The Future of Drugging RNA Using AI

The Future of Drugging RNA Using AI

Table of Contents

Challenges of Drugging RNA

You’ve heard of RNA-based therapies (think mRNA vaccines), but the newest player in RNA-based therapeutics involves targeting existing RNA, rather than introducing beneficial RNA into the body. RNA was long believed to be too polar and solvent-exposed to be a viable target for small-molecule drugs. However, it is now known that RNA molecules contain secondary structures that small molecules can, and do, bind.

Drugging RNA is appealing for a number of reasons. Perhaps the most compelling reason is that 80% of the genome encodes “non-coding” RNA of still-unknown function, compared to just 3% of the genome encoding proteins (which are first transcribed as mRNA). Of those proteins, roughly 85% of them are still considered “undruggable.”

In spite of the promise of RNA therapeutics increasing the landscape of druggable targets by nearly two orders of magnitude, very few RNA drugs have been discovered, let alone come to therapeutic fruition. In a recent news feature in Nature Biotechnology, Ken Garber explored the challenges and opportunities for drugging RNA.

Current Approaches

Companies in the RNA drug space have yet to release detailed information on their discovery processes, but a few key directions have emerged. The first target is splicing, the process of splicing out (removing) introns from pre-mRNA transcripts. When mRNA is initially transcribed, it contains introns, regions of non-coding DNA that are spliced out to allow the coding regions, or exons, to join. Exons can also be spliced out in a process called alternative splicing, where the same pre-mRNA can yield different mature mRNAs depending on which exons are removed, yielding proteins with different functions.

The only currently available drug that targets RNA is Evrysdi (risdiplam), which is approved for spinal muscular atrophy (SMA). Evrysdi targets the RNA/protein splicing complex to splice an exon into SMA2, a usually non-functional gene that is subsequently activated and can compensate for the mutation of SMA1, the cause of SMA. The current workflow for discovering drugs that can alter splicing and/or RNA levels involves random in vitro screening of compounds looking for desired splicing outcomes. Compounds are then optimized using structural biology tools and specificity and efficiency are determined via RNA sequencing (RNA-seq). There is yet to be a proof-of-concept for drugging mature mRNA after the splicing process.

Phenotypic screens like the pipeline described above look for desired outcomes without knowing the target. Companies are also pursuing target-based screens, attempting to increase the odds of getting a hit and removing the uncertainty of determining the affected RNA in a phenotypic screen. Target-based screens look for compounds that interact with known disease-related RNAs. However, a major challenge of this approach is the ability of many compounds to bind RNA non-specifically or to bind and have no biological effect, requiring laborious functional assays to rule out candidates.

AI and Future Developments

Two approaches are promising to bring the field of RNA drugs closer to fruition. The first is the development of AI tools to predict the best RNA structures for small molecules to bind to. The company Atomic AI is developing a model specifically for applications to drug discovery.

The second approach is the development of RNA degraders. These compounds circumvent the search for ideal binding targets to affect function by simply eliminating any RNA they bind. The ability of these compounds to often bind multiple RNAs carries risks of toxicity, but RNA-seq allows researchers to weed out nonspecific binders.

Taken together, the current state of drugging RNA shows a field on the brink of a breakthrough. New tools like AI and new companies specifically aimed at drugging RNA promise to move the field forward and develop new therapeutic strategies.

Outsourcing Bioinformatics Analysis: How Bridge Informatics Can Help

Groundbreaking studies like these are made possible by technological advances making biological data generation, storage, and analysis faster and more accessible than ever before. From pipeline development and software engineering to deploying existing bioinformatics tools, Bridge Informatics can help you on every step of your research journey.


As experts across data types from leading sequencing platforms, we can help you tackle the challenging computational tasks of storing, analyzing, and interpreting genomic and transcriptomic data. Bridge Informatics’ bioinformaticians are trained bench biologists, so they understand the biological questions driving your computational analysis. Click here to schedule a free introductory call with a member of our team.

Challenges of Drugging RNA

You’ve heard of RNA-based therapies (think mRNA vaccines), but the newest player in RNA-based therapeutics involves targeting existing RNA, rather than introducing beneficial RNA into the body. RNA was long believed to be too polar and solvent-exposed to be a viable target for small-molecule drugs. However, it is now known that RNA molecules contain secondary structures that small molecules can, and do, bind.

