Deep learning for regulatory DNA design
2022
Chalmers University of Technology, Gothenburg, Sweden
The 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, the researchers prototype a deep learning strategy based on generative adversarial networks (GAN) by learning directly from genomic and transcriptomic data. The ExpressionGAN tool 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.
Controlling gene expression with deep generative design of regulatory DNA
Jan Zrimec, Aleksej Zelezniak
Added on: 12-16-2022
[1] https://www.nature.com/articles/s41467-022-32818-8[2] https://www.drugtargetreview.com/news/106850/the-future-of-drug-development-ai-tailors-artificial-dna/?utm_source=Email+marketing&utm_medium=email&utm_campaign=DTR+-+Newsletter+49+-+Metabolon+-+08.12.2022&utm_term=The+future+of+drug+development%3a+AI+tailors+artificial+DNA&utm_content=https%3a%2f%2femails.drugtargetreview.com%2frussellpublishinglz%2f&gator_td=uHQv3oL3RMur7rpz9cGWyHw3BuSYScaMU3AecOpOuuvyM3yMCcvT02nWulG0%2bgLo7FYbL%2bPthq89omlY0wdfzOVCw2s5fOpOem%2bGIngIJG3LDe68KfB%2fh5xOVy0%2fFIt97AtD%2fiaQaFtUedQ2fy%2fp%2fP2x2hn2C5BKGCuS%2bcnpF%2bn2zOLWq81jND7P5SlXvNJvOmg2GzQHTjtzM7GYNL0iQY5QPuaRWp5jhKgNF9ZY%2bV4%3d
