(Press-News.org) Small molecules called immunomodulators can help create more effective vaccines and stronger immunotherapies to treat cancer.
But finding the molecules that instigate the right immune response is difficult —the number of drug-like small molecules has been estimated to be 1060, much higher than the number of stars in the visible universe.
In a potential first for the field of vaccine design, machine learning guided the discovery of new immune pathway-enhancing molecules and found one particular small molecule that could outperform the best immunomodulators on the market. The results are published in the journal Chemical Science.
“We used artificial intelligence methods to guide a search of a huge chemical space,” said Prof. Aaron Esser-Kahn, co-author of the paper who led the experiments. “In doing so, we found molecules with record-level performance that no human would have suggested we try. We’re excited to share the blueprint for this process.”
“Machine learning is used heavily in drug design, but it doesn’t appear to have been previously used in this manner for immunomodulator discovery,” said Prof. Andrew Ferguson, who led the machine learning. “It’s a nice example of transferring tools from one field to another.”
Machine learning to screen molecules
Immunomodulators work by changing the signaling activity of innate immune pathways within the body. In particular, the NF-κB pathway plays a role in inflammation and immune activation, while the IRF pathway is essential in antiviral response.
Earlier this year, the PME team conducted a high-throughput screen that looked at 40,000 combinations of molecules to see if any affected these pathways. They then tested the top candidates, finding that when those molecules were added to adjuvants — ingredients that help boost the immune response in vaccines — the molecules increased antibody response and reduced inflammation.
To find more candidates, the team used these results combined with a library of nearly 140,000 commercially available small molecules to guide an iterative computational and experimental process.
Graduate student Yifeng (Oliver) Tang used a machine learning technique called active learning, which blends both exploration and exploitation to efficiently navigate the experimental screening through molecular space. This approach learns from the data previously collected and finds potential high-performing molecules to be tested experimentally while also pointing out areas that have been under-explored and may contain some valuable candidates.
The process was iterative; the model pointed out potential good candidates or areas in which it needed more information, and the team conducted a high-throughput analysis of those molecules and then fed the data back into the active learning algorithm.
Molecules that outperform the rest
After four cycles —and ultimately sampling only about 2% of the library — the team found high-performing small molecules that had never been found before. These top-performing candidates improved NF-κB activity 110%, elevated IRF activity by 83%, and suppressed NF-κB activity by 128%.
One molecule induced a three-fold enhancement of IFN-β production when delivered with what’s called a STING (stimulator of interferon genes) agonist. STING agonists promote stronger immune responses within tumors and are a promising treatment for cancer.
“The challenge with STING has been that you can’t get enough immune activity in the tumor, or you have off-target activity,” Esser-Kahn said. “The molecule we found outperformed the best published molecules by 20 percent.”
They also found several “generalists” — immunomodulators capable of modifying pathways when co-delivered with agonists, chemicals that activate cellular receptors to produce a biological response. These small molecules could ultimately be used in vaccines more broadly.
“These generalists could be good across all vaccines and therefore could be easier to bring to market,” Ferguson said. “That’s quite exciting, that one molecule could play a multifaceted role.”
To better understand the molecules found by machine learning, the team also identified common chemical features of the molecules that promoted desirable behaviors. “That allows us to focus on molecules that have these characteristics, or rationally engineer new molecules with these chemical groups,” Ferguson said.
The team expects to continue this process to search for more molecules and hope others in the field will share datasets to make the search even more fruitful. They hope to screen molecules for more specific immune activity, like activating certain T-cells, or find a combination of molecules that gives them better control of the immune response.
“Ultimately, we want to find molecules that can treat disease,” Esser-Kahn said.
A team from the Pritzker School of Molecular Engineering (PME) at The University of Chicago tackled the problem by using machine learning to guide high-throughput experimental screening of this vast search space.
UChicago’s Pritzker School of Molecular Engineering Faculty boost vaccines and immunotherapies with machine learning to drive more effective treatments
ELSE PRESS RELEASES FROM THIS DATE:
Seven ORNL scientists among world’s top 1% most-cited researchers
Seven scientists from the Department of Energy’s Oak Ridge National Laboratory have been named among the world’s most influential researchers on the 2023 Highly Cited Researchers list, produced by Clarivate, a data analytics firm that specializes in scientific and academic research. "These scientists have delivered significant impact for the scientific community and nation," said ORNL Director Stephen Streiffer. "This honor highlights their commitment, hard work and leadership in their respective fields.” The ORNL researchers named to the list are: Miaofang Chi, Center for Nanophase Materials Sciences David A. Cullen, Center for Nanophase Materials ...
Lung cancer cells’ ‘memories’ suggest new strategy for improving treatment
A new understanding of lung cancer cells’ “memories” suggests a new strategy for improving treatment, Memorial Sloan Kettering Cancer Center (MSK) researchers have found. Research from the lab of cancer biologist Tuomas Tammela, MD, PhD shows that some lung cancer cells retain a “memory” of the healthy cell where they came from — one that might be exploited to make an emerging type of lung cancer treatment called KRAS inhibition more effective. The study looked specifically at lung adenocarcinoma, a type of non-small ...
Idai vs. Impalas: New study shows in real-time what helps mammals survive a natural disaster
When Cyclone Idai swept through Mozambique’s Gorongosa National Park in May 2019, one of nature‘s deadliest forces encountered one of the most technologically sophisticated wildlife parks on the planet. Princeton researchers and colleagues from around the world documented the effects using trail cameras and animal-tracking devices that had been in use before the storm. Thanks to the extensive network of cameras, GPS collars and other instruments, park staff and ...
Nanoplastics promote conditions for Parkinson’s across various lab models
DURHAM, N.C. – Nanoplastics interact with a particular protein that is naturally found in the brain, creating changes linked to Parkinson’s disease and some types of dementia. In a Duke-led study appearing Nov. 17 in Science Advances, the researchers report that the findings create a foundation for a new area of investigation, fueled by the timely impact of environmental factors on human biology. “Parkinson’s disease has been called the fastest growing neurological disorder in the world,” said principal investigator, Andrew West, Ph.D., professor in the Department of Pharmacology and Cancer Biology at ...
New research suggests plants might be able to absorb more CO2 from human activities than previously expected
New research published today in leading international journal Science Advances paints an uncharacteristically upbeat picture for the planet. This is because more realistic ecological modelling suggests the world’s plants may be able to take up more atmospheric CO2 from human activities than previously predicted. Despite this headline finding, the environmental scientists behind the research are quick to underline that this should in no way be taken to mean the world’s governments can take their foot off the brake in their obligations to reduce carbon ...
In the fight against malaria-carrying mosquitoes, just add soap
EL PASO, Texas (Nov. 17, 2023) – Could the solution to the decades-long battle against malaria be as simple as soap? In a new study published in PLOS Neglected Tropical Diseases, scientists at The University of Texas at El Paso have made a compelling case for it. The team has found that adding small quantities of liquid soap to some classes of pesticides can boost their potency by more than ten-fold. The discovery is promising news as malaria-carrying mosquitoes display ...
Deep dive on sea level rise: new modelling gives better predictions on Antarctic ice sheet melt
Using historical records from around Australia, an international team of researchers have put forward the most accurate prediction to date of past Antarctic ice sheet melt, providing a more realistic forecast of future sea level rise. The Antarctic ice sheet is the largest block of ice on earth, containing over 30 million cubic kilometers of water. Hence, its melting could have a devasting impact on future sea levels. To find out just how big that impact might be, the research team, including Dr Mark Hoggard from The Australian National University, turned to the past. “If ...
Crime-free housing policies increase evictions among minorities, but do not cut crime
Policies that encourage landlords to evict tenants who have involvement with the criminal justice system do not appear to reduce crime, while increasing evictions among Black residents and people with lower incomes, according to a new RAND Corporation report. Studying “crime-free housing policies” adopted by cities in California over a decade-long period, researchers found no meaningful statistical evidence that the policies reduce crime. The study also found that crime-free housing policies significantly increased ...
Consumption of antibiotics in the community back to pre-pandemic levels in the European Union and European Economic Area
This year’s European Antibiotic Awareness Day (EAAD) focuses on the targets outlined in the 2023 Council Recommendation to step up efforts in the European Union (EU) against antimicrobial resistance in a One Health approach.  Those recommendations formulate the 2023 goal to reduce total antibiotic consumption (community and hospital sectors combined) by 20%, using consumption data from 2019 as baseline. Consumption of antibiotics in the community accounts for around 90% of the total use. This means, that a substantial and consistent decline in the use of antibiotics in this sector will be key on the way towards reaching ...
LSU Health’s Bailey to receive prestigious national award
New Orleans, LA – The American Psychiatric Association (APA) Foundation has selected Rahn Baily, MD, DLFAPA, ACP, Professor and Chair of Psychiatry at LSU Health New Orleans School of Medicine, as the recipient of the 2024 Solomon Carter Fuller Award. According to the APA Foundation, “The Solomon Carter Fuller Award—established in 1969 and named for Dr. Solomon Carter Fuller, recognized as the first Black psychiatrist in America—honors a Black citizen who has pioneered in ...