Germline and somatic mutations TCGA (GDC Data Portal)

Question

[stubbe1charlotte]

Hi everyone

I want to train a machine learning model to find somatic mutations in RNA data. For this I need clearly labeled somatic and germline mutations from WXS. I have access to the data on TCGA. Regarding somatic mutations: I think these are the PASS variants in the mutect2 vcf of WXS tumor-normal paired data, if I understand correctly. But I also need confidently called germline mutations, are these the PASS variants from the normal only sample?

Some help figuring this out would be really appreciated

Thanks in advance!

Kind regards Charlotte