Deep learning suggests that gene expression is encoded in all parts of a co-evolving interacting gene regulatory structure
Journal article, 2020

Understanding the genetic regulatory code governing gene expression is an important challenge in molecular biology. However, how individual coding and non-coding regions of the gene regulatory structure interact and contribute to mRNA expression levels remains unclear. Here we apply deep learning on over 20,000 mRNA datasets to examine the genetic regulatory code controlling mRNA abundance in 7 model organisms ranging from bacteria to Human. In all organisms, we can predict mRNA abundance directly from DNA sequence, with up to 82% of the variation of transcript levels encoded in the gene regulatory structure. By searching for DNA regulatory motifs across the gene regulatory structure, we discover that motif interactions could explain the whole dynamic range of mRNA levels. Co-evolution across coding and non-coding regions suggests that it is not single motifs or regions, but the entire gene regulatory structure and specific combination of regulatory elements that define gene expression levels.

Author

Jan Zrimec

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

Christoph Sebastian Börlin

Novo Nordisk Foundation Center for Biosustainability

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

Filip Buric

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

Muhammad Azam Sheikh

Chalmers, Computer Science and Engineering (Chalmers), CSE Verksamhetsstöd, Data Science Research Engineers

Rongzhen Chen

Chalmers, Computer Science and Engineering (Chalmers), CSE Verksamhetsstöd, Data Science Research Engineers

Verena Siewers

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

Vilhelm Verendel

Chalmers, Computer Science and Engineering (Chalmers), CSE Verksamhetsstöd, Data Science Research Engineers

Jens B Nielsen

Novo Nordisk Foundation Center for Biosustainability

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

Mats Töpel

University of Gothenburg

Gothenburg Global Biodiversity Centre

Aleksej Zelezniak

Science for Life Laboratory (SciLifeLab)

Chalmers, Biology and Biological Engineering, Systems and Synthetic Biology

Nature Communications

2041-1723 (ISSN)

Vol. 11 1 6141

Subject Categories

Evolutionary Biology

Bioinformatics and Systems Biology

Genetics

DOI

10.1038/s41467-020-19921-4

PubMed

33262328

More information

Latest update

12/10/2020