Back

P4ward: an automated modelling platformfor Protac ternary complexes

Jofily, P.; Kalyaanamoorthy, S.

2024-12-03 bioinformatics
10.1101/2024.11.28.625921 bioRxiv
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.

50% of probability mass above

"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.