BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
PRODID:-//Missouri State University/Calendar of Events//EN
CALSCALE:GREGORIAN
X-WR-TIMEZONE:America/Chicago
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
DTSTART:20070311T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
TZNAME:CDT
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
DTSTART:20071104T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
TZNAME:CST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:043bc1c9-e47b-413c-82fc-cf4c7e22dc41.234353@calendar.missouristate.edu
CREATED:20240220T144029Z
LAST-MODIFIED:20240220T144029Z
LOCATION:
SUMMARY:PAMS Seminar: "DiffDock: Diffusion Steps\, Twists\, and Turns for 
 Molecular Docking" by Hannes Stärk &amp; Gabriele Corso
DESCRIPTION:Hannes Stärk &amp; Gabriele CorsoMassachusetts Institute of Techno
 logyComputer Science &amp; Artificial Intelligence Laboratory\n\n\nAbstract:\
 n\n\n\n\n\nMolecular docking\, the process of predicting how small molecu
 le ligands bind to proteins\, is pivotal in drug design. Our work introdu
 ces a novel perspective by conceptualizing molecular docking as a generat
 ive modeling challenge. We present DiffDock\, a diffusion generative mode
 l that operates on the complex\, non-Euclidean manifold of ligand poses\,
  efficiently navigating through the translational\, rotational\, and tors
 ional degrees of freedom essential for accurate docking. Our empirical re
 sults showcase DiffDock's superiority\, achieving a 38% top-1 success rat
 e (RMSD&lt;2Å) on the PDBBind dataset\, markedly surpassing both traditional
  (23%) and other deep learning methodologies (20%). Notably\, DiffDock de
 monstrates remarkable performance on computationally folded structures\, 
 achieving more than double the accuracy of existing methods. This talk wi
 ll delve into the intuition and methodology behind DiffDock\, and its str
 engths and limitations.\n\n\nHannes and Gabriele are PhD students at MIT 
 in the CS and AI Laboratory (CSAIL).\n\n\nThis is a Zoom seminar: 915 207
 2 1543
X-ALT-DESC;FMTTYPE=text/html:&lt;html&gt;&lt;head&gt;&lt;title&gt;&lt;/title&gt;&lt;/head&gt;&lt;body&gt;&lt;p&gt;&lt;b
 &gt;Hannes Stärk &amp;amp\; Gabriele Corso&lt;br&gt;&lt;/b&gt;&lt;b&gt;Massachusetts Institute of 
 Technology&lt;br&gt;&lt;/b&gt;&lt;strong&gt;Computer Science &amp;amp\; Artificial Intelligence
  Laboratory&lt;br&gt;&lt;/strong&gt;&lt;/p&gt;\n&lt;p&gt;Abstract:&lt;/p&gt;\n&lt;p&gt;&lt;/p&gt;\n&lt;p&gt;Molecular doc
 king\, the process of predicting how small molecule ligands bind to prote
 ins\, is pivotal in drug design. Our work introduces a novel perspective 
 by conceptualizing molecular docking as a generative modeling challenge. 
 We present DiffDock\, a diffusion generative model that operates on the c
 omplex\, non-Euclidean manifold of ligand poses\, efficiently navigating 
 through the translational\, rotational\, and torsional degrees of freedom
  essential for accurate docking. Our empirical results showcase DiffDock'
 s superiority\, achieving a 38% top-1 success rate (RMSD&amp;lt\;2Å) on the P
 DBBind dataset\, markedly surpassing both traditional (23%) and other dee
 p learning methodologies (20%). Notably\, DiffDock demonstrates remarkabl
 e performance on computationally folded structures\, achieving more than 
 double the accuracy of existing methods. This talk will delve into the in
 tuition and methodology behind DiffDock\, and its strengths and limitatio
 ns.&lt;/p&gt;\n&lt;p&gt;Hannes and Gabriele are PhD students at MIT in the CS and AI 
 Laboratory (CSAIL).&lt;/p&gt;\n&lt;p&gt;This is a Zoom seminar: 915 2072 1543&lt;/p&gt;\n&lt;p
 &gt;&lt;/p&gt;&lt;/body&gt;&lt;/html&gt;
DTSTART;TZID=America/Chicago:20240229T160000
DTEND;TZID=America/Chicago:20240229T170000
SEQUENCE:0
URL:https://physics.missouristate.edu/seminars.htm
CATEGORIES:Public,Alumni,Current Students,Faculty,Future Students,Staff
END:VEVENT
END:VCALENDAR