‘Remarkable’ AI tool designs mRNA vaccines that are more potent and stable

[bnew]

‘Remarkable’ AI tool designs mRNA vaccines that are more potent and stable

Software from Baidu Research yields jabs for COVID that have greater shelf stability and that trigger a larger antibody response in mice than conventionally designed shots.

www.nature.com

https://archive.is/s9XJB

• NEWS
• 02 May 2023

Software from Baidu Research yields jabs for COVID that have greater shelf stability and that trigger a larger antibody response in mice than conventionally designed shots.

During the COVID-19 pandemic, mRNA vaccines against the coronavirus SARS-CoV-2 had to be kept at temperatures below –15°C to maintain their stability. A new AI tool could improve that characteristic.Credit: Jean-Francois Monier/AFP via Getty


An artificial intelligence (AI) tool that optimizes the gene sequences found in mRNA vaccines could help to create jabs with greater potency and stability that could be deployed across the globe.

Developed by scientists at the California division of Baidu Research, an AI company based in Beijing, the software borrows techniques from computational linguistics to design mRNA sequences with more-intricate shapes and structures than those used in current vaccines. This enables the genetic material to persist for longer than usual. The more stable the mRNA that’s delivered to a person’s cells, the more antigens are produced by the protein-making machinery in that person’s body. This, in turn, leads to a rise in protective antibodies, theoretically leaving immunized individuals better equipped to fend off infectious diseases.

What’s more, the enhanced structural complexity of the mRNA offers improved protection against vaccine degradation. During the COVID-19 pandemic, mRNA-based shots against the SARS-CoV-2 coronavirus famously had to be transported and kept at temperatures below –15°C to maintain their stability. This limited their distribution in resource-poor regions of the world that lack access to ultracold storage facilities. A more resilient product, optimized by AI, could eliminate the need for cold-chain equipment to handle such jabs.

The new methodology is “remarkable”, says Dave Mauger, a computational RNA biologist who previously worked at Moderna in Cambridge, Massachusetts, a maker of mRNA vaccines. “The computational efficiency is really impressive and more sophisticated than anything that has come before.”

Linear thinking​

Vaccine developers already commonly adjust mRNA sequences to align with cells’ preferences for certain genetic instructions over others. This process, known as ‘codon optimization’, leads to more-efficient protein production. The Baidu tool takes this a step further, ensuring that the mRNA — usually a single-stranded molecule — loops back on itself to create double-stranded segments that are more rigid (see ‘Design optimization’).

Known as LinearDesign, the tool takes just minutes to run on a desktop computer. In validation tests, it has yielded vaccines that, when evaluated in mice, triggered antibody responses up to 128 times greater than those mounted after immunization with more conventional, codon-optimized vaccines. The algorithm also helped to extend the shelf stability of vaccine designs up to sixfold in standard test-tube assays performed at body temperature.

“It’s a tremendous improvement,” says Yujian Zhang, former head of mRNA technology at StemiRNA Therapeutics in Shanghai, China, who led the experimental-validation studies.

So far, Zhang and his colleagues have tested LinearDesign-enhanced vaccines against only COVID-19 and shingles in mice. But the technique should prove useful when designing mRNA vaccines against any disease, says Liang Huang, a former Baidu scientist who spearheaded the tool’s creation. It should also help in mRNA-based therapeutics, says Huang, who is now a computational biologist at Oregon State University in Corvallis.
The researchers reported their findings on 2 May in Nature1.

Optimal solutions​

Already, the tool has been used to optimize at least one authorized vaccine: a COVID-19 shot from StemiRNA, called SW-BIC-213, that won approval for emergency use in Laos late last year. Under a licensing agreement established in 2021, the French pharma giant Sanofi has been using LinearDesign in its own experimental mRNA products, too.

Executives at both companies stress that many design features factor into the performance of their vaccine candidates. But LinearDesign is “certainly one type of algorithm that can help with this”, says Sanofi’s Frank DeRosa, head of research and biomarkers at the company’s mRNA Center of Excellence.

Another was reported last year. A team led by Rhiju Das, a computational biologist at Stanford School of Medicine in California, demonstrated that even greater protein expression can be eked out of mRNA — in cultured human cells at least — if certain loop patterns are taken out of their strands, even when such changes loosen the overall rigidity of the molecule2.

That suggests that alternative algorithms might be preferable, says theoretical chemist Hannah Wayment-Steele, a former member of Das’s team who is now at Brandeis University in Waltham, Massachusetts. Or, it suggests that manual fine-tuning of LinearDesign-optimized mRNA could lead to even better vaccine sequences.

But according to David Mathews, a computational RNA biologist at the University of Rochester Medical Center in New York, LinearDesign can do the bulk of the heavy lifting. “It gets people in the right ballpark to start doing any optimization,” he says. Mathews helped develop the algorithm and is a co-founder, along with Huang, of Coderna.ai, a startup based in Sunnyvale, California, that is developing the software further. Their first task has been updating the platform to account for the types of chemical modifications found in most approved and experimental mRNA vaccines; LinearDesign, in its current form, is based on an unmodified mRNA platform that has fallen out of favour among most vaccine developers.

A structured approach​

But mouse studies and cell experiments are one thing. Human trials are another. Given that the immune system has evolved to recognize certain RNA structures as foreign — especially the twisted ladder shapes within many viruses that encode their genomes as double-stranded RNA — some researchers worry that an optimization algorithm like LinearDesign could end up creating vaccine sequences that spur harmful immune reactions in people.

“That’s kind of a liability,” says Anna Blakney, an RNA bioengineer at the University of British Columbia in Vancouver, Canada, who was not involved in the study.

