Processed datasets for epiVIP: paired immunopeptidome and transcriptome training and test datasets

This repository contains the processed training and test datasets used to develop and evaluate epiVIP, a transformer-based model for predicting HLA-I peptide abundance. Included files contain: Cohort-level summaries Processed MHC-I peptide sequences Matched RNA-seq TPM expression matrices Controlled-access transcriptome datasets are not included.