Protein Docking（GeoDock）
1 Introduction
GeoDock1 is a novel multi-track iterative transformer network designed to address limitations in conventional protein-protein docking algorithms and existing deep learning methods. It is capable of predicting docked structures from separate docking partners, allowing for flexibility at the protein residue level to accommodate conformational changes upon binding. GeoDock attains an average inference speed of under one second on a single GPU, enabling its application in large-scale structure screening.
Figure 1. The overall architecture of GeoDock.
Figure 2. The performance of GeoDock.
2 Parameters
- partner1: The partner1 Protein PDB File.
- partner2: The partner2 Protein PDB File.
- output name: The output name.
3 Results Explanation
GeoDock predicts the conformation of the complex after docking with partner1 and partner2.
4 Reference
[1] Chu LS, Ruffolo JA, Harmalkar A, Gray JJ. Flexible Protein-Protein Docking with a Multi-Track Iterative Transformer. bioRxiv [Preprint]. 2023 Jul 1:2023.06.29.547134. Update in: Protein Sci. 2024 Feb;33(2):e4862. PMID: 37425754; PMCID: PMC10327054. https://doi.org/10.1101/2023.06.29.547134