Bellerophon: An Automated Tool for PROTAC Decomposition

2026/04/10 by Giulia Apprato, Matteo Bertola, Amelia LOCATELLI +3 · 1 voice
Biochemistry, Genetics and Molecular Biology · Medicine · Chemistry · #Protein Degradation and Inhibitors #HER2/EGFR in Cancer Research #Click Chemistry and Applications

paper · pdf · doi:10.1021/acsmedchemlett.5c00769

openalex publication_date 2026/04/10 · openalex created_date 2026/04/11 · openalex updated_date 2026/06/15

Abstract

Proteolysis-targeting chimeras (PROTACs) represent a promising modality for targeted protein degradation, yet their structural complexity complicates systematic design and analysis. Bellerophon is a new computational tool that automatically decomposes PROTACs into their warhead, linker, and E3 ligase ligand directly from molecular structure. By enabling automated and standardized decomposition of degraders, the tool facilitates drug design at different levels: Bellerophon demonstrated versatility for moiety replacement (ARV-110), large-scale annotation (PROTAC-DB) and linker analysis (IRAK4 data set). The tool is freely available through a user-friendly web interface, with open-source code to encourage transparency and collaborative development in chemical biology and medicinal chemistry.

Citations

• PROTAC targeted protein degraders: the past is prologue
• Finding a needle in the haystack: ADME and pharmacokinetics/pharmacodynamics characterization and optimization towards orally available bifunctional protein degraders
• ChEMBL: a large-scale bioactivity database for drug discovery

Discussions

• Glad to have contributed to Bellerophon: an automated tool for PROTAC decomposition (warhead, linker, E3 ligand) ✔️ Rule-based, deterministic approach ✔️ Full atom conservation, no ML hallucinations [bsky, 0 points, 1 comments]

Related

• PROTAC-Splitter: A Machine Learning Framework for Automated Identification of PROTAC Substructures
• Advances in computational methods for PROTAC drug discovery
• Language model driven: a PROTAC generation pipeline with dual\n constraints of structure and property
• A Comprehensive Review of Emerging Approaches in Machine Learning for De Novo PROTAC Design
• PROflow: An iterative refinement model for PROTAC-induced structure prediction