BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:"AI in chemistry and beyond: ML for modeling molecular interaction
 s: DiffDock as example for docking prediction" seminar by Hannes Stärk
DTSTART:20230418T151500
DTEND:20230418T161500
DTSTAMP:20260930T213413Z
UID:6026cbe19c2d881f84f6f544db14941d8c1cce4c886735580b655189
CATEGORIES:Conferences - Seminars
DESCRIPTION:Hannes Stärk is a PhD student at MIT in the CS and AI Laborat
 ory (CSAIL) co-advised by Tommi Jaakkola and Regina Barzilay.\nWe will dis
 cuss the use of machine learning methods for modeling molecular interactio
 ns with a focus on protein-ligand docking. Predicting the binding structur
 e of a small molecule ligand to a protein -- a task known as molecular doc
 king -- is critical to drug design. Recent deep learning methods that trea
 t docking as a regression problem have decreased runtime compared to tradi
 tional 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-E
 uclidean 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.
LOCATION:https://epfl.zoom.us/j/68447908297?pwd=OU5JUGJUSUhZc0ZNYjQ2WENvYl
 NRdz09#success
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR