Scvi 1.4.0. model.differential_expression outputs

Help scvi-tools
1

Hello, I am using the scvi version 1.4.0.post1. The model.differential_expression function gives proba_m1, proba_m2, bayes_factor, scale1, scale2, raw_mean1, raw_mean2, non_zeros_proportion1, non_zeros_proportion2, raw_normalized_mean1, raw_normalized_mean2 as output without is_de_fdr_0.05 and lfc_mean columns. How can I filter the results? I have tried the following, which filtered out all of the genes. I appreciate any help, thanks!

scvi_de[‘lfc’] = np.log2((scvi_de[‘raw_mean1’] + 1e-6) / (scvi_de[‘raw_mean2’] + 1e-6)) scvi_de[‘proba_de’] = 1 - np.exp(-scvi_de[‘bayes_factor’])

scvi_de[‘pseudo_pval’] = 1 - scvi_de[‘proba_de’]

scvi_de[‘pseudo_fdr’] = multipletests(scvi_de[‘pseudo_pval’], method=‘fdr_bh’)[1]

2

You can run it with mode=“change” (default is “vanilla”), it will give you proba_de, lfc, etc and is_de_fdr_0.05, which is how we usually filter by.