Using Machine Learning to Develop a More Effective Malaria Vaccine
![](https://www.umiacs.umd.edu/sites/default/files/styles/medium/public/Cummings%20Chou.jpeg?itok=QbH602bV)
Michael Cummings (left) and Renee Ti Chou (right) collaborated on the project with researchers from the University of Maryland School of Medicine.
While cases of malaria have been decreasing in some parts of the world thanks to drug-based therapies, efforts to eradicate this life-threatening disease have recently stalled, due in part to the parasites that transmit malaria becoming resistant to current therapeutics.
Computational biologists from the University of Maryland have partnered with researchers at the University of Maryland School of Medicine to address this challenge. Using a novel approach called reverse vaccinology, which employs powerful bioinformatic tools and reverse pharmacology practices, the researchers are examining the genetic makeup of several parasites that cause malaria, seeking specific antigens to target with new vaccines.
The team’s initial research was just published in npj Systems Biology and Applications, a leading journal that focuses on scientific work that takes a systems-based approach.
The paper’s lead author is Renee Ti Chou, a data scientist at Lexical Intelligence in Rockville, Maryland, who earned her Ph.D. in computational biology last year at the University of Maryland.
Co-authors include Michael Cummings, a professor of biology with an appointment in the University of Maryland Institute for Advanced Computer Studies, and Amed Ouattara, Matthew Adams, Andrea A. Berry and Shannon Takala Harrison, all from the University of Maryland School of Medicine’s Center for Vaccine Development and Global Health.
Without a good vaccine, the researchers say, it is hard to get rid of any disease, malaria included. But to make a truly effective vaccine for malaria—which killed an estimated 608,000 people in 85 countries in 2022—scientists need to target different life cycle stages of the P. falciparum parasite, the deadliest species of Plasmodium that causes malaria in humans.
This can be tricky, though, because not only does the parasite take on different forms during its life cycle, but its genetic proteins also change, making it difficult for the human immune system to counter. So far, most vaccine efforts have focused on a few proteins without looking at the whole picture of the P. falciparum parasite’s genes.
With the reverse vaccinology approach, based in-part on powerful machine learning algorithms, the UMD/UMB researchers hope to gain a clearer picture that will lead to better vaccine antigens.
For their work, the researchers analyzed thousands of proteins from the P. falciparum parasite, considering 272 different factors for each. They used a machine learning technique called positive-unlabeled learning to sort through this data, focusing on proteins that resemble known vaccine targets.
They do not have to start with specific criteria; instead, they let the computer learn from what is already known about effective vaccine targets. This method looks at all the genes of the malaria parasite to find ones that might make good vaccine targets, even if they are not obvious at first.
Cummings, who is also the director of the Center for Bioinformatics and Computational Biology, says this approach has not been widely used for malaria, but it could help find new vaccine candidates, especially for parts of the P. falciparum parasite that are not well understood yet.
The researchers not only identified new potential vaccine targets, Cummings adds, but also ranked them based on importance. To prioritize the most promising candidates, they looked at factors like gene essentiality and when the proteins are active in the parasite’s life cycle.
“These findings offer a flexible framework for future vaccine research,” says Cummings, who was Chou’s academic adviser at UMD. “We can adjust our criteria and even apply this approach to other diseases beyond malaria. It’s a big step forward in the quest for better vaccines.”
The team’s research is supported by the National Science Foundation, the National Institutes of Health (NIH), a National Health and Medical Research Council grant, and a grant from MPowering Maryland. Other support came in the form of the Anne G. Wylie Dissertation Fellowship, which Chou received in her final year of Ph.D. training at UMD.
For her doctoral work related to this project, Chou recently received the Charles A. Caramello Distinguished Dissertation Award. Also, in work that is peripherally tied to this current research, Cummings was the recipient of an NIH grant in 2023 to study the body’s immune response to malaria to help scientists develop more effective vaccines.
—Story by Melissa Brachfeld, UMIACS communications group