sift.sifter

sift.sifter(adata, kernel_key=None, metric=KernelType.RBF, src_key=None, tgt_key=None, knn_key=None, batch_key=None, embedding_key=None, use_raw=False, pseudocount=False, key_added=None, copy=False, **kwargs)

Perform filtering, subtract the projection of the kernel from the expression.

Parameters:

• adata (AnnData) – Annotated data object.

• kernel_key (Optional[str]) – Key in anndata.AnnData where information for distance is stored.

• metric (Literal['precomputed', 'knn', 'mapping', 'rbf', 'laplacian']) – Metric to use.

• src_key (Optional[str]) – Mask for the source space of the kernel.

• tgt_key (Optional[str]) – Mask for the target space of the kernel.

• knn_key (Optional[str]) – Key in anndata.AnnData.obs for k-NN masking.

• batch_key (Optional[str]) – Key in anndata.AnnData.obs for batch masking.

• embedding_key (Optional[str]) – Key in anndata.AnnData.obsm for which to compute the projection on. If None, use anndata.AnnData.X.

• use_raw (Optional[bool]) – Whether to use anndata.AnnData.raw, if present.

• pseudocount (bool) – If True, add a pseudocount to filtered expression to avoid negative values.

• key_added (Optional[str]) – Key used when saving the result. If None, use '{embedding_key}_sift'. The result is saved to anndata.AnnData.X, anndata.AnnData.layers or anndata.AnnData.obsm, depending on the embedding_key.

• copy (bool) – Whether to modify adata inplace.

• kwargs (Any) – Additional keyword arguments [n_neighbors, precomputed_kernel].

Return type:

AnnData

Returns:

: The filtered data matrix.