Microsoft Suggests Artificial Intelligence is the Answer to Improving CRISPR
Although the prospect of being able to wipe out some of the worlds most devastating diseases would be revolutionary, gene editing technology CRISPR has a few problems to resolve first before it can do so.
Scientists have struggled to accurately target and alter the tiny fragment of genetic code that they have been trying to locate. As a result, this can actually make permanent changes to DNA that it was meant to leave alone. Depending on what those changes are, sometimes the patient can end up with new health problems, including cancer.
However, after a long wait, scientists at Microsoft believe that Artificial Intelligence (AI) is the way forward. Published in a paper in the journal Nature Biomedical Engineering, computer scientists and biologists from research institutions across the U.S., have developed a new tool known as Elevation, that predicts off-target effects when editing genes with the CRISPR.
How does it work I hear you asking? Well, if a scientist is planning to alter a specific gene, they enter its name into Elevation. The CRISPR system is made up of two parts, a protein that does the cutting and a synthetic guide RNA designed to match a DNA sequence in the gene they want to edit.
Different guides can have different off-target effects depending on how they are used. Elevation is able to suggest which guide is least likely to result in off-target effects for a particular gene, using machine learning to do so. In addition, it also provides general feedback on how likely off-target effects are for the gene being targeted. The platform bases its learning both on Microsoft research and publicly available data about how different genetic targets and guides interact.
MIcrosoft’s new tool will be welcomed by the industry, who have been plagued with debate over how problematic the off-target effects of CRISPR really are. Over the past year, Microsoft have doubled its efforts to use AI to attack healthcare problems.