Artificial intelligence (AI) has significantly accelerated the entire process from drug discovery to clinical application by rapidly analyzing large amounts of biomedical data. AI technology, especially machine learning and deep learning algorithms, plays an increasingly important role in the development of RNA-targeted small molecule drugs.
Here we cite a review article that provides a comprehensive overview of AI in the field of RNA-targeted small molecule drug discovery, including recent advances, challenges, and future directions.
RNA-targeted small molecules are seen as an alternative to traditional protein-targeted drug discovery and have the potential to address unmet and emerging medical needs. Because only a small fraction (0.05%) of the human genome has been used for drug development, and this fraction corresponds to only about 10-15% of disease-related proteins, mRNAs encoding the remaining 85-90% of disease-related proteins could be prime targets for drug discovery. In addition, a large portion of the human genome is transcribed into ncRNAs, which may represent promising targets for small-molecule drug discovery.
Fig. 1. AI applications and tools in RNA-targeted small-molecule drug discovery. (Morishita E C.; et al. 2024)
AI identifies disease associations of ncRNAs that may not be immediately apparent from the large literature obtained experimentally. AI can also be used to analyze the large amount of ncRNA disease association experimental data stored in databases.
As an alternative to free energy minimization, machine learning methods have been used to extract energy parameters from databases of RNA sequences and their secondary structures.
AI tools can be used not only to predict the 3D structure of RNA directly, but also to evaluate the predicted 3D structure obtained by non-AI-based computational methods.
Some studies have begun to use AI technology to identify RNA binding sites.
Through high-throughput screening technology, AI can screen small molecules with strong binding to RNA targets from a large compound library.
Researchers have combined experimental data and machine learning algorithms to develop a variety of chemical libraries focused on RNA.
AI uses machine learning algorithms to construct QSAR/QSPR models to predict the biological activities and in vivo pharmacokinetic properties of small molecules, including absorption, distribution, metabolism, excretion and toxicity (ADMET).
Prediction of binding activity between small molecules and RNA by machine learning models.
Researchers have exploited the de novo design capabilities of AI to develop small molecules with higher affinity and selectivity for RNA targets.
Numerous studies have shown that AI has great potential and a scientific basis for promoting the development of RNA-targeted small-molecule drugs. With the continuous progress of technology and the increasing amount of data, AI is expected to play a more key role in this field and promote the discovery and development of more drugs.
Protheragen-ING AI-Pharma is committed to using advanced AI technology to accelerate the development process of RNA-targeted drugs, reduce costs, and improve success rates. If you are interested in our services or have a question, please feel free to contact us for more details.
Original Article:
Morishita E C.; et al. (2024). Recent applications of artificial intelligence in RNA-targeted small molecule drug discovery. Expert Opinion on Drug Discovery. 2024, 19(4): 415-431.
Services Related in the Article:
AI-powered Drug Discovery and Design
AI-assisted Drug High Throughput Screening
Therapeutic Applications of Small Nucleic Acid Drugs
Small Nucleic Acid Drugs CDMO
Small Molecule Drug CDMO
We harness the power of artificial intelligence to transform the landscape of drug discovery. Our mission is to accelerate the development of life-saving medicines by leveraging cutting-edge AI technologies.
