Summarizing a multipatient experimental design

Assume I have a dataset with cells from many patients. I want to create a space where each observation is the average of all the cells of a certain type in one patient (i.e., the number of observations will be the number of cell types X the number of patients).

What will be the most intuitive way to summarize the latent space for the new observations?

  1. Simply average the scVI latent space coordinates of all the cells in each observation to generate a latent coordinate for the observation?
  2. Same, but weight average by posterior probabilities of cells in the observation?
  3. Mode of posterior distribution over the cells in the observation?
  4. (other?)