An ‘Oracle’ for Predicting the Evolution of Gene Regulation
Published:09 Mar.2022    Source:Massachusetts Institute of Technology Department of Biology

Computational biologists have created a neural network model capable of predicting how changes to non-coding DNA sequences in yeast affect gene expression. They also devised a unique way of representing this data in two dimensions, making it easy to understand the past and future evolution of non-coding sequences in organisms beyond yeast -- and even design custom gene expression patterns for gene therapies and industrial applications. 

Despite the sheer number of genes that each human cell contains, these so-called 'coding' DNA sequences comprise just 1% of our entire genome. The remaining 99% is made up of 'non-coding' DNA -- which, unlike coding DNA, does not carry the instructions to build proteins.