Using artificial intelligence, MIT researchers have developed a new way to design nanoparticles that can more efficiently deliver RNA vaccines and other types of RNA therapies.
After training a machine learning model to analyse thousands of existing delivery particles, the researchers used it to predict new materials that would work even better for RNA therapies.
It also enabled the researchers to identify particles that would work well in different types of cells, and to discover ways to incorporate new types of materials into the particles.
Giovanni Traverso, associate professor of mechanical engineering at MIT and senior author of the study, explained: “We applied machine learning tools to help accelerate the identification of optimal ingredient mixtures in lipid nanoparticles to help target a different cell type or help incorporate different materials, much faster than previously was possible.”
This approach could dramatically speed the process of developing new RNA vaccines, as well as therapies that could be used to treat obesity, diabetes, and other metabolic disorders, the researchers say.
Giovanni Traverso, associate professor of mechanical engineering at MIT and senior author of the study, explained: “We applied machine-learning tools to help accelerate the identification of optimal ingredient mixtures in lipid nanoparticles to help target a different cell type or help incorporate different materials.”
Better functioning particles for effective RNA vaccines
RNA vaccines, such as the vaccines for SARS-CoV-2, are usually packaged in lipid nanoparticles (LNPs) for delivery. These particles protect mRNA from being broken down in the body and help it to enter cells once injected.
Creating particles that handle these jobs more efficiently could help researchers to develop even more effective vaccines. Better delivery vehicles could also make it easier to develop mRNA therapies that encode genes for proteins that could help to treat a variety of diseases.
“We’re trying to develop ways of producing more protein, for example, for therapeutic applications. Maximising efficiency is important to be able to boost how much we can have the cells can produce,” Traverso commented.
AI speeds up formulation making
A typical LNP consists of four components: a cholesterol, a helper lipid, an ionizable lipid, and a lipid that is attached to polyethene glycol (PEG). Different variants of each of these components can be swapped in to create a huge number of possible combinations.
However, changing up these formulations and testing each one individually is very time-consuming, so the researchers turned to AI to speed up the process.
Alvin Chan, lead author of the study, said: “Most AI models in drug discovery focus on optimising a single compound at a time, but that approach doesn’t work for lipid nanoparticles, which are made of multiple interacting components.
“To tackle this, we developed a new model called COMET, inspired by the same transformer architecture that powers large language models like ChatGPT. Just as those models understand how words combine to form meaning,
“COMET learns how different chemical components come together in a nanoparticle to influence its properties – like how well it can deliver RNA into cells.”
Testing different LNP formulations
To generate training data for their machine-learning model, the researchers created a library of about 3,000 different LNP formulations. Each of these 3,000 particles was tested in the lab to see how efficiently they could deliver their payload to cells, then fed into a machine-learning model.
After the model was trained, the researchers asked it to predict new formulations that would work better than existing LNPs. They tested those predictions by using the new formulations to deliver mRNA encoding a fluorescent protein to mouse skin cells grown in a lab dish.
They found that the LNPs predicted by the model outperformed the particles in the training data, and in some cases, better than LNP formulations that are used commercially.
Accelerated development of RNA therapies
Once the researchers showed that the model could accurately predict particles that would efficiently deliver RNA therapies, they began asking additional questions.
First, they wondered if they could train the model on nanoparticles that incorporate a fifth component: a type of polymer known as branched poly beta amino esters (PBAEs).
Next, the researchers set out to train the model to make predictions about LNPs that would work best in different types of cells, including Caco-2 cells, which are derived from colorectal cancer cells.
The model was able to predict LNPs that would efficiently deliver mRNA to these cells.
Lastly, the researchers used the model to predict which LNPs could best withstand lyophilisation – a freeze-drying process often used to extend the shelf-life of medicines.
Traverso concluded: “This is a tool that allows us to adapt it to a whole different set of questions and help accelerate development of RNA vaccines.
“We did a large training set that went into the model, but then you can do much more focused experiments and get outputs that are helpful on very different kinds of questions.”