TotalVI log normalization and non-negativity

Help scvi-tools
1

Hello,

I was wondering about two questions:

[1] Would that make sense to do log2 transformation on the denoised protein value (totalVI output)?

[2] It looks like the totalVI output denoised protein value are all non-negative, I wonder how this is guaranteed by the model?

Many thanks in advance,
Frank

2

yes as it’s on the scale of the original data (might need to add pseudocount)

The model uses transformations internally (exp or softplus) to guarantee non negativity

3

thanks so much for the prompt reply!

4

Hi Adam,

Would it make sense to further normalise the protein value by the ADT library size as well?

Regards,
Mikhael

5

ADT library size is tricky – if you’re using the same exact antibody panel in each dataset it might make sense.