BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC/SV Colloquium: Machine Learning-Guided Treatment Discovery and 
 Planning
DTSTART:20230227T100000
DTEND:20230227T110000
DTSTAMP:20260407T045654Z
UID:078553fd2b860315ac93711467848fde9ff2bebd8501d084474869d3
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Charlotte Bunne - ETH Zurich\nIC/SV Faculty candidate\n\nA
 bstract\nIn recent years\, massively parallel high-throughput methods have
  changed the course of modern drug discovery. While providing us with an u
 nprecedented resolution into molecular processes\, they require scalable a
 nd principled algorithms that integrate the most recent insights from huma
 n biology\, are well aligned with the constrained nature of experiments\, 
 and incorporate the inherent structure of macromolecules and tissues. Thes
 e criteria have guided my research toward mathematically grounded deep lea
 rning solutions\, using notably optimal transport and geometric modeling. 
 In this seminar\, I will demonstrate how integrating these principles into
  the design of learning algorithms shifts our ability to predict heterogen
 eous patient treatment responses to the single-cell level\, model combinat
 ion therapies\, and trace developmental differentiation processes. These n
 ovel deep learning approaches not only achieve state-of-the-art quantitati
 ve improvements over prior works but also open new frontiers in a current 
 large-scale clinical study to predict treatment responses of unseen patien
 ts. Altogether\, my work on neural optimal transport and geometric deep le
 arning shows that innovations in the design of machine learning algorithms
  will be crucial for accelerating the discovery of therapeutics and propos
 ing personalized treatment plans to patients.\n\nBio\nCharlotte Bunne is a
  PhD student in Computer Science at ETH Zurich working with Andreas Krause
  and Marco Cuturi and currently a visiting researcher at the Broad Institu
 te of MIT and Harvard hosted by Anne Carpenter and Shantanu Singh. Before\
 , she worked with Stefanie Jegelka as a Master student at MIT. With a focu
 s on accelerating therapeutics discovery and proposing personalized treatm
 ent plans for patients\, she develops mathematically grounded deep learnin
 g solutions based on optimal transport and geometrical modeling. The neura
 l optimal transport methods she innovates prove successful within both the
  medical and the machine learning community: These tools are the current s
 tate-of-the-art in predicting dynamic single-cell responses of a patient a
 nd are a key ingredient of an ongoing clinical cohort study while at the s
 ame time receiving best paper awards at machine learning conference worksh
 ops at NeurIPS’18\, ICML’20\, and ICML’21. Throughout her studies\, 
 Charlotte has been a Fellow of the German National Academic Foundation. Sh
 e is a recipient of the ETH Medal.\n\nMore information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420 https://epfl.zoom.us/
 j/69212957435
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR