New AI model reveals hidden code behind gene activation

Precise activation of tens of thousands of genes is critical for healthy development and growth. Specialized segments of our DNA are responsible for carefully orchestrating genetic sequences that result in the production of enzymes, hormones, proteins and other crucial components underlying cell structure and function. But if these genes are not correctly activated, cells can stop functioning or result in various disorders, including cancer.

To fully understand specific sequences within DNA that enable gene activation, researchers in University of California San Diego Professor James T. Kadonaga's laboratory set out to decipher an important segment of DNA known as the "initiator." This is the site at which the instructions coded in genes are first converted, or expressed, into functional products.

In the new study led by graduate student researcher Torrey Rhyne-Carrigg, scientists used high-throughput DNA sequencing technology to determine the gene expression activity of approximately 500,000 different versions of the initiator. With this information, they employed machine learning, a type of artificial intelligence, to create an AI model that then decoded the initiator's signature DNA pattern. With the initiator's DNA identity unmasked, the researchers could then search for its telltale sequence, finding that about 60% of human genes contain the initiator.