BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:AI Center x IBI - Distinguished Seminar Series - Prof. Fabian Thei
 s
DTSTART:20251118T141500
DTEND:20251118T151500
DTSTAMP:20260406T224206Z
UID:21ec0484a71233efa7872a43ba09dd4728574fe31075abdaaa78bed1
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Dr. Dr. Fabian J. Theis\nThe talk is co-organized by th
 e EPFL AI Center and the Institute of Bioengineering as part of their di
 stinguished research seminar series and BioE series.\n\nHosting professors
 : Prof. Maria Brbic & Prof. Raphael Gottardo\n\nTitle\nDecoding cellular s
 ystems: From observational atlases to generative interventions\n\nAbstract
 \nOver the past decade\, the field of computational cell biology has under
 gone a transformation — from cataloging cell types to modeling how cells
  behave\, interact\, and respond to perturbations. In this talk\, I will r
 eview and explore how machine learning is enabling this shift\, focusing o
 n two converging frontiers: integrated cellular mapping and actionable gen
 erative models. I’ll begin with a brief overview of recent advances in r
 epresentation learning for atlas-scale integration\, highlighting work acr
 oss the Human Cell Atlas and beyond. These efforts aim to unify diverse si
 ngle-cell and spatial modalities into shared manifolds of cellular identit
 y and state. As one example\, I will present our recent multimodal atlas o
 f human brain organoids\, which integrates transcriptomic variation across
  development and lab protocols. From there\, I’ll review the emerging la
 ndscape of foundation models in single-cell genomics\, including our work 
 on Nicheformer\, a transformer trained on millions of spatial and dissocia
 ted cells. These models offer generalizable embeddings for a range of task
 s—but more importantly\, they set the stage for predictive modeling of b
 iological responses. I’ll close by introducing perturbation models lever
 aging generative AI to model interventions on these systems. As example I 
 will show Cellflow\, a generative framework that learns how perturbations 
 such as drugs\, cytokines or gene edits — shift cellular phenotypes. It 
 enables virtual experimental design\, including in silico protocol screeni
 ng for brain organoid differentiation. This exemplifies a move toward mode
 ls that not only interpret biological systems but help shape them.\n\nBio\
 nProf. Dr. Dr. Fabian J. Theis is internationally recognized for pioneerin
 g work at the interface of artificial intelligence\, machine learning\, an
 d biomedicine. As Head of the Computational Health Center at Helmholtz Mun
 ich and Chair for Mathematical Models of Biological Systems at the Technic
 al University of Munich\, he leads cutting-edge research on multimodal dat
 a integration\, single-cell and spatial omics\, and AI-powered modeling of
  cell states in health and disease.\nA founding force behind Helmholtz.AI 
 and co-director of several national and European AI initiatives\, Theis pl
 ays a key role in shaping the biomedical AI landscape. He is a core contri
 butor to the Human Cell Atlas and has driven the development of widely ado
 pted computational tools in the life sciences.\nHis achievements have been
  recognized with numerous honors\, including the Gottfried Wilhelm Leibniz
  Prize (2023)\, the ISCB Innovator Award (2025)\, and an ERC Advanced Gran
 t (2022). In 2025\, he was elected to the German National Academy of Scien
 ces Leopoldina and appointed Chair of the Bavarian AI Council.\nBeyond aca
 demia\, Theis actively advises biotech companies and drives translational 
 AI research towards clinical applications and precision medicine.
LOCATION:SV 1717 https://plan.epfl.ch/?room==SV%201717 https://epfl.zoom.u
 s/j/62488670473?pwd=7kG1mteJajIwtFZXaBoRrTOZtnBQ32.1
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR