BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Developing Approaches for Knowledge-Driven Protein 3D Structure Pr
 ediction: Next Steps Beyond AI
DTSTART:20260519T090000Z
DTEND:20260519T110000Z
DTSTAMP:20260518T155100Z
UID:indico-event-3830@indico.ijs.si
CONTACT:events@slaif.si
DESCRIPTION:Speakers: Yazan Haddad (Mendel University Brno\, CTO at Mendel
 FOLD)\n\nYazan Haddad\, CTO at MendelFOLD\, and Assistant Professor at Men
 del University in Brno  presents a knowledge-driven approach to protein 3
 D structure prediction as an alternative to current AI-based methods like 
 AlphaFold.\nThe talk highlights challenges such as high computational cost
 \, limited interpretability\, and difficulties with certain protein types.
  The proposed approach leverages genetic and biophysical principles\, incl
 uding amino acid residue pairing and constraint-based simulations\, to ena
 ble more interpretable and flexible structure prediction.\nAs deep learnin
 g approaches such as AlphaFold continue to redefine structural biology\, t
 heir limitations highlight persistent challenges\, including high computat
 ional demands\, dependence on homologous structural data\, limited interpr
 etability\, difficulty with orphan\, membrane\, multistate and disordered 
 proteins\, and insufficient sensitivity to mutation-driven structural chan
 ges.\nBy contrast\, we take a knowledge-driven approach to protein 3D stru
 cture and function prediction based on genetic and biophysical principles 
 of amino acid residue pairing (the proteomic code)\, rotameric/geometric s
 hapes\, and relay information system (RIS) mechanisms which represent inte
 rpretable fundamentals for protein 3D structure and function prediction me
 thodologies accessing constraint-driven simulation protocols. Further kno
 wledge gained by our approach and the broad scope of protein families acce
 ssible to our approach should also benefit future AI strategies.\nPredavan
 je bo v angleščini\, in sicer na Fakulteti za računalištvo in in infor
 matiko v Ljubljani.\n \n\nhttps://indico.ijs.si/event/3830/
IMAGE;VALUE=URI:https://indico.ijs.si/event/3830/logo-1596601024.png
LOCATION:Predavalnica P18 na UL FRI
URL:https://indico.ijs.si/event/3830/
END:VEVENT
END:VCALENDAR