Scientists have developed an AI-based computational model called a convolutional neural network that can design promoter sequences that drive gene expression at customized levels in yeast. The model can simulate millions of years of evolution in seconds to provide insights into the effect of changes in promoter sequences on gene expression. The study provides a mathematical framework for studying and designing gene regulatory DNA sequences to control gene expression using deep transformer neural networks, tensor processing units, and gigantic parallel reporter assays.
A recent study led by bioengineers at the University of Bristol shows how to simultaneously harnessing gene expression at the levels of both RNA and protein synthesis in living cells can more precisely regulate the switching on and off of genes, opening new avenues for improved biotechnologies.
Scientists have uncovered that the expression of many liver genes is dually regulated, spatially and temporally. The new study uses innovative statistical approaches to analyze RNA sequencing and smFISH data to reveal the expression patterns of 5,000 genes in individual liver cells across a 24-hour period and modeled how the circadian clock and liver functions crosstalk in sync with the feeding-fasting cycle.