search

theislab / scCODA

A Bayesian model for compositional single-cell data analysis
BSD 3-Clause "New" or "Revised" License
141 stars 23 forks source link

mixed effect model #87

Closed t-a-m-i closed 1 month ago

t-a-m-i commented 7 months ago

Hi, I´m trying to implement scCODA for my scRNAseq data set of 6 different donors for which I have control and treatment data each. I´d like to see the effect of the treatment, but want to always compare control vs. treatment within each donor and handle the donors as random effects in a mixed effects model. However, I can´t seem to figure out how to adjust the formula. Any help appreciated!

johannesostner commented 7 months ago

Hi! Unfortunately, mixed effect models are not implemented for scCODA. Some alternatives would be to encode the donor info as a categorical variable or to do a donor-wise analysis, if that is an option for your study design