Controlling gene expression with deep generative design of regulatory DNA.

Autor: Zrimec J; Department of Biology and Biological Engineering, Chalmers University of Technology, Kemivägen 10, SE41296, Gothenburg, Sweden. jan.zrimec@nib.si.; Department of Biotechnology and Systems Biology, National Institute of Biology, Večna pot 111, SI1000, Ljubljana, Slovenia. jan.zrimec@nib.si., Fu X; Department of Biology and Biological Engineering, Chalmers University of Technology, Kemivägen 10, SE41296, Gothenburg, Sweden., Muhammad AS; Department of Computer Science and Engineering, Chalmers University of Technology, Rännvägen 6, SE41296, Gothenburg, Sweden., Skrekas C; Department of Biology and Biological Engineering, Chalmers University of Technology, Kemivägen 10, SE41296, Gothenburg, Sweden., Jauniskis V; Department of Biology and Biological Engineering, Chalmers University of Technology, Kemivägen 10, SE41296, Gothenburg, Sweden.; Biomatter Designs, Zirmunu st. 139A, LT09120, Vilnius, Lithuania., Speicher NK; Department of Computer Science and Engineering, Chalmers University of Technology, Rännvägen 6, SE41296, Gothenburg, Sweden., Börlin CS; Department of Biology and Biological Engineering, Chalmers University of Technology, Kemivägen 10, SE41296, Gothenburg, Sweden.; BioInnovation Institute, Ole Maaloes Vej 3, DK2200, Copenhagen N, Denmark., Verendel V; Department of Computer Science and Engineering, Chalmers University of Technology, Rännvägen 6, SE41296, Gothenburg, Sweden., Chehreghani MH; Department of Computer Science and Engineering, Chalmers University of Technology, Rännvägen 6, SE41296, Gothenburg, Sweden., Dubhashi D; Department of Computer Science and Engineering, Chalmers University of Technology, Rännvägen 6, SE41296, Gothenburg, Sweden., Siewers V; Department of Biology and Biological Engineering, Chalmers University of Technology, Kemivägen 10, SE41296, Gothenburg, Sweden., David F; Department of Biology and Biological Engineering, Chalmers University of Technology, Kemivägen 10, SE41296, Gothenburg, Sweden., Nielsen J; Department of Biology and Biological Engineering, Chalmers University of Technology, Kemivägen 10, SE41296, Gothenburg, Sweden.; BioInnovation Institute, Ole Maaloes Vej 3, DK2200, Copenhagen N, Denmark., Zelezniak A; Department of Biology and Biological Engineering, Chalmers University of Technology, Kemivägen 10, SE41296, Gothenburg, Sweden. aleksej.zelezniak@chalmers.se.; Institute of Biotechnology, Life Sciences Centre, Vilnius University, Sauletekio al. 7, LT10257, Vilnius, Lithuania. aleksej.zelezniak@chalmers.se.; Randall Centre for Cell & Molecular Biophysics, King's College London, New Hunt's House, Guy's Campus, SE1 1UL, London, UK. aleksej.zelezniak@chalmers.se.
Jazyk: angličtina
Zdroj: Nature communications [Nat Commun] 2022 Aug 30; Vol. 13 (1), pp. 5099. Date of Electronic Publication: 2022 Aug 30.
DOI: 10.1038/s41467-022-32818-8
Abstrakt: Design of de novo synthetic regulatory DNA is a promising avenue to control gene expression in biotechnology and medicine. Using mutagenesis typically requires screening sizable random DNA libraries, which limits the designs to span merely a short section of the promoter and restricts their control of gene expression. Here, we prototype a deep learning strategy based on generative adversarial networks (GAN) by learning directly from genomic and transcriptomic data. Our ExpressionGAN can traverse the entire regulatory sequence-expression landscape in a gene-specific manner, generating regulatory DNA with prespecified target mRNA levels spanning the whole gene regulatory structure including coding and adjacent non-coding regions. Despite high sequence divergence from natural DNA, in vivo measurements show that 57% of the highly-expressed synthetic sequences surpass the expression levels of highly-expressed natural controls. This demonstrates the applicability and relevance of deep generative design to expand our knowledge and control of gene expression regulation in any desired organism, condition or tissue.
(© 2022. The Author(s).)
Databáze: MEDLINE
Externí odkaz: