Advancing Targeted Protein Degradation via Multiomics Profiling and Artificial Intelligence

Area of Science:

• Biochemistry
• Drug Discovery
• Proteomics

Background:

• Limited druggability of the human proteome (approx. 20%) restricts therapeutic options.
• Targeted protein degradation (TPD) emerges as a promising strategy to address undruggable targets.
• TPD utilizes small molecules to induce proximity between a target protein and an E3 ligase, leading to protein degradation.

Purpose of the Study:

• To review current challenges in targeted protein degradation.
• To explore the role of multiomics profiling and AI/ML in advancing TPD.
• To propose a roadmap for future TPD development.

Main Methods:

• Perspective and review of current literature and emerging technologies.
• Discussion of multiomics data integration.
• Exploration of artificial intelligence and machine learning applications in drug discovery.

Main Results:

• Identified key challenges in TPD, including target specificity and delivery.
• Highlighted the potential of multiomics and AI/ML to accelerate degrader design and discovery.
• Outlined a strategic roadmap for overcoming TPD limitations.

Conclusions:

• TPD represents a significant advancement in drug discovery, expanding the druggable proteome.
• Multiomics and AI/ML are crucial for unlocking the full potential of TPD.
• The discussed roadmap is applicable to small-molecule degraders and other proximity-inducing modalities.