Format

Send to

Choose Destination
Nat Rev Genet. 2019 Apr 10. doi: 10.1038/s41576-019-0122-6. [Epub ahead of print]

Deep learning: new computational modelling techniques for genomics.

Author information

1
Institute of Computational Biology, Helmholtz Zentrum München, Neuherberg, Germany.
2
School of Life Sciences Weihenstephan, Technical University of Munich, Freising, Germany.
3
Department of Informatics, Technical University of Munich, Garching, Germany.
4
Department of Informatics, Technical University of Munich, Garching, Germany. gagneur@in.tum.de.
5
Institute of Computational Biology, Helmholtz Zentrum München, Neuherberg, Germany. fabian.theis@helmholtz-muenchen.de.
6
School of Life Sciences Weihenstephan, Technical University of Munich, Freising, Germany. fabian.theis@helmholtz-muenchen.de.
7
Department of Mathematics, Technical University of Munich, Garching, Germany. fabian.theis@helmholtz-muenchen.de.

Abstract

As a data-driven science, genomics largely utilizes machine learning to capture dependencies in data and derive novel biological hypotheses. However, the ability to extract new insights from the exponentially increasing volume of genomics data requires more expressive machine learning models. By effectively leveraging large data sets, deep learning has transformed fields such as computer vision and natural language processing. Now, it is becoming the method of choice for many genomics modelling tasks, including predicting the impact of genetic variation on gene regulatory mechanisms such as DNA accessibility and splicing.

PMID:
30971806
DOI:
10.1038/s41576-019-0122-6

Supplemental Content

Full text links

Icon for Nature Publishing Group
Loading ...
Support Center