Early results from human clinical trials involving StemiRNA’s SW-BIC-213 suggest the extra structure is not a problem, though. In small booster trials reported to date, the shot’s side effects have proven no worse than those reported with other mRNA-based COVID-19 vaccines3. But as Blakney points out: “We’ll learn more about that in the coming years.”
doi: ‘Remarkable’ AI tool designs mRNA vaccines that are more potent and stable

 

[bnew]

How scientists are using AI to supercharge mRNA vaccines and drugs

A new AI-driven software has written code for COVID-19 vaccines that trigger up to 128 times greater antibody responses.

www.euronews.com

Chinese tech giant Baidu is using AI to unlock better mRNA vaccines and cancer drugs. Here’s how​

By Camille Bello • Updated: 17/05/2023 - 08:19

A new AI-driven software has written code for COVID-19 vaccines that trigger up to 128 times greater antibody responses.

The research arm of Chinese tech giant Baidu has unveiled a novel algorithm to design mRNA vaccine sequences that were previously out of reach.

In validation tests with mice, the AI-driven software yielded code for COVID-19 vaccines that trigger up to 128 times greater antibody responses.

The algorithm, called LinearDesign, has also proven successful in extending the shelf stability of the vaccines sixfold, even when exposed to body temperatures.


Cold storage is needed for most vaccines, and this condition makes distribution efforts challenging, especially in the hotter regions of the world.

The ability to extend the shelf stability of vaccines and improve their tolerance to various temperatures could therefore have a radical impact on immunisation efforts across the planet.

The AI tool the researchers developed could also have applications beyond vaccines and help design potent new cancer treatments, Dr He Zhang, Staff Software Engineer at Baidu Research, told Euronews Next.

Just last week, personalised mRNA vaccines for pancreatic cancer patients showed promising results in a small study conducted by New York researchers and Germany’s BioNTech, staving off the return of the tumour in half of those treated.

The study used a pancreatic cancer mRNA vaccine tailored to each patient’s tumour to potentially help provoke an immune response.

Messenger RNA (mRNA) medicine refers to a new class of drugs and vaccines that use a small piece of genetic material called mRNA to teach the body's cells to produce a protein, which triggers an immune response against a specific pathogen, such as a virus. This approach is different from traditional vaccines, which use weakened or inactivated parts of a specific pathogen to stimulate the immune system.

Oncology is an important area for mRNA vaccine manufacturers, allergies is another. BioNTech - the same company that along with Pfizer produced the mRNA COVID-19 vaccine - also holds the patent rights to an mRNA vaccination platform designed to protect against allergens such as grass pollen and house dust mites.

While mRNA medicine is promising, it comes with its own challenges.

“mRNA vaccines have saved many lives,” Zhang said, “but there are still some problems around the stability and therefore the effectiveness”.

The challenge of keeping mRNA intact​

Messenger RNA is unstable because it is single-stranded, unlike DNA, which is double-stranded.

The single-stranded parts of our mRNA are more easily cut down to pieces or degraded into segments - either by the immune systems, water molecules or even before being injected into your body, explained Dr Liang Huang, Professor at Oregon State University and co-author of the LinearDesign paper.

And when the mRNA is degraded into little pieces, it cannot pass the full message on to the cells.

“The goal is to keep the mRNA intact in its full length,” said Huang, and to do that the messenger RNA has to be as compact as possible.

“In other words, you want to design mRNA that folds and looks more like a [double-stranded] DNA,” he told Euronews Next.

And that’s exactly what the LinearDesign algorithm has done.

How does the LinearDesign algorithm work?​

The breakthrough algorithm that promises to revolutionise the field of mRNA therapeutics is not actually new.

The LinearDesign model is based on a 1961 algorithm called lattice parsing, originally invented for natural language processing and speech recognition.

“We basically used the same algorithm without any change, the only change is the input, which was grammar,” he said.

The lattice parsing algorithm had been originally used to identify the most likely sentence among several possible alternatives that sound similar.

“The technique was already somehow there 60 years ago,” said Huang. “It was just waiting for us to discover the connection between two distant, remote fields: linguistics and biology”.

Using this technique, the researchers found a way to make the algorithm create, in just 11 minutes, “the most stable COVID-19 mRNA vaccine”.

In other words: they identified the most secure structure for the mRNA messenger to travel and deliver the message to the cells.

Running all the possible combinations that the AI algorithm did to find the most stable vaccine would have taken humans "the life of the universe: billions of billions of billions of years,” said Huang.

Is AI the future of vaccines?​

The Baidu researchers predict the LinearDesign algorithm will make mRNA technology even “more popular than it currently is,” as well as enable other variants of the technology to enter more fields of medicine.

French giant Sanofi, a pharmaceutical industry company headquartered in Paris, has already licensed the LinearDesign technology. The drugmaker picked it up at the end of 2021 when the researchers first published the preprint of their study.

The paper - written in collaboration with Oregon State University, StemiRNA Therapeutics, and the University of Rochester Medical Center and unveiled in the scientific magazine Nature earlier this month - was first published under “rare option of accelerated article preview,” said Huang, which means the scientific journal made the study public before it actually underwent the editing process.

“The editor chose us for accelerated article preview because he, quote: ‘thought this has relevance to the public health and the pandemic’”.

The Baidu Research scientists are optimistic that mRNA technology will replace traditional vaccines in the next decade.

“I think in about five years, probably all the mRNA pharmaceutical industry will be using this algorithm,” Huang told Euronews Next, adding that “mRNA vaccines are much better, except for stability, which we solved”.

[Editor's note: This article has been corrected to clarify that the company behind the study is Baidu, China's largest search engine. Baidu Research is the research unit of Baidu.]