BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: Can we Design Any Biomolecule? From Binders to Asse
 mblies
DTSTART:20260316T101500
DTEND:20260316T111500
DTSTAMP:20260502T103209Z
UID:0d4ff91c6b8b754d8ae17e5653c6c95cd2c20db9399a7505565707e4
CATEGORIES:Conferences - Seminars
DESCRIPTION:Par : Hannes Stärk - MIT\nIC Faculty candidate\n\nAbstract\nT
 he vision is to build machine learning tools capable of designing any biom
 olecule: binders as starting points for therapeutics\, therapeutics with h
 igh selectivity and low immunogenicity\; assemblies as delivery vehicles f
 or drugs\; enzymes engineered to perform endosomal escape or degrade toxin
 s. Realizing this vision demands innovation at the level of core inference
  algorithms and machine learning methodology alike. As a central example\,
  I will present BoltzGen\, a framework for designing protein and peptide b
 inders against target biomolecules of any molecular modality. BoltzGen dis
 covers binders against targets with no existing bound structures\, demonst
 rated across eight diverse design campaigns with functional and affinity r
 eadouts spanning 26 targets. The binder modalities range from nanobodies t
 o disulfide-bonded peptides\; the targets\, from intrinsically disordered 
 proteins to small molecules. Notably\, we identified nanomolar-affinity pr
 otein and nanobody binders for six of ten novel targets bearing low struct
 ural similarity to any protein with a known bound partner\, a regime where
  prior methods falter. Several successful designs are now advancing into m
 ouse models and human cell lines to assess their efficacy against a range 
 of cancers. The talk closes by charting research trajectories toward the b
 roader ambition: the generative design of any biomolecule from binders to 
 assemblies.\n\nBio\nHannes Stark is a PhD Student at MIT advised by Regina
  Barzilay and Tommi Jaakkola. His works\, including DiffDock\, Dirichlet F
 low matching\, ProtComposer\, Boltz-2\, and BoltzGen\, develop new generat
 ive models and inference algorithms to understand and design biomolecules.
 \n\nMore information\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420 https://epfl.zoom.us/
 j/69134096548
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR