Cell.Classify: Classification of cells using similarity scores

In JSB-UCLA/scDED: Single-cell Dubious Embedding Detector

Classification of cells using similarity scores

Description

This function classifies the cell embeddings as dubious, trustworthy, or intermediate. It uses the cell similarity scores calculated on permuted data (rho_permuted) to classify the cell similarity scores calculated on the original data (rho_original). The classifications are based on the dubious_cutoff and trustworthy cutoff.

Usage

Cell.Classify(rho_original, rho_permuted, dubious_cutoff = 0.05, trustworthy_cutoff = 0.95)

Arguments

rho_original	A vector containing the similarity scores calculated on the original data
rho_permuted	A vector containing the similarity scores calculated on the permuted data
dubious_cutoff	The cutoff for dubious cells (default = 0.05). Cells with scores worse (lower) than the dubious_cutoff percentile of null scores will be considered dubious. A lower dubious_cutoff means that to be considered dubious, cells will have to have lower scores. A higher dubious_cutoff means that cells can score higher and still be considered dubious. It is similar to significance level in hypothesis testing.
trustworthy_cutoff	The cutoff for trustworthy cells (default = 0.95). Cells with scores better (higher) than the trustworthy_cutoff percentile of null scores will be considered trustworthy. A lower trustworthy_cutoff means that to be considered trustworthy, cells will not have to score as high. A higher trustworthy_cutoff means that cells will need to score higher in order to be considered trustworthy. It is similar to significance level in hypothesis testing.
similarity_percent	The percentage of cells to consider in the similarity score calculations (default = 0.5). scDEED uses the nearest floor(number of cells * similarity_percent) neighbors in the similarity percent calculations. Intuitively, a higher similarity score considers more cells as neighbors (emphasis on global preservation) while a lower similarity score considers less (emphasis on local preservation)

Value

Returns a list with three vectors, (1) 'dubious_cells': the cell embeddings with dubious classification, as determined by the dubious_cutoff on the null data (2) 'trustworthy_cells': the cell embeddings with trustworthy classification, as determined by the trustworthy_cutoff on the null data (3) 'intermediate_cells': the cells with intermediate classification, as determined by the dubious_cutoff and trustworthy_cutoff on the null data

JSB-UCLA/scDED documentation built on Feb. 8, 2025, 11:12 a.m.