One of the outputs of cellbender remove-background
is a PDF with "a ranked-ordered total UMI plot along with posterior cell probabilities."
tiny_10x_pbmc.pdf
: A PDF summary of the results showing (1) the evolution of the loss function during training, (2) a ranked-ordered total UMI plot along with posterior cell probabilities, and (3) a two-dimensional PCA scatter plot of the latent embedding of the expressions in cell-containing droplets. Notice the rapid drop in the cell probability after UMI rank ~ 500.
On the graph below, each index (droplet) is represented by a black dot showing UMI count and a red dot showing cell probability. What is indicated by the dotted line going up or down from each red dot?
I am not 100% sure but I think those are the prior probabilities of each droplet to contain a cell. At each iteration of the model (epoch) the red dots will move toward 1 or 0 (probability of a droplet to contain a cell or not) and the dashlines represent each trajectory of a specific red dot throughout the epochs.