Â鶹´«Ã½

News — More than 10 years in the making, researchers in the growing fields of bionanotechnology and artificial intelligence have combined forces to accurately predict – and ultimately influence – how the human immune system responds to next-generation therapeutics.

AI-Cell – which stands for or Artificial Intelligence Cell – is already in use, freely available to biomedical researchers who may use it in their first steps toward designing the next life-saving cancer treatment or vaccine to stave off worldwide illness.

“Essentially, AI-cell is a computational algorithm that thinks like the human immune cell,” said Kirill Afonin, Ph.D., professor of chemistry in the Klein College of Science.

at UNC Charlotte is not only at the center of burgeoning nucleic acid nanoparticle research but also spearheaded this first-of-its-kind AI tool in collaboration with Drs. Dobrovolskaia’s (NCI) and Zakharov’s (NCATS) teams.

Afonin is now collaborating with Brittany Johnson, Ph.D., biological sciences assistant professor, alongside other experts in machine learning and immunology, to further diversify and improve the capability of this  platform. 

The recently unveiled AI-powered tool predicts human immunological responses of RNA and DNA-based nanomedicines – widely heralded as the next frontier for gene therapies. 

Behind the scenes of AI-Cell, the nucleic acid nanoparticle data itself holds revolutionary promise. Researchers have discovered ways to use lab-constructed nucleic acids (biopolymers, naturally occurring in all living cells) to predict and then mimic the body’s normal response to pathogens or diseases. 

Put simply, are highly effective in drug or vaccine delivery. “If designed correctly, your body will recognize these artificially made NANPs as its own components, which can initiate and guide various biochemical processes and help fix the problem from within,” Afonin said.

Already, the FDA has approved several nucleic acid-based nanotechnologies. Advancements in these gene therapies may someday help doctors treat currently incurable cancers or other diseases involving the human central nervous system. 

In recent years, awareness among the general public has grown – particularly about mRNA therapeutics. 

“mRNA became famously known recently because of COVID-19,” Afonin said. 

Both Pfizer and Moderna developed messenger RNA vaccines in December 2020. These highly effective vaccines prompt the body to produce coronavirus antibodies, preparing the recipient to better fend off a dangerous virus.

“While RNA is considered ‘a molecule of life,’ rationally designed mRNA vaccines have literally helped to save millions of human lives. This revolutionary approach made it possible to encode viral proteins and make human cells synthesize them following the instructions provided by the exogenous mRNAs. So, when the virus with the same proteins appears in our body, the immune system is already primed,” Afonin said. 

Yet for all the ways mRNA drugs and vaccines – and more broadly, emerging therapeutics using nucleic acids or NANPs – spark optimism, researchers are challenged in taking these products from the lab into doctors’ hands. 

There are the usual hurdles like funding and the long process of clinical trials with human patients. But these promising therapeutics also face a particular problem – one that AI-Cell directly helps solve. 

“The immune system is a very complex process,” Johnson said. “A lot of times we think the immune response is always productive. In reality, it’s a little bit more like a see-saw and you want things to be in balance.” 

“You need peaks at certain times… and you want that immune response to have certain qualities. And then you want that to resolve so that you can go through a healing process,” Johnson said.

Because nucleic acids in medicines or vaccines effectively “piggyback” on the immune system’s fight against an invading virus or bacteria, there’s a risk of instigating a severe response that ultimately isn’t healthy.

AI-Cell addresses this by putting a library of known nucleic acid nanoparticle combinations – and associated immunological responses – directly in the hands of researchers. With this data, scientists can better predict which compositions, structures, shapes, and amounts of nanoparticles will work best to curb disease without causing extremely negative immune responses.

"The big idea is to develop a biomolecular language to explain to our bodies and immune system how to reveal and deal with certain diseases – and make this technology user-friendly, widely available, personalized, and affordable," Afonin said. 

Now, the experts at UNC Charlotte, NCI, and NCATS are expanding on AI-Cell, hoping to help labs and teams across the world work more quickly and confidently to develop revolutionary medicines and vaccines.

