BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260421T090513Z
LOCATION:Plenary Room (Bldg. 6 - 001)
DTSTART;TZID=Europe/Stockholm:20260629T193300
DTEND;TZID=Europe/Stockholm:20260629T193400
UID:submissions.pasc-conference.org_PASC26_sess124_pos141@linklings.com
SUMMARY:Exploring Performance and Efficiency of State-Of-The-Art Deep Lear
 ning Protein Structure Prediction Frameworks on the Frontier Exascale Supe
 rcomputer
DESCRIPTION:Verónica G. Melesse Vergara, Elijah MacCarthy, Asim YarKhan, J
 ohn Holmen, Manesh Shah, Érica Teixeira Prates, and Dan Jacobson (Oak Ridg
 e National Laboratory)\n\nAccurately predicting the structure of a protein
  has been a long standing and extremely challenging problem in biology. In
  recent years, the rapid evolution and adoption of artificial intelligence
  have made the prediction of protein structures leveraging deep learning f
 rameworks with accuracy rivaling that of experimental crystal structures p
 ossible. These advances are key to understanding protein function and play
  a central role in accelerating the drug discovery process. As the number 
 of frameworks available continues to grow and improved versions emerge, de
 termining which tool is best suited for an experiment has become increasin
 gly challenging.\n\nThis study presents an in-depth performance and effici
 ency comparison across AlphaFold3, AF3Complex, and Boltz-2 on the Oak Ridg
 e Leadership Computing Facility’s Frontier supercomputer. The evaluation c
 ompares the performance, accuracy, energy and power consumption of each mo
 del across a predefined set of three biomolecule categories: (i) proteins 
 with long intrinsically disordered regions, (ii) proteins with functional 
 modified or mutated residues, and (iii) off-target effects in multimers.\n
 \nThe results from this work and the lessons learned provide practical gui
 dance for selecting appropriate protein structure prediction frameworks un
 der performance and energy constraints and can be useful in the evaluation
  of future versions of the models discussed.\n\n
END:VEVENT
END:VCALENDAR