Artificial Intelligence News

AI-powered tool predicts human immune response to nucleic acid nanoparticles


April 09, 2023

(Nanowerk Highlights) As new biomedical technologies approach clinical trials, understanding their interactions with the human immune system becomes a major concern. Unwanted immune recognition can result in severe side effects, which can not only halt the further development of the substance under investigation but also adversely affect the entire research field.

The same concept naturally applies to therapeutic nucleic acids (TNA) which significantly impacted the field of nanomedicine, leading to the development of nucleic acid nanoparticles (NANPs). These novel materials are engineered solely from short RNA and/or DNA strands that self-assemble into defined architectures of varying composition, size, and shape, resulting in precisely controlled physicochemical properties and therapeutic functions.

NANP has the potential to treat various diseases, including cancer, infectious diseases, and cardiovascular diseases. However, understanding their interactions with the human immune system is critical for their clinical translation.

“The unique nature of NANP means that its immune recognition cannot be extrapolated from conventional TNA,” Professor Kirill Afonin told Nanowerk. “The ability to predict how NANP interacts with the immune system can enable the development of customized formulations with optimized therapeutic effects and controlled immunological activity.”

Deep learning has significantly advanced various research fields, including computer vision and natural language processing. It is also widely used in biomedical research, such as drug discovery and genomics. In genomics, sequence-based deep learning models have gone beyond classical machine learning, enabling efficient prediction of function, origin, and properties of DNA and RNA sequences through training neural networks on large data sets.

Development of a computer-assisted learning tool that will predict NANP immune recognition in siliconbased solely on their sequence composition, will accelerate the translation of this promising technology and lead more research teams into the emerging field of RNA nanotechnology.

Now, an interdisciplinary team, led by Afonin Laboratory at UNC Charlotte, have developed an unprecedented artificial intelligence-based tool that can predict the immune response of human immune cells (specifically peripheral blood mononuclear cells, or PBMCs) when they encounter nucleic acid nanoparticles or other therapeutic nucleic acids. A conceptual representation of an artificial immune cell (or AI cell) tool. A conceptual representation of an artificial immune cell (or AI cell) tool. A) Preliminary design and synthesis of nucleic acid nanoparticles (NANPs) followed by physicochemical characterization and assessment of immunostimulatory potential to then be applied for predictive computational analysis of NANPs immune response. B) Experimental workflow used for AI-cell development. (Reprinted with permission by Wiley-VCH Verlag) (click on image to enlarge)

The researchers report their findings in Small (“Artificial Immunity Cells, AI-cellNew Tool for Predicting Interferon Production by Peripheral Blood Monocytes in Response to Nucleic Acid Nanoparticles”).

According to Afonin, this work was a massive collaborative effort with five years of hard work and constant interaction between UNC Charlotte, the National Center for Advancing Translation Sciences (NIH), the computing team of Dr. Alexey Zakharov, and the Frederick National Laboratory for Cancer Research (NCI), a team of immunologists led by Dr. Marina Dobrovolskaia.

By systematically examining the physicochemical and immunological profiles of a broad panel of diverse nanoparticles, interdisciplinary research teams collaboratively develop and experimentally validate computational models.

This model, based on transformer architecture, is able to predict the immune activity of nanomaterials. The researchers used a random forest (RF) and two different neural network architectures, including a recurrent neural network and a transformer neural network, to predict the immunomodulatory activity of 58 NANP representatives.

The best performing models are now freely accessible to the research community via online tool called “Artificial Immune Cell” or AI-cell. This tool can be used to predict the immunological response of any new nucleic acid architecture, potentially accelerating the design and selection of NANPs for personalized immunotherapy approaches or immunologically safe nano-scaffolds for other applications. By
Michael is the author of three books by the Royal Society of Chemistry:
Nano-Society: Pushing the Boundaries of Technology,
Nanotechnology: A Small FutureAnd
Nanoengineering: Skills and Tools for Making Technology Invisible
Copyright ©

nano job

Become a Spotlight guest writer! Join our large and growing group of guest contributors. Have you recently published a scientific paper or have other interesting developments to share with the nanotechnology community? Here’s how to publish on


Source link

Related Articles

Back to top button