BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.openondemand.org//2025//talk//NYHCQF
BEGIN:VTIMEZONE
TZID:US/Eastern
BEGIN:DAYLIGHT
DTSTART:20240319T000000
TZNAME:EDT
TZOFFSETFROM:-0400
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241103T020000
RDATE:20251102T020000
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250309T030000
RDATE:20260308T030000
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:AlphaFold accessibility: an optimized open-source OOD app for Prot
 ein Structure Prediction - Vinay Saji Mathew [Pennsylvania State Universit
 y]\, William Lai [Cornell]
DTSTART;TZID=US/Eastern:20250319T160000
DTEND;TZID=US/Eastern:20250319T162500
DTSTAMP:20260911T133252Z
UID:pretalx-2025-NYHCQF@cfp.openondemand.org
DESCRIPTION:The AlphaFold AI system won the 2024 Chemistry Nobel Prize bec
 ause of its predictive achievements poised to revolutionize disease unders
 tanding and drug discovery. Initially released as open-source (and now pro
 prietary)\, researchers are working to improve the code to require less re
 sources and maintain open-source accessibility. We present an open-source 
 implementation of AlphaFold 2 & 3 that optimizes computational resource al
 location by intelligently separating CPU and GPU phases within a single OO
 D instance. This addresses a critical challenge to make AlphaFold more acc
 essible by minimizing idle GPU cycles. Benchmarking across three major clu
 sters (NCSA Delta\, Jetstream2\, and ROAR)\, we developed a user-friendly 
 OOD application that operates with maximum resource efficiency.
LOCATION:Tsai Auditorium (CGIS S010)
URL:https://cfp.openondemand.org/2025/talk/NYHCQF/
END:VEVENT
END:VCALENDAR