Project home page here, tutorial notebook here.

Function docstrings

bbknn.bbknn(adata[, batch_key, use_rep, ...])

Batch balanced KNN, altering the KNN procedure to identify each cell's top neighbours in each batch separately instead of the entire cell pool with no accounting for batch.

bbknn.ridge_regression(adata, batch_key[, ...])

Perform ridge regression on scaled expression data, accepting both technical and biological categorical variables.

bbknn.matrix.bbknn(pca, batch_list[, ...])

Scanpy-independent BBKNN variant that runs on a PCA matrix and list of per-cell batch assignments instead of an AnnData object.