Drugging RNA is appealing for a number of reasons. Perhaps the most compelling reason is that 80% of the genome encodes “non-coding” RNA of still-unknown function, compared to just 3% of the genome encoding proteins (which are first transcribed as mRNA). Of those proteins, roughly 85% of them are still considered “undruggable.”

In spite of the promise of RNA therapeutics increasing the landscape of druggable targets by nearly two orders of magnitude, very few RNA drugs have been discovered, let alone come to therapeutic fruition. In a recent news feature in Nature Biotechnology, Ken Garber explored the challenges and opportunities for drugging RNA.

Current Approaches

Companies in the RNA drug space have yet to release detailed information on their discovery processes, but a few key directions have emerged. The first target is splicing, the process of splicing out (removing) introns from pre-mRNA transcripts. When mRNA is initially transcribed, it contains introns, regions of non-coding DNA that are spliced out to allow the coding regions, or exons, to join. Exons can also be spliced out in a process called alternative splicing, where the same pre-mRNA can yield different mature mRNAs depending on which exons are removed, yielding proteins with different functions.

The only currently available drug that targets RNA is Evrysdi (risdiplam), which is approved for spinal muscular atrophy (SMA). Evrysdi targets the RNA/protein splicing complex to splice an exon into SMA2, a usually non-functional gene that is subsequently activated and can compensate for the mutation of SMA1, the cause of SMA. The current workflow for discovering drugs that can alter splicing and/or RNA levels involves random in vitro screening of compounds looking for desired splicing outcomes. Compounds are then optimized using structural biology tools and specificity and efficiency are determined via RNA sequencing (RNA-seq). There is yet to be a proof-of-concept for drugging mature mRNA after the splicing process.

Phenotypic screens like the pipeline described above look for desired outcomes without knowing the target. Companies are also pursuing target-based screens, attempting to increase the odds of getting a hit and removing the uncertainty of determining the affected RNA in a phenotypic screen. Target-based screens look for compounds that interact with known disease-related RNAs. However, a major challenge of this approach is the ability of many compounds to bind RNA non-specifically or to bind and have no biological effect, requiring laborious functional assays to rule out candidates.

AI and Future Developments

Two approaches are promising to bring the field of RNA drugs closer to fruition. The first is the development of AI tools to predict the best RNA structures for small molecules to bind to. The company Atomic AI is developing a model specifically for applications to drug discovery.

The second approach is the development of RNA degraders. These compounds circumvent the search for ideal binding targets to affect function by simply eliminating any RNA they bind. The ability of these compounds to often bind multiple RNAs carries risks of toxicity, but RNA-seq allows researchers to weed out nonspecific binders.

Taken together, the current state of drugging RNA shows a field on the brink of a breakthrough. New tools like AI and new companies specifically aimed at drugging RNA promise to move the field forward and develop new therapeutic strategies.

Outsourcing Bioinformatics Analysis: How Bridge Informatics Can Help

Groundbreaking studies like these are made possible by technological advances making biological data generation, storage, and analysis faster and more accessible than ever before. From pipeline development and software engineering to deploying existing bioinformatics tools, Bridge Informatics can help you on every step of your research journey.


As experts across data types from leading sequencing platforms, we can help you tackle the challenging computational tasks of storing, analyzing, and interpreting genomic and transcriptomic data. Bridge Informatics’ bioinformaticians are trained bench biologists, so they understand the biological questions driving your computational analysis. Click here to schedule a free introductory call with a member of our team.


Jane Cook, Biochemist & Content Writer, Bridge Informatics

Jane Cook, the leading Content Writer for Bridge Informatics, has written over 100 articles on the latest topics and trends for the bioinformatics community. Jane’s broad and deep interdisciplinary molecular biology experience spans developing biochemistry assays to genomics. Prior to joining Bridge, Jane held research assistant roles in biochemistry research labs across a variety of therapeutic areas. While obtaining her B.A. in Biochemistry from Trinity College in Dublin, Ireland, Jane also studied journalism at New York University’s Arthur L. Carter Journalism Institute. As a native Texan, she embraces any challenge that comes her way. Jane hails from Dallas but returns to Ireland any and every chance she gets. If you’re interested in reaching out, please email [email protected] or [email protected].

Share this article with a friend

Create an account to access this functionality.
Discover the advantages