Predicting Transcriptional Regulatory Activities with Deep Convolutional Networks
Joe Paggi, Andrew Lamb, Kevin Tian, Irving Hsu, Pierre-Louis Cedoz, Prasad Kawthekar
The paper trains a multitask convolutional neural network on MPRA data to predict transcriptional regulatory activity across cell types and promoters, finding that importance scores correlate with conservation and transcription factor binding.
bioRxiv · Jan 12, 2017 · PreprintGenomics