Histone modifications play an important role in affecting gene regulation. Specific histone modifications at specific locations in or near the gene can alter the expression of genes. Predicting gene expression from histone modification signals is a widely studied research topic.

In this competition you will predict gene expression levels (low=0, high=1) based on the presence of histone modifications at specific locations in the gene. You will try to find the model that learns the true underlying model best.

For each gene a region of 10.000bp around the transcription start site of the gene is extracted (5000bp upstream and 5000bp downstream). This region is binned in 100 bins of 100bp. For each bin five core histone modification marks are counted [1].

The dataset is compiled from the "E047" (Primary T CD8+ naive cells from peripheral blood) celltype from Roadmap Epigenomics Mapping Consortium (REMC) database.

[1] Kundaje, A. et al. Integrative analysis of 111 reference human epige-
nomes. Nature, 518, 317–330, 2015.