Artificial intelligence could revolutionise the field of antibody medicines that activate the immune system to fight diseases like Parkinson's, Alzheimer's and colorectal cancer.
Until now, antibody medicines have faced the problem that they are less effective when they bind with the 'wrong' molecules – either other drug molecules or molecules that are not markers of disease.
But researchers at the University of Michigan designed AI algorithms that highlight problem areas on antibody medicines that may make them prone to this.
Professor Peter Tessier, author of the study published in Nature Biomedical Engineering, said: "We can use the models to pinpoint the positions in antibodies that are causing trouble and change those positions to correct the problem without causing new ones.
"The models are useful because they can be used on existing antibodies, brand new antibodies in development, and even antibodies that haven’t been made yet."
Antibodies fight disease by binding specific molecules called antigens on disease-causing agents – such as the spike protein on the virus that causes COVID-19.
Once bound, the antibody either directly inactivates the harmful viruses or cells or signals the body’s immune cells to do so.
Some antibodies are also prone to binding with other antibodies of the same type and, in the process, forming thick solutions that don't flow easily through the needles that deliver antibody drugs.
Tessier said: "The ideal antibodies should do three things at once: bind tightly to what they're supposed to, repel each other and ignore other things in the body."
Many clinical-stage antibodies can't do all of those three things.
In their study, Tessier's team measured the activity of 80 clinical-stage antibodies in the lab and found that 75% of the antibodies interacted with the wrong molecules, to one another, or both.
Changing the amino acids that comprise an antibody, and in turn the antibody's 3D structure, could prevent antibodies from misbehaving.
But some changes could cause more problems than they fix, and the average antibody has hundreds of different amino acid positions that could be changed.
Emily Makowski, a recent PhD graduate in pharmaceutical sciences and the study's lead author, said: "Exploring all the changes for a single antibody takes about two work days with our models, which is substantially shorter compared to experimentally measuring each modified antibody – which would take months, at best."
The team's models, which are trained on the experimental data they collected from clinical-stage antibodies, can identify how to change antibodies so they check all three boxes with 78% to 88% accuracy.
Watch: New drug shows promise against Alzheimer's