Advances in machine-learning approaches to RNA-targeted drug design

Area of Science:

• Biochemistry
• Computational Biology
• Pharmacology

Background:

• RNA molecules have critical cellular functions and are emerging as therapeutic targets.
• Artificial intelligence (AI) has shown success in various fields, prompting its application in drug design.
• Computer-aided drug design (CADD) is increasingly exploring RNA targets.

Purpose of the Study:

• To review recent advancements in computational modeling of RNA-small molecule interactions.
• To highlight the role of machine learning (ML) in RNA-targeted drug discovery.
• To discuss challenges and future directions in the field.

Main Methods:

• Review of current literature on ML applications in RNA-targeted drug discovery.
• Analysis of computational methodologies for modeling RNA-small molecule interactions.
• Discussion of data resource development and its impact.

Main Results:

• ML approaches for protein-targeted drug discovery are established but nascent for RNA targets.
• Scarcity of data is a primary challenge in ML-based RNA drug discovery.
• Development of curated databases is crucial for advancing the field.

Conclusions:

• AI and ML hold significant promise for discovering novel RNA-targeted therapeutics.
• Overcoming data limitations is key to unlocking the potential of ML in this area.
• The field is poised for rapid growth, opening new therapeutic avenues.