Giovanni Visonà

This paper introduces DecoDen, a method that learns shared chromatin landscapes and de-noises histone modification assays across multiple tissues.

The paper introduces eDICE, a deep learning model for imputing epigenomic tracks, showing improved performance on reference data and successful application to individual-specific epigenomic patterns.

DecoDen removes shared biases in multi-histone ChIP-Seq data by learning a joint background signal and correcting for it using non-negative matrix factorisation and half-sibling regression.