BEGIN:VCALENDAR
PRODID:-//github.com/ical-org/ical.net//NONSGML ical.net 4.0//EN
VERSION:2.0
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:STANDARD
DTSTART:20241103T020000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250309T020000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
DESCRIPTION:Taming the Biomolecular Structure Revolution: Representation L
 earning for dynamics\, RNA\, and substructures Abstract: The post-AlphaFo
 ld biomolecular structure revolution has set off a wave of structure-awar
 e machine learning\, but most of that progress still rests on several con
 venient assumptions\, such as that one static structure is enough to desc
 ribe a protein\, that proteins are the workhorses of molecular function\,
  and that the rigid substructure units are a sufficient unit of analysis.
  Each is now under pressure. Protein dynamics\, the ensembles of conforma
 tions a protein samples to function\, break the single-structure assumpti
 on behind virtually every current encoder. RNA 3D structure\, governed by
  distinct biophysics and tightly coupled to function\, remains underserve
 d by tools built for proteins\, despite the therapeutic appeal of RNA tar
 geting. Finally\, much biomolecular function lives in cohesive substructu
 res\, including catalytic triads\, binding pockets\, and base-pairing net
 works\, that traditional encoders tend to dilute. I will discuss how our 
 group has approached these challenges with a unifying recipe: building bi
 ology-aware benchmarks that expose where current models break\, designing
  representations that respect the geometry\, sparsity\, and modularity of
  the data\, and reasoning at the substructure level as one important lens
  on where function actually lives. Taming this revolution\, I argue\, wil
 l hinge less on bigger models than on representation learning that embrac
 es richer modalities and biologically meaningful units of analysis. Carlo
 s Oliver\, PhD is an Assistant Professor at Vanderbilt University\, with 
 a joint appointment in the Departments of Molecular Physiology & Biophysi
 cs and Computer Science\, and a core member of the Vanderbilt Center for 
 AI in Protein Dynamics. His research group develops geometric deep learni
 ng methods for structural biology\, with a focus on RNA 3D structure\, pr
 otein conformational dynamics\, and functional substructure discovery in 
 biomolecules.\n\nSpeaker:\nCarlos Oliver\, PhD \n\nAdmission:\nFree\n\nFo
 od:\nLunch\n\nDetails URL:\nhttps://medicine.yale.edu/event/research-in-p
 rogress-or-rising-star-seminar-5-14/\n
DTEND;TZID=America/New_York:20260514T130000
DTSTAMP:20260514T210359Z
DTSTART;TZID=America/New_York:20260514T120000
LOCATION:Zoom\, URL: https://yale.zoom.us/j/97037559157
SEQUENCE:0
STATUS:Confirmed
SUMMARY:Research in Progress | Rising Star Seminar
UID:517863b5-9046-4249-a744-2faa639059ed
END:VEVENT
END:VCALENDAR