Researchers at LMU Munich have developed Bits2Bonds, the first platform to combine molecular simulation and machine learning. This will accelerate the discovery of polymeric carriers for therapeutic RNA.
A research group led by Professor Olivia Merkel, Head of the Department of Drug Delivery at LMU Munich, has announced a new computational platform that can significantly speed up the development of RNA-based medicines. This study introduces Bits2Bonds, the first tool to combine molecular dynamics (MD) simulations and machine learning (ML). de novo Design of polymeric carriers that can transport therapeutic RNA into cells.
This breakthrough is part of Professor Merkel’s European Research Council (ERC) Consolidator grant project ‘RatInhalRNA’, which focuses on creating advanced RNA delivery technologies specifically for pulmonary administration.
Overcoming barriers in RNA delivery research
The development of effective delivery vehicles for therapeutic RNA is one of the major challenges in modern drug design. Experimental screening of large polymer libraries is known to be labor-intensive, expensive, and time-consuming. On the other hand, early computational tools were limited by the lack of training data and the high processing power required for accurate simulations.
The development of effective delivery vehicles for therapeutic RNA is one of the major challenges in modern drug design.
Bits2Bonds aims to solve these problems by integrating coarse-grained MD simulations, used to mimic important biological phenomena such as siRNA binding and membrane interactions, with machine learning systems that can predict and optimize molecular structures. By combining these approaches, the platform can rapidly virtually analyze thousands of potential polymer candidates, narrowing down the field long before laboratory testing begins.
A new era in high-throughput RNA carrier design
“Our study shows for the first time that physics-based simulation combined with data-driven optimization can efficiently guide the discovery of entirely new materials for RNA therapy,” said Professor Merkel. “This method paves the way for more rational, high-throughput design of polymer delivery systems and brings us closer to personalized RNA medicines.”
Hybrid approaches provide researchers with a powerful means to explore unexplored chemical space.
Hybrid approaches provide researchers with a powerful means to explore unexplored chemical space and identify materials that may be missed by traditional screening methods. As a result, Bits2Bonds has the potential to significantly shorten the development timeline for clinically viable nanocarriers, especially nanocarriers capable of delivering small interfering RNAs (siRNAs) that require stability and precision to function safely.
Promising experimental validation
To test the platform, the team synthesized several polymer candidates that Bits2Bonds predicted would exhibit strong RNA binding and delivery capabilities. Subsequent laboratory experiments confirmed the strong correlation between simulated behavior and real biological performance, demonstrating the reliability of the integrated modeling approach.
The researchers report that the system is intentionally modular, meaning it can be adapted to study a wider range of polymer classes and nucleic acid types. This includes emerging therapeutic technologies such as messenger RNA (mRNA) vaccines and CRISPR-based gene editing systems.
A versatile tool for future RNA therapeutics
Bits2Bonds allows researchers to explore a huge number of potential materials In silico, This is a major step for the field of nucleic acid delivery. As RNA-based therapies continue to play an expanding role in personalized and precision medicine, the ability to quickly design safer and more effective carriers will be critical.
As research continues under the RatInhalRNA program, Professor Merkel’s team is hopeful that this platform will support the next wave of RNA therapeutic innovation, potentially changing the way such medicines are designed, tested, and ultimately delivered to patients.
