BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Large-Scale Causal Gene Regulatory Network Inference from Genetic 
 Interventions
DTSTART:20220912T113000
DTEND:20220912T123000
DTSTAMP:20260609T120425Z
UID:5393897ab481ab4d45407334a22ee02a643451f2441d4e34db3ec3b3
CATEGORIES:Conferences - Seminars
DESCRIPTION:Romain Lopez\npostdoctoral fellow at Genentech & Stanford Univ
 ersity\nAbstract: \n\nPooled genetic screens with single-cell transcripto
 mics readout promise to resolve the causal relationship between genes in a
  given population of cells. The most commonly employed statistical approac
 hes to process this data\, however\, mainly consist of regression. Because
  of potential confounding factors\, the results of such an analysis may no
 t be interpreted as the (causally) direct effect of a gene onto other gene
 s. Separately\, the field of causal discovery learning recently introduced
  many algorithms that are applicable to inferring gene regulatory networks
  from Perturb-seq data\, but most research has so far focused on relativel
 y small causal graphs\, with up to tens of nodes. Here\, we introduce the 
 notion of factor directed acyclic graphs (f-DAGs) as a way to restrict the
  search space to non-linear low-rank causal interaction models. Combining 
 this novel structural assumption with recent advances that bridge the gap 
 between causal discovery and continuous optimization\, we propose Differen
 tiable Causal Discovery of Factor Graphs (DCD-FG)\, a scalable implementat
 ion of f-DAG constrained causal discovery for high-dimensional interventio
 nal data. DCD-FG uses a Gaussian non-linear low-rank structural equation m
 odel and shows significant improvements compared to state-of-the-art metho
 ds in both simulations as well as a recent large-scale single-cell RNA seq
 uencing data set with hundreds of genetic interventions.\n\nBio:\nRomain L
 opez is a postdoctoral fellow with a joint appointment between Genentech R
 esearch and Early Development and Stanford University\, hosted by Aviv Reg
 ev & Jonathan Pritchard. He obtained a PhD degree in May 2021 from the dep
 artment of Electrical Engineering and Computer Sciences at UC Berkeley\, a
 dvised by Mike Jordan & Nir Yosef. His research interests lie at the inter
 section of statistics\, computation and modeling with a strong focus on bi
 ological applications. Romain developed scVI and several extensions\, a sc
 alable set of core analysis tools for single-cell omics data\, based on de
 ep generative models. He is a lead contributor to scvi-tools\, an open-sou
 rce library for deep probabilistic modeling of single-cell data. He also w
 orked on counterfactual inference and offline policy learning methods in c
 ollaboration with technology companies (Ant Financial\, 2018 & Amazon\, 20
 19). Before graduate school\, Romain obtained a Diplome d'Ingenieur and a 
 MSc in Applied Mathematics from Ecole polytechnique\, Palaiseau.
LOCATION:SV 1717 https://plan.epfl.ch/?room==SV%201717
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR