MIT researchers use AI algorithm to make mRNA vaccines more heat-resistant
MIT researchers used an AI algorithm to adjust lipid nanoparticle formulations, producing mRNA vaccines that could remain stable at room temperature for up to a year.
Researchers at MIT have used an AI algorithm to make mRNA vaccines more heat-resistant by adjusting the formulation around the lipid nanoparticles (LNPs) that typically deliver them, according to an article by Anne Trafton in MIT News. Vaccines made this way could remain stable at room temperature for up to a year. The work appears in a paper in Nature Biotechnology.
RNA is highly fragile, and RNA-LNP vaccines still need to be kept at -20 to -80 degrees Celsius, which makes it difficult to ship them to regions without cold-storage facilities. The team wanted to see if it could make the FDA-approved formulations used for the Moderna and Pfizer Covid-19 vaccines more stable at high temperatures.
Researchers have experimented with adding excipients, such as sugars, salts or polymers, to LNPs. Ana Jaklenec, a principal investigator in MIT's Koch Institute for Integrative Cancer Research, said the team was “really getting stuck” when it reused excipients that had worked in its earlier efforts. It then worked with researchers at MIT's Computer Science and Artificial Intelligence Lab (CSAIL) to develop an algorithm that can make predictions based on very small datasets.
The researchers measured how well each of nearly 50 FDA-approved excipients protected mRNA inside an LNP, then chose five of the most promising and used the algorithm to predict the ratios that would best stabilize LNPs similar to those used by Moderna. They tested two formulations at a time in cells and fed the results back into the algorithm. After several rounds, they picked one formulation to test in animal studies. The process took only a few weeks, much less than it would have taken without the algorithm. “The real beauty of this algorithm is that we can use it with small data sets,” Jaklenec said.
For heat testing, the team packaged Covid-19 mRNA antigens in the new particles, dehydrated them by vacuum drying and stored them at 37 degrees Celsius (98 degrees Fahrenheit) for two months or at room temperature for one year. Mice vaccinated with these particles, even after long-term storage, showed immune responses equivalent to those of mice given vaccines carried by LNPs similar to the original Moderna formulation. The team also used the formulation to create solid microneedle patches that could deliver a SARS-CoV-2 antigen, and these generated an immune response similar to that produced by the injectable RNA vaccines.
The researchers also showed that they could use the algorithm to stabilize other LNP formulations, including one similar to those used by Pfizer to deliver its Covid-19 vaccine. Once a heat-resistant formulation has been developed for an LNP, it could be adapted to deliver any type of mRNA payload, the researchers say.
Jaklenec and Robert Langer, the David H. Koch Institute Professor, are the paper's senior authors. Graduate student Jinbi Tian and postdoc Khanh Tran are its lead authors. The research was funded in part by the Gates Foundation.