BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260627T040824EDT-8673MWgjI4@132.216.98.100
DTSTAMP:20260627T080824Z
DESCRIPTION:Join D2R for this hybrid seminar with Professor Carlos Oliver f
 rom Vanderbilt University about 'Structure-Based Machine Learning for RNA 
 Drug Discovery: The Story So Far'. \n\nRNA has emerged as a vast and under
 explored class of therapeutic targets\, yet RNA-targeted drug discovery ha
 s lagged behind its protein counterpart. The reasons are well-rehearsed: R
 NA structural data is scarce\, RNA-ligand interactions are governed by dis
 tinct biophysics\, and the machine learning toolkit that powered the prote
 in-folding revolution does not transfer cleanly to RNA. Specific small-mol
 ecule recognition of RNA is achievable\, but unlocking the potential of ma
 chine learning for RNA drug discovery will require specialized methods at 
 every step of the workflow.\n	\n	In this talk\, Prof Oliver will describe su
 ch a pipeline. In target discovery\, substructure-aware methods learn the 
 recurring structural building blocks of RNA and the binding pockets where 
 small molecules engage: graph representation learning recovers and expands
  known motif libraries\, and adaptive graph coarsening predicts druggable 
 binding sites that already support experimental virtual screens. In hit id
 entification\, structure-based virtual screening on coarse-grained\, base-
 pair-aware representations runs orders of magnitude faster than docking an
 d has produced the first experimentally validated hits from a structure-ba
 sed deep learning system. In evaluation\, shared benchmarking infrastructu
 re for RNA structure-function modeling\, alongside a recent field review p
 roposing standards for measuring drug-target specificity\, gives the commu
 nity common ground to compare approaches. The recurring theme is that resp
 ecting the modality\, through coarse-grained representations\, RNA-specifi
 c self-supervision\, and substructure-aware reasoning\, is what unlocks da
 ta efficiency and wet-lab translation.\n\nAgenda\n\n\n	\n		\n			10:30AM-10:35AM
 \n			Welcome\n				By Jérôme Waldispühl\, Associate Professor\, McGill University
 \n		\n		\n			10:35AM-11:15AM\n			Presentation\n				By Carlos Oliver\, Assistant Professo
 r at Vanderbilt University \n		\n		\n			11:15AM-11:30AM\n			\n				Q&A \n					Moderated by Jér
 ôme Waldispühl\n			\n		\n	\n\n\nRegister\n\nRegister here to receive the Zoom li
 nk\n\nFor those attending in-person\, confirmation emails will be provided
  to registered participants a few days before the event. Space is limited!
  \n\nRegister here to attend in person at D2R Office\n
DTSTART:20260521T143000Z
DTEND:20260521T153000Z
SUMMARY:Seminar Series | Carlos Oliver 'Structure-Based Machine Learning fo
 r RNA Drug Discovery: The Story So Far'
URL:https://www.mcgill.ca/dna-to-rna/channels/event/seminar-series-carlos-o
 liver-structure-based-machine-learning-rna-drug-discovery-story-so-far-372
 904
END:VEVENT
END:VCALENDAR