BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230124T170804Z
LOCATION:C1-2-3
DTSTART;TZID=America/Chicago:20221116T083000
DTEND;TZID=America/Chicago:20221116T170000
UID:submissions.supercomputing.org_SC22_sess274_rpost157@linklings.com
SUMMARY:Self Supervised Solution for Analysis of Molecular Dynamics Simula
 tions In Situ
DESCRIPTION:Posters, Research Posters\n\nSelf Supervised Solution for Anal
 ysis of Molecular Dynamics Simulations In Situ\n\nSahni, Estrada\n\nWith m
 odern technology and High-Performance Computing (HPC), Molecular Dynamics 
 (MD) simulations can be task and data parallel. That means, they can be de
 composed into multiple independent tasks (i.e., trajectories) with their o
 wn data, which can be processed in parallel. Analysis of MD simulations in
 cludes finding specific molecular events and the conformation changes that
  a protein undergoes. However, the traditional analysis relies on the glob
 al decomposition of all the trajectories for a specific molecular system, 
 which can be performed only in a centralized way. We propose a lightweight
  self-supervised machine learning technique to analyze MD simulations in s
 itu. That is, we aim to speed up the process of finding molecular events i
 n the protein trajectory at run-time, without having to wait for the entir
 e simulation to finish. This allows us to scale the analysis with the simu
 lation.\n\nRegistration Category: Tech Program Reg Pass, Exhibits Reg Pass
END:VEVENT
END:VCALENDAR