Скачать с ютуб DiffDock: Diffusion Steps, Twists and Turns for Molecular Docking and Beyond! в хорошем качестве

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

presented on March 8th 2023 by Gabriele Corso, Bowen Jing, and Hannes Stärk abstract: Predicting the binding structure of a small molecule ligand to a protein is critical to drug design. Unlike previous work, we frame molecular docking as a generative modeling problem and develop DiffDock, a diffusion generative model over the non-Euclidean manifold of ligand poses. Empirically, DiffDock significantly outperforms the previous state-of-the-art traditional docking and deep learning methods on both crystal and computationally folded structures.