โก Quick Summary
The study introduces DeepDegradome, an innovative AI-powered framework designed for the automated generation of PROTACs and small-molecule ligands targeting proteins. This method significantly enhances the diversity and effectiveness of drug discovery by eliminating the reliance on predefined warheads or E3 ligands.
๐ Key Details
- ๐ Framework: DeepDegradome
- ๐งฉ Methodology: Structure-aware design using a large fragment library
- โ๏ธ Docking Technique: iFitDock for initial binding fragment acquisition
- ๐ Performance: Higher predicted binding affinity and drug-like molecules compared to other AI models
๐ Key Takeaways
- ๐ก DeepDegradome automates the design of both ligands and PROTACs.
- ๐ Fragment assembly is based on the shape and physicochemical features of target protein pockets.
- ๐ Validation: Multiple potent inhibitors and PROTACs were successfully designed and validated.
- ๐ฌ X-ray crystallography confirmed the binding conformation of a synthesized compound.
- ๐ Targets: WDR5 and CDK9 proteins were specifically addressed in the study.
- ๐ Scalability: Offers a scalable and reliable tool for drug discovery.
- ๐ Drug discovery can benefit from the innovative approach of combining ligand and PROTAC design.
๐ Background
Targeted protein degradation has emerged as a promising strategy in drug discovery, particularly for challenging protein targets lacking well-defined binding sites. Traditional methods often limit the diversity of molecular architectures by relying on fixed ligands and linkers. The introduction of AI in this domain opens new avenues for innovation and efficiency in drug design.
๐๏ธ Study
The research presented in this study focuses on the development of DeepDegradome, a framework that leverages deep learning to automate the design of PROTACs and small-molecule ligands. By utilizing a comprehensive fragment library and an advanced docking method, the study aims to enhance the drug discovery process, particularly for proteins like WDR5 and CDK9.
๐ Results
The results demonstrated that DeepDegradome outperformed existing AI models by generating more valid, drug-like molecules with higher predicted binding affinities. The synthesized compounds showed excellent agreement between predicted and actual binding conformations, validated through X-ray crystallography, highlighting the framework’s effectiveness in practical applications.
๐ Impact and Implications
The introduction of DeepDegradome could significantly impact the field of drug discovery by providing a more efficient and innovative approach to designing PROTACs and ligands. This framework not only enhances the potential for discovering new drugs but also paves the way for addressing previously challenging protein targets, ultimately improving therapeutic outcomes.
๐ฎ Conclusion
The study showcases the transformative potential of AI in drug discovery through the development of DeepDegradome. By automating the design process and enhancing molecular diversity, this framework represents a significant advancement in the quest for effective therapeutics. Continued research and application of such technologies could lead to groundbreaking discoveries in the pharmaceutical landscape.
๐ฌ Your comments
What are your thoughts on the implications of AI in drug discovery? We would love to hear your insights! ๐ฌ Share your comments below or connect with us on social media:
DeepDegradome: A structure-aware deep learning framework for PROTAC and ligand generation against protein targets.
Abstract
Targeted protein degradation is a promising strategy for drug discovery, but designing effective PROTACs remains challenging, especially for proteins without well-defined binding sites. Current methods rely on modifying linkers between fixed ligands, which limits the diversity and innovation of the overall molecular architecture of PROTAC. Here, we introduce DeepDegradome, an AI-powered method that automates the structure-aware design of both small-molecule ligands and PROTACs. It employs a large fragment library constructed from public databases and applies an in-house docking method (iFitDock) to obtain initial binding fragments. DeepDegradome builds ligands by assembling these fragments based on the shape and physicochemical features of the target protein pocket. It can further construct PROTACs from these generated ligands, eliminating the dependency on predefined warheads or E3 ligands. Compared to other AI models, DeepDegradome produces more valid, drug-like molecules with higher predicted binding affinity. We demonstrate DeepDegradome’s effectiveness by designing and validating multiple potency inhibitors and PROTACs for two protein targets: WDR5 and CDK9. One synthesized compound showed excellent agreement between predicted and actual binding conformation confirmed by X-ray crystallography. By combining ligand and PROTAC design in one system, DeepDegradome offers a scalable and reliable tool for discovering new drugs against protein targets.
Author: [‘Hu Q’, ‘Cao Y’, ‘Ren P’, ‘Zhang X’, ‘Li F’, ‘Zhang X’, ‘Cai F’, ‘Zhang R’, ‘Zhou Y’, ‘Mei L’, ‘Bai F’]
Journal: Proc Natl Acad Sci U S A
Citation: Hu Q, et al. DeepDegradome: A structure-aware deep learning framework for PROTAC and ligand generation against protein targets. DeepDegradome: A structure-aware deep learning framework for PROTAC and ligand generation against protein targets. 2026; 123:e2518248123. doi: 10.1073/pnas.2518248123