BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Machine learning as an assay for high-dimensional biology - Sara M
 ostafavi\, University of Washington\, USA
DTSTART:20220315T131500Z
DTEND:20220315T141500Z
UID:TALK165862@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION:"Join us on Zoom":https://zoom.us/j/99166955895?pwd=SzI0M3pMVE
 kvNmw3Q0dqNDVRalZvdz09\n\nThe growing availability of hundreds of differen
 t functional genomic assays across thousands of individuals presents an ex
 citing opportunity to understand the inner workings of biological systems\
 , and in turn identify molecular causes of disease. Toward this goal\, mac
 hine learning (ML) provides a powerful toolkit to integrate diverse datase
 ts\, uncovering hidden structure that can reveal how different layers of b
 iological systems relate to each other. However\, to harness the power of 
 ML for biology\, we need to be able to tune it so to distinguish meaningfu
 l structure from those that arise because of artifact and noise. In this t
 alk\, I’ll present our recent approaches for leveraging heterogeneous da
 ta to guide discovery of meaningful biological structure. In particular\, 
 I will first describe our deep learning approach to combining a large comp
 endium of epigenomic data\, in order to learn the relationship between non
 -coding genomic sequence and regulatory activity across the immune system 
 (Yoshida et al.\, Cell 2019\; Maslova et al.\, PNAS 2020).  I will then fo
 cus on the challenging task of understanding molecular causes of complex d
 isease. Here\, I will describe our techniques for revealing mechanistic in
 sights into Alzheimer’s disease by combining large and heterogeneous gen
 e expression datasets from the brain (Beebe-Wang et al.\, Nature Comm 2021
 ). Together\, these examples illustrate that ML is an important “assay
 ” that can synthesize information across multiple experimental assays\, 
 in order to uncover hidden complexities of biology and yield system level 
 hypotheses. \n\n*Bio:* Sara Mostafavi is an Associate Professor at the Pau
 l G. Allen School of Computer Science and Engineering at University of Was
 hington (UW). Previously (until Sept 2020)\, she was a faculty member at t
 he University of British Columbia (UBC)\, and Vector Institute (Toronto). 
  She is a recipient of a Canada Research Chair in Computational Biology\, 
 a Canada CIFAR Chair in Artificial Intelligence (CIFAR-AI)\, and is a CIFA
 R fellow in the Child and Brain Development program. Before UBC\, Sara did
  her postdoctoral fellowship with Daphne Koller at Stanford University and
  obtained a PhD in Computer Science from the University of Toronto in 2011
 . 
LOCATION:Zoom
END:VEVENT
END:VCALENDAR