Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking

About

Predicting the binding structure of a small molecule ligand to a protein -- a task known as molecular docking -- is critical to drug design. Recent deep learning methods that treat docking as a regression problem have decreased runtime compared to traditional search-based methods but have yet to offer substantial improvements in accuracy. We instead frame molecular docking as a generative modeling problem and develop DiffDock, a diffusion generative model over the non-Euclidean manifold of ligand poses. To do so, we map this manifold to the product space of the degrees of freedom (translational, rotational, and torsional) involved in docking and develop an efficient diffusion process on this space. Empirically, DiffDock obtains a 38% top-1 success rate (RMSD<2A) on PDBBind, significantly outperforming the previous state-of-the-art of traditional docking (23%) and deep learning (20%) methods. Moreover, while previous methods are not able to dock on computationally folded structures (maximum accuracy 10.4%), DiffDock maintains significantly higher precision (21.7%). Finally, DiffDock has fast inference times and provides confidence estimates with high selective accuracy.

Gabriele Corso, Hannes St\"ark, Bowen Jing, Regina Barzilay, Tommi Jaakkola• 2022

Related benchmarks

TaskDatasetResultRank
Flexible blind self-dockingPDBbind v2020 (unseen protein receptors)
Ligand RMSD % < 2Å Success Rate17.2
24
Blind DockingPDBBind Apo ESMFold proteins generated (test)
Top-1 RMSD < 2Å Acc21.7
21
Molecular DockingPDBBind (unseen receptors)
Top-1 RMSD < 2Å (%)20.8
17
Flexible blind self-dockingPDBbind v2020 (test complexes recorded after 2019)
Ligand RMSD (25th Pctl)1.5
12
Blind DockingPDBBind Holo crystal proteins (test)
Top-1 RMSD < 2Å (%)0.382
11
Molecular DockingPDBBind Full (test)
Top-1 Success Rate (2Å)38.2
8
Showing 6 of 6 rows

Other info

Code

Follow for update