Supervised and unsupervised deep learning-based approaches for studying DNA replication spatiotemporal dynamics

This project aimed to demonstrate how deep learning could be leveraged for studying DNA replication spatiotemporal dynamics. Through well-characterised cellular models, we showed in both supervised and unsupervised settings how convolutional neural networks could successfully identify aberrant DNA replication dynamics, while additionally reconstructing progression through S-phase. We make the associated image datasets available here. Please refer to README.txt for further information.