Washington: With the help of AI, researchers at Sweden’s Chalmers University of Technology have succeeded in designing synthetic DNA that controls the protein production of cells. This technology could contribute to the development and production of vaccines, drugs for serious diseases as well as alternative food proteins much faster and at significantly lower cost than today.
How our genes are expressed is a process that is fundamental to the functionality of cells in all living organisms. Simply put, the genetic code in DNA is transcribed into nuclear messenger RNA (mRNA), which tells the cell’s factory which proteins to produce and in what quantities.
Researchers have put a lot of effort into trying to control gene expression because it can, among other things, contribute to the development of protein-based drugs. A recent example is the mRNA vaccine against Covid-19, which instructed the body’s cells to produce proteins similar to those found on the surface of the coronavirus. The body’s immune system can then learn to make antibodies against the virus. Likewise, it is possible to teach the body’s immune system to defeat cancer cells or other complex diseases if one understands the genetic code behind the production of certain proteins.
Most of today’s new drugs are protein-based, but the techniques to produce them are both expensive and slow, because it is difficult to control how DNA is expressed. Last year, a research group at Chalmers led by Aleksej Zelezniak, associate professor of systems biology, took an important step toward understanding and controlling how much protein is made from a specific DNA sequence.
“At first it was about being able to completely ‘read’ the instructions of a DNA molecule. Now we have succeeded in designing our own DNA that contains specific instructions to control the amount of specific proteins,” says Aleksej Zelezniak about the research group’s latest breakthrough. Progress
The principle behind the new method is the same as when AI creates faces that look like real people. By learning what a wide variety of faces look like, AI can create completely new but natural-looking faces. Then it’s easy to modify the face, for example, by saying it should be older, or have a different hairstyle. On the other hand, without using AI, programming a believable face from scratch would have been more difficult and time-consuming. Similarly, researchers’ AIs have been taught the structure and regulatory code of DNA. The AI then designs synthetic DNA, where its regulatory information is easy to modify in the desired direction of gene expression. Simply put, the AI is told how many genes are desired and then ‘prints’ the appropriate DNA sequence.
“DNA is an incredibly long and complex molecule. It’s very challenging experimentally to make changes to it by repeatedly reading it and changing it, then reading it and changing it again. It took years of research to figure out how it works. His Instead, it’s more efficient to let AI learn the principles of navigating DNA. What would otherwise take years is now shortened to weeks or days,” says first author Jan Zrimek, a research associate and past postdoc at the National Institute of Biology in Slovenia. The group of Aleksej Zelezniak.
The researchers developed their method in the yeast Saccharomyces cerevisiae, whose cells resemble mammalian cells. The next step is to use human cells. The researchers hope that their breakthrough will impact the development of new as well as existing drugs.
“Protein-based drugs for complex diseases or alternative sustainable food proteins can take many years and be extremely expensive to develop. Some are so expensive that it is impossible to get a return on investment, making them economically unviable. With our technology , it is possible to develop and produce that protein more efficiently so that it can be marketed,” says Aleksej Zelezniak.
