BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230831T095745Z
LOCATION:Dischma
DTSTART;TZID=Europe/Stockholm:20230626T123000
DTEND;TZID=Europe/Stockholm:20230626T130000
UID:submissions.pasc-conference.org_PASC23_sess175_pap107@linklings.com
SUMMARY:Causal Discovery and Optimal Experimental Design for Genome-Scale 
 Biological Network Recovery
DESCRIPTION:Paper\n\nAshka Shah (University of Chicago, Argonne National L
 aboratory); Arvind Ramanathan (Argonne National Laboratory, University of 
 Chicago); and Valerie Hayot-Sasson and Rick Stevens (University of Chicago
