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:20260421T090512Z
LOCATION:Plenary Room (Bldg. 6 - 001)
DTSTART;TZID=Europe/Stockholm:20260629T194300
DTEND;TZID=Europe/Stockholm:20260629T194400
UID:submissions.pasc-conference.org_PASC26_sess124_pos143@linklings.com
SUMMARY:An Integrated HPC Workflow for AI-Driven Immunogenic Peptide Predi
 ction
DESCRIPTION:Cathrine Bergh (KTH Royal Institute of Technology), Leonardo S
 alicari (CINECA), Danai Kotzampasi and Victor Reys (Utrecht University), N
 arendra Kumar (National Institute of Immunology), Archana Achalere and Sun
 itha Manjari Kasibhatla (Center for the Development of Advanced Computing)
 , Alessandra Villa (KTH Royal Institute of Technology), Uddhavesh Sonavane
  (Center for the Development of Advanced Computing), and Alexandre Bonvin 
 (Utrecht University)\n\nImmunogenic peptides play important roles as drive
 rs for the adaptive immune response - our bodies' ultimate protection agai
 nst infections and cancers. Parts of these peptides, called epitopes, are 
 recognized by either major histocompatibility complexes or antibodies, whi
 ch then interact with T-cells or B-cells, respectively. Identifying and de
 signing these epitopes is crucial for immunotherapy and vaccine developmen
 t, yet remains challenging due to the vast possibilities in sequence combi
 nations, limited experimental data, and the need to understand detailed at
 omic interactions and how they contribute to binding affinities. While AI 
 tools, docking, and molecular dynamics simulations address parts of this p
 roblem, no single method is sufficiently accurate for practical vaccine de
 velopment.\nWe present an integrated computational workflow for AI-driven 
 immunogenic peptide prediction designed for high-performance computing sys
 tems. The workflow combines three components: generative AI that designs i
 mmunogenic peptides using data from sequence and immunogenicity databases;
  docking that builds molecular complexes; and molecular dynamics simulatio
 ns that characterize dynamic interactions and estimate binding affinities 
 through an alchemical mutation screen. Crucially, structural and thermodyn
 amic data from simulations feed back into the AI, iteratively improving pr
 edictions. Thus, by combining generative AI with physics-based methods, th
 is workflow aims to approach the prediction accuracy necessary for practic
 al vaccine development.\n\n
END:VEVENT
END:VCALENDAR