Collected sources and patterns will appear here. Add from search, explore, or the patterns library.
(List<LigandPose>, Receptor) -> List<OptimizedLigandPose>
Optimize and score candidate ligand-receptor docking poses using a 3D convolutional neural network scoring function.
Problem it solves
Empirical scoring functions can miss complex non-covalent structural nuances captured by learned deep representation grids.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.