Researchers at MIT have developed a new AI method to design nanoparticles that can deliver RNA vaccines and other RNA-based treatments more effectively.
The team trained a machine learning system on thousands of existing lipid nanoparticles (LNPs), the tiny fat-based particles commonly used to carry mRNA into cells. The model was able to suggest new designs that outperformed existing ones. It also revealed which particles worked best in different cell types and how new materials could be added to improve performance.
According to one of the study authors, Giovanni Traverso, AI allowed them to test combinations far faster than traditional trial-and-error methods. “Our tools let us pinpoint the right mixtures for nanoparticles much quicker, whether to reach a different cell type or to add new materials,” he explained.
This breakthrough could shorten the time it takes to create next-generation RNA vaccines and treatments for conditions like diabetes, obesity, and other metabolic diseases.
RNA vaccines, including those developed for COVID-19, typically rely on LNPs to protect fragile RNA molecules and help them enter cells once administered. Making these nanoparticles more efficient could open the door to stronger vaccines and new RNA therapies that deliver instructions for producing beneficial proteins.
Last year, Traverso’s team launched a long-term project supported by the U.S. Advanced Research Projects Agency for Health (ARPA-H) to explore oral RNA delivery devices.
A standard LNP has four parts: a helper lipid, a polyethylene glycol-linked lipid, cholesterol, and an ionizable lipid. Each component has many possible variants, creating an enormous number of potential combinations. Testing them one by one is slow and costly.
To handle this, the researchers built a new AI model, COMET, which uses the same underlying architecture as large language models (LLMs). Just as LLMs learn how words fit together, COMET learns how chemical components interact inside nanoparticles to determine their ability to deliver RNA.
To train the system, the team tested about 3,000 nanoparticle designs in the lab and recorded their performance. After processing the data, the AI generated predictions for new, more efficient designs. When tested in mouse skin cells, these AI-predicted particles outperformed many existing and even commercially used LNPs.
The team then expanded the model to test nanoparticles with a fifth component; branched poly-beta-amino esters (PBAEs), a polymer known to deliver genetic material on its own. These polymers are already known to carry nucleic acids effectively, and combining them with LNPs further improved performance.
They also trained the system to find formulations suited for specific cells, such as colorectal-derived Caco-2 cells, and even to predict particles that could survive freeze-drying, an important step for long-term storage of medicines.
Traverso noted that the tool can adapt to different research questions and speed up experiments dramatically. His team is now working to apply the technology to therapies for obesity and diabetes, including GLP-1–based treatments similar to drugs like Ozempic.
The findings were recently published in Nature Nanotechnology. Such studies suggest that as more advanced technologies are commercialized by AI companies like D-Wave Quantum Inc. (NYSE: QBTS), the paradigm-shifting impact of these technologies could revolutionize nearly every industry, and not just the biomedical research industry.
NOTE TO INVESTORS: The latest news and updates relating to D-Wave Quantum Inc. (NYSE: QBTS) are available in the company’s newsroom at https://ibn.fm/QBTS
About AINewsWire
AINewsWire (“AINW”) is a specialized communications platform with a focus on the latest advancements in artificial intelligence (“AI”), including the technologies, trends and trailblazers driving innovation forward. It is one of 70+ brands within the Dynamic Brand Portfolio @ IBN that delivers: (1) access to a vast network of wire solutions via InvestorWire to efficiently and effectively reach a myriad of target markets, demographics and diverse industries; (2) article and editorial syndication to 5,000+ outlets; (3) enhanced press release enhancement to ensure maximum impact; (4) social media distribution via IBN to millions of social media followers; and (5) a full array of tailored corporate communications solutions. With broad reach and a seasoned team of contributing journalists and writers, AINW is uniquely positioned to best serve private and public companies that want to reach a wide audience of investors, influencers, consumers, journalists, and the general public. By cutting through the overload of information in today’s market, AINW brings its clients unparalleled recognition and brand awareness.
AINW is where breaking news, insightful content and actionable information converge.
To receive SMS alerts from AINewsWire, text “AI” to 888-902-4192 (U.S. Mobile Phones Only)
For more information, please visit www.AINewsWire.com
Please see full terms of use and disclaimers on the AINewsWire website applicable to all content provided by AINW, wherever published or re-published: https://www.AINewsWire.com/Disclaimer
AINewsWire
Los Angeles, CA
www.AINewsWire.com
310.299.1717 Office
Editor@AINewsWire.com
AINewsWire is powered by IBN