Organisms are built from thousands of different proteins, each of them encoded by a specific gene. For a cell type to acquire its unique identity, form, and function, it must activate genes through the activation of regulatory DNA sequences called enhancers. Scientists have long tried to crack the code by which enhancers operate. The labs of Alexander Stark at the IMP Vienna and Eileen Furlong at EMBL Heidelberg now harnessed genomics and artificial intelligence to solve this second “code of life”. Their findings were published in the journal Nature.

The scientists developed a powerful deep learning model that was trained on large datasets from the fruit fly Drosophila melanogaster, a model organism in developmental biology. Through transfer learning, the model predicted enhancer activity in various tissues of the fruit fly embryo. To validate their predictions, the researchers designed and tested 40 synthetic enhancers in living fruit fly embryos, which successfully drove gene expression in targeted tissues. This breakthrough has profound implications for synthetic biology and gene therapy, as it enables the precise design and manipulation of gene expression patterns.

Curious about the details behind the Science? Check out the IMP press release and De Almeida et al., Nature 2023!