New treatments for Alzheimer’s disease are desperately needed, but numerous
clinical trials of investigational drugs have failed to generate promising
options. Now a team at Massachusetts General Hospital (MGH) and Harvard
Medical School (HMS) has developed an artificial intelligence–based method
to screen currently available medications as possible treatments for
Alzheimer’s disease. The method could represent a rapid and inexpensive way
to repurpose existing therapies into new treatments for this progressive,
debilitating neurodegenerative condition. Importantly, it could also help
reveal new, unexplored targets for therapy by pointing to mechanisms of drug
action.
“Repurposing FDA-approved drugs for Alzheimer’s disease is an attractive
idea that can help accelerate the arrival of effective treatment—but
unfortunately, even for previously approved drugs, clinical trials require
substantial resources, making it impossible to evaluate every drug in
patients with Alzheimer’s disease,” explains Artem Sokolov, PhD, director of
Informatics and Modeling at the Laboratory of Systems Pharmacology at HMS.
“We therefore built a framework for prioritizing drugs, helping clinical
studies to focus on the most promising ones.”
In an article published in Nature Communications, Sokolov and his colleagues
describe their framework, called DRIAD (Drug Repurposing In Alzheimer’s
Disease), which relies on machine learning—a branch of artificial
intelligence in which systems are “trained” on vast amounts of data, “learn”
to identify telltale patterns and augment researchers’ and clinicians’
decision-making.
DRIAD works by measuring what happens to human brain neural cells when
treated with a drug. The method then determines whether the changes induced
by a drug correlate with molecular markers of disease severity.
The approach also allowed the researchers to identify drugs that had
protective as well as damaging effects on brain cells.
“We also approximate the directionality of such correlations, helping to
identify and filter out neurotoxic drugs that accelerate neuronal death
instead of preventing it,” says co-first author Steve Rodriguez, PhD, an
investigator in the Department of Neurology at MGH and an instructor at HMS.
DRIAD also allows researchers to examine which proteins are targeted by the
most promising drugs and if there are common trends among the targets, an
approach designed by Clemens Hug, PhD, a research associate in the
Laboratory of Systems Pharmacology and a co-first author.
The team applied the screening method to 80 FDA-approved and clinically
tested drugs for a wide range of conditions. The analysis yielded a ranked
list of candidates, with several anti-inflammatory drugs used to treat
rheumatoid arthritis and blood cancers emerging as top contenders. These
drugs belong to a class of medications known as Janus kinase inhibitors. The
drugs work by blocking the action of inflammation-fueling Janus kinase
proteins, suspected to play a role in Alzheimer’s disease and known for
their role in autoimmune conditions. The team’s analyses also pointed to
other potential treatment targets for further investigation.
“We are excited to share these results with the academic and pharmaceutical
research communities. Our hope is that further validation by other
researchers will refine the prioritization of these drugs for clinical
investigation,” says Mark Albers, MD, PhD, the Frank Wilkins Jr. and Family
Endowed Scholar and associate director of the Massachusetts Center for
Alzheimer Therapeutic Science at MGH and a faculty member of the Laboratory
of Systems Pharmacology at HMS.
One of these drugs, baricitinib, will be investigated by Albers in a
clinical trial for patients with subjective cognitive complaints, mild
cognitive impairment, and Alzheimer’s disease that will be launching soon at
MGH in Boston and at Holy Cross Health in Fort Lauderdale, Florida. “In
addition, independent validation of the nominated drug targets could provide
new insights into the mechanisms behind Alzheimer’s disease and lead to
novel therapies,” says Albers.
Reference:
Steve Rodriguez, Clemens Hug, Petar Todorov, Nienke Moret, Sarah A. Boswell,
Kyle Evans, George Zhou, Nathan T. Johnson, Bradley T. Hyman, Peter K.
Sorger, Mark W. Albers, Artem Sokolov. Machine learning identifies
candidates for drug repurposing in Alzheimer’s disease. Nature
Communications, 2021; 12 (1) DOI:
10.1038/s41467-021-21330-0