Hi,
I would like to compute p(z|c) from a trained scanvi model where z represents a latent state and c represents a cell-type. I know in the scanvi framework there is a learnable probability p(z|c,u) where u is just a latent cell-type specific state sampled from N(0,1), so I think based on that, computing p(z|c) is possible. Could you tell me which function I need to call to compute p(z|c,u) in scanvi?
Thanks!