Predicting cell population-specific gene expression from genomic sequence

Zenodo (CERN European Organization for Nuclear Research)

Abstract

This repository contains all the pseudobulk expression values, trained models, and predictions from scEP. scEP is a deep learning framework that uses the genomic sequence as input to predict cell population-specific gene expression levels. The scEP GitHub can be used to reproduce all the figures from the paper, train your own models, look at the effect of variants, and do in-silico mutagenesis.

Authors 3

1. Lieke Michielsen Aachen

   Leiden University Medical Center

   Affiliation as printed

   Leiden University Medical Center

2. Marcel J. T. Reinders

   Delft University of Technology

   Affiliation as printed

   Delft University of Technology

3. Ahmed Essam Mahfouz Aachen

   Leiden University Medical Center

   Affiliation as printed

   Leiden University Medical Center