Designer genes courtesy of artificial intelligence

The core promoter determines not only where gene transcription initiates but also the transcriptional activity in both basal and enhancer-induced conditions. Multiple short sequence elements within the core promoter have been identified in different species, but how they function together and to what extent they are truly species-specific has remained unclear. In this issue of Genes & Development, Vo ngoc and colleagues ( pp. 377-382) report undertaking massively parallel measurements of synthetic core promoters to generate a large data set of their activities that informs a statistical learning model to identify the sequence differences of human and Drosophila core promoters. This machine learning model was then applied to design gene core promoters that are particularly specific for the human transcriptional machinery.

Automated summary

The study focuses on understanding the function and species-specificity of short sequence elements in the core promoter that determine gene transcription activity. Through massively parallel measurements of synthetic core promoters, a statistical learning model was developed to identify the sequence differences between human and Drosophila core promoters. This model was then used to design gene core promoters that are specifically recognized by the human transcriptional machinery.