean and variance calculation
  • The mean and variance API
  • Example: calculate mean and variance for a slice of the Census
• Training a PyTorch Model
  • Open the Census
  • Create a DataLoader
  • Define the model
  • Train the model
  • Make predictions with the model