Image by Getty / Futurism
Gene editing has made huge leaps in recent years, such as treating the congenital blood disorders sickle cell anemia and beta thalassemia, which can require lifelong blood transfusions. But scientists still fear that some snipping may lead to unwelcome surprises.
However, a research team led by the University of Zurich says that artificial intelligence could help.
A new study published in the journal Nature details how the researchers combined AI and the gene editing technique CRISPR-Cas for more precise editing, which may lead to better gene therapies for patients and fewer side effects.
They did this by developing a new AI tool called Pythia, named after the ancient oracle at the Temple of Apollo, which can predict how cells will repair a portion of DNA post-gene editing.
“DNA repair follows patterns; it’s not random,” said lead author and University of Zurich biotechnology researcher Thomas Naert in a statement about the study. “We were able to model on a large scale that this DNA repair process obeys consistent rules that AI can learn and predict.”
To test out the efficacy of Pythia, the scientists developed what they called “DNA repair templates” based on Pythia’s predictions.
“Our team has developed tiny DNA repair templates that act like molecular glue, guiding the cell to make precise genetic changes,” said Naert.
They were successful in making precise repairs on human cell cultures and then on lab mice and small frogs, which are often used for science experiments.
Scientists observed the altered cells that were subjected to a DNA repair template and saw that edits didn’t negatively impact the process of cell division or the subsequent functions within the cells.
Their experiments with Pythia could enable scientists to precisely change a few letters or insert strings of genetic code into their correct location, while also having the ability to work with cells that don’t divide or replicate like mature brain cells.
Besides more accurate gene editing, Pythia could also allow researchers to precisely tag genes that make certain proteins with fluorescent labels that glow under microscopic observation.
“This allows us to directly observe what individual proteins do in healthy and diseased tissue,” said Naert.
The scientists are hopeful that others could make use of their AI model, potentially inspiring more treatments for intractable diseases caused by faulty genes.
More on AI and medicine: Man Follows ChatGPT’s Advice and Poisons Himself