Batch balanced KNN
BBKNN is a batch effect removal tool that can be directly used in the Scanpy workflow. It serves as an alternative to
scanpy.api.pp.neighbors(), with both functions creating a neighbour graph for subsequent use in clustering, pseudotime and UMAP visualisation. If technical artifacts are present in the data, they will make it challenging to link corresponding cell types across different batches. BBKNN actively combats this effect by splitting your data into batches and finding a smaller number of neighbours for each cell within each of the groups. This helps create connections between analogous cells in different batches without altering the counts or PCA space.
Identify inputs that should be native inputs
|'python-cython' should probably be a native input|