AI Model Decodes DNA 'Initiator' Sequence Present in About 60% of Human Genes

Precise activation of tens of thousands of genes is critical for healthy development and growth, and specialized segments of DNA orchestrate the genetic sequences that produce enzymes, hormones, proteins and other components underlying cell structure and function. When genes are not correctly activated, cells can stop functioning properly or contribute to disorders including cancer. Researchers in University of California San Diego Professor James T. Kadonaga's laboratory set out to decipher a key DNA segment known as the 'initiator,' the site where instructions coded in genes are first converted, or expressed, into functional products.

In the study, led by graduate student researcher Torrey Rhyne-Carrigg, the scientists used high-throughput DNA sequencing technology to measure the gene expression activity of approximately 500,000 different versions of the initiator. They then used machine learning, a type of artificial intelligence, to build an AI model that decoded the initiator's signature DNA pattern.

With the initiator's DNA identity unmasked, the researchers searched for its telltale sequence and found that about 60% of human genes contain it. 'These AI models were found to provide, for the first time, strong predictions of the presence or absence of the initiator in human genes and were thus able to decode the DNA base sequence pattern of the initiator,' said Kadonaga, a professor in UC San Diego's Department of Molecular Biology.

The newly uncovered information gives researchers the ability to predict the effects of DNA mutations that can lead to disorders tied to the initiator. The data and models from the study could also be used to design synthetic promoters, the sequences that turn genes on and off, with customised functions.

'Within the 6 billion bases of DNA in each of our cells, there is a gene expression code that specifies when, where and to what extent each of our genes should be turned on or off,' Kadonaga said. 'The new AI model for the initiator is a small but important part of this gene expression code.' The study, titled 'Machine learning analysis of the human initiator region reveals key features of different types of core promoters,' was published in the journal Genes and Development.