Epiphany: predicting Hi-C contact maps from 1D epigenomic signals

Abstract

Predicting chromatin contact maps from 1D epigenomic signals remains a challenging problem in computational biology. Here we present Epiphany, a deep learning method that predicts Hi-C contact maps from 1D epigenomic signals using a novel architecture that combines convolutional and attention mechanisms to capture both local and long-range interactions in chromatin organization.

Alireza Karbalayghareh

Senior Research Scientist

My research interests include AI/ML for biology, gene regulation, single-cell genomics, and using them to engineer immune system for effective cancer therapies.