P4ward: an automated modelling platformfor Protac ternary complexes
Jofily, P.; Kalyaanamoorthy, S.
Show abstract
Proteolysis Targeting Chimeras (Protacs) are a new class of drugs which promote degradation of a protein of interest (POI) by hijacking the Ubiquitin-Proteasome system. Struc tural knowledge of an E3 ligase: Protac:POI ternary complex is required for Protac rational design, and computational modelling of such heteromeric complex structures is nontrivial. To date, few programs have been developed to address this challenge, however, there remains a need for readily accessible tools that can significantly improve ternary complex modelling accuracy. Particularly, programs that can also support the screening phase of Protac discovery, where speed and the ability to test multiple Protacs is essential to advance the field of Protac therapeutics. To bridge these gaps, we present P4ward, a free and fully automated Protac ternary complex modelling pipeline. P4ward achieves a hit-rate of 76.5% with an average rank of 7.26, and substantially reduces the rank of the near-native pose by 73-98% compared to earlier programs. We believe that P4ward could be a user-friendly, fast, and effective tool for gaining atomistic insights necessary for Protac modelling and optimization.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- ArtiDock: accurate Machine Learning approach to protein-ligand docking optimized for high-throughput virtual screening 98%
- Sampling and ranking of protein conformations using machine learning techniques do not improve quality of rigid protein-protein docking 97%
- Fast Local Alignment of Protein Pockets (FLAPP): A system-compiled program for large-scale binding site alignment 96%
Similar papers in this journal
- Improved protein complex prediction with AlphaFold-multimer by denoising the MSA profile 96%
- Revisiting the \"satisfaction of spatial restraints\" approach of MODELLER for protein homology modeling 96%
- Fast and versatile sequence-independent protein docking for nanomaterials design using RPXDock 96%
Similar papers in this journal
- NRGSuite-Qt: A PyMOL plugin for high-throughput virtual screening, molecular docking, normal-mode analysis, the study of molecular interactions and the detection of binding-site similarities 96%
- A Random Forest Classifier for Protein-Protein Docking Models 96%
- Estimating Protein Complex Model Accuracy Using Graph Transformers and Pairwise Similarity Graphs 96%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.