DeepC: predicting 3D genome folding using megabase-scale transfer learning.

Schwessinger R., Gosden M., Downes D., Brown RC., Oudelaar AM., Telenius J., Teh YW., Lunter G., Hughes JR.

Predicting the impact of noncoding genetic variation requires interpreting it in the context of three-dimensional genome architecture. We have developed deepC, a transfer-learning-based deep neural network that accurately predicts genome folding from megabase-scale DNA sequence. DeepC predicts domain boundaries at high resolution, learns the sequence determinants of genome folding and predicts the impact of both large-scale structural and single base-pair variations.

DOI

10.1038/s41592-020-0960-3

Type

Journal article

Journal

Nat Methods

Publication Date

11/2020

Volume

17

Pages

1118 - 1124

Keywords

Base Sequence, CCCTC-Binding Factor, Chromatin, Computer Simulation, Genome, Human, Genomic Structural Variation, Genomics, Humans, Models, Genetic, Neural Networks, Computer

Permalink Original publication