‘We’re engineering it down’

Delivering targeted genetic material to cells – with programmable messages and nanoparticles capable of controlling or reducing adverse side effects – is a particularly vexing proposition.

“Our bodies look for specific sequences and aspects of foreign nucleic acids … It’s looking for things that are amiss,” Johnson said. “Because of that, when we deliver things like nucleic acids, you have to be cautious because you could stimulate an unwanted immune response.”

In addition, there are near-limitless structures and combinations possible with nanoparticle technology. 

“Particularly for nucleic acid-based nanotechnology, (AI-Cell) is going to be incredibly helpful because you can move in both directions… You can imagine going in and because a patient is diagnosed with a certain disease, you may be trying to get a certain immune response. You can use this tool. You can say, ‘Okay, I know what immune response I want – now I need to work backward [to determine] what nucleic acids I can use to get there,’” Johnson explained. 

“Instead of starting with unlimited possibility, we’re engineering it down to this targeted portion.”

AI-Cell also holds immense potential for deploying individualized medicine and therapeutics. 

UNC Charlotte alumnae Morgan Chandler, Ph.D., says while this prospect is “far off on the horizon,” the research like what she and others have performed in the Afonin Lab is setting the stage.

After obtaining her doctorate at UNC Charlotte in 2021, Chandler completed a 13-month fellowship at the FDA. Now she works as a scientist at Mimetas, a small biotech company based just outside Washington, D.C.

Around the time she started in her current role, a peer-reviewed paper about AI-Cell (for which Chandler served as lead author) was published in Small, a leading nanoscience and nanotechnology journal. In it, the research team explains in-depth their approach – the first of its kind – to use “state-of-the-art transformer neural networks to predict immunological activity and thus advance the current understanding of the NANP properties.” 

The collaborative work utilized peripheral blood mononuclear cells isolated from freshly collected blood of healthy human donors, which confers a higher degree of accuracy when predicting severe immunological responses (e.g., cytokine storm)  compared to traditional tests on animals. 

At this stage, a query using AI-Cell can return a compatibility response in just a few seconds. This could support the design of future gene therapies – not only by saving days in pre-clinical research but also by saving lives.

“We could ideally just do the same thing where we extract a patient’s PBMCs before applying a therapeutic to them,” Chandler said. “We could see exactly how they’re going to respond to something and then we could select the best adjuvant, for instance, or the best therapeutic. Using these assays in real-time could be amazing for the future of personalized medicine.”

‘No limits for expansion’

To grasp the impact of AI-Cell and the advancement in treating diseases on the cellular level, it helps to understand the basics of biotechnology and nanotechnology targets. 

DNA is the building block or blueprint of the human cell, and RNA decodes the blueprint. 

In the context of gene therapies, NANPs work in concert with the body's natural response to pathogens and disease. NANPs are effective because nucleic acids in drug delivery can augment the body's natural defense and self-healing processes. 

Knowing if the body needs to control or lower inflammation or stimulate more action from the immune cells is a balancing act. Combining rationally designed and lab-constructed NANPs with the AI-Cell tool aids drug and vaccine design towards this goal.

There is huge potential to offer new ways to treat a broad spectrum of malignancies, from cancers to cardiovascular problems and infectious diseases. This includes therapeutics, diagnostics, and preventative biomedicine, such as vaccines with mRNA technology. 

Each set of NANPs is unique in its architectural parameters and physicochemical properties, which, together with the type of delivery vehicle, determine the kind and magnitude of its immune response. Many experimental drugs fail in trials due to cytokine storm response where the body has an extreme immune response, which can be damaging, if not fatal. 

Using human blood immune cell data in combination with AI-Cell’s predictive power renders a more realistic view of likely patient immune responses. 

Having logged the immunorecognition of close to 180 NANPs, Afonin said: "What we're doing will be of huge help to the scientific community and the growing field of y  – the field right now is starting to bloom … AI-Cell has already become a very dynamic platform which has no limits for expansion.”

Afonin and Johnson explain the concept of NANPs and AI-Cell using a Lego block analogy. Each block (a NANP) is a known structure, yet the options for building those blocks into various forms are nearly exponential.

The Afonin lab in the has undergraduate and graduate students working on two fronts in advancing the AI-Cell platform. They’re investigating and experimenting to find new NANPs, examine how they work, and contribute to the dataset behind AI-Cell so that other labs can "test" or query the data. 

"Our work basically compiled this huge database to identify all the structural parameters and biological activities of our NANPs. That was the library we passed on to the NCATS (National Center for Advancing Translational Sciences) lab to build the predictive model using all of their computational expertise," Chandler said. 

Her work in the Afonin lab at UNC Charlotte added to the AI-Cell database in testing the 2D and 3D structures that are now in use with current students.

Ph.D. student from the Afonin Lab, Laura Rebolledo, has been working with fibrous NANPs – multistranded molecular devices decorated with functional aptamers (blockades or binders) – which are intended for various biomedical applications. Fibrous NANPs help to arrange functional structures into a single formulation with embedded biochemical instructions and further deliver the intended therapies either extracellularly or into human cells.

Rebolledo, originally from Colombia, is the first in her family to graduate from college. Before she applied to work in the Afonin Lab, she says, she felt lost in the academic process. The experience of working with other undergraduate and graduate students opened the door to her current role in the lab as a Ph.D. student in the chemistry and nanoscale sciences program. 

Part of was published by The American Chemical Society’s (ACS) Applied Bio Materials journal in June. Rebolledo was also the lead author of a paper also published by ACS earlier this year in .

“While we were analyzing these fibrous NANPs we discovered that their functionalization with aptamers defines not only their activity but also changes their immunorecognition. We wanted to better understand the mechanisms of how these NANPs were recognized by cells and how we can apply this knowledge in more efficient drug design,” Rebolledo said. “And then we discovered that by increasing the number of functional groups per each fiber, we can stealth coat them from being seen by some parts of cellular machinery responsible for detection of foreign nucleic acids.”

Expanding AI-Cell

Rebolledo credits UNC Charlotte’s support for undergraduate research, the push from her faculty advisor, and the Afonin Lab’s welcoming culture for helping her reach her goals.

"It was eye-opening to see people from similar backgrounds be as successful as they are today in government labs, academia and industry. Dr. Afonin embraces diversity in his lab, and the support for his students attracted me to the lab because of the inclusivity of every single grad student," she said. 

And soon, the number of students involved in expanding AI-Cell could grow.

Afonin submitted a $3 million funding proposal to the National Science Foundation to start a new center called Traineeship in the Advancement of RNA Nanotechnologies (TARNAno). There, faculty would train UNC Charlotte graduate students to work with NANPs and carry out cutting-edge research in this field, with a particular emphasis on NANP immunotherapies. 

“The predictive capacity of AI-cell is just going to increase,” Afonin said. “It’s very very promising but there’s more work to do for sure. It’s also very exciting because our team will continue working on it. There are still lots of questions to answer.”

An upcoming manuscript from Afonin and Johnson will explore AI-Cell’s capability to predict the immunostimulation of NANPs in the human central nervous system (CNS). This work was done in collaboration with NCATS, Ball State University, and UNC Charlotte. In 2022, the National Cancer Institute (NCI) with immunostimulatory NANPs on the cover page of a Congressional presentation. Funding for AI-Cell and related research comes from the National Institute of General Medical Sciences of the National Institutes of Health under Award Numbers R35GM139587, with additional support from NCI and NCATS.

Glossary of Terms 

Nucleic Acid Nanoparticles (NANPs): Nanostructures (i.e. small molecular platforms) derived from DNA, RNA, or associated chemicals.

mRNA: Messenger RNA is a nucleic acid that prompts cellular protein production.

Gene therapies: Modifying or adding to genes to eliminate or treat disease or disease-causing genes.

Immunoresponse: How the body reacts when bacteria, viruses, or pathogens enter.

PBMCs: Peripheral blood mononuclear cells (from donor blood) which are commonly used in clinical or research settings.

Adjuvant: Generally increases the effectiveness of a vaccine and may reduce the need for boosters.

Functional aptamers: When used with mRNA or synthetic DNA, aptamers can regulate the functions of target proteins.