Quality Control: qc

Tools to filter cells and images based on quality control metrics and morphological profiles. For cells, unsupervised filtering is done using pyod through filter_outliers. For images, unsupervised filtering is done with qc_images_by_dissimilarity.

Note that performing unsupervised QC may remove underrepresented cell types or removes images with suitable quality and should therefore be tailored to your analysis needs.

filter_outliers(adata[, outliers, fraction, ...])	Filter outlier observations from an AnnData object.
qc_images_by_dissimilarity(adata, qcadata[, ...])	Perform QC of datasets using unsupervised, kNN-based distance filtering
count_cells_per_group(adata, group_keys[, ...])	Count number of cells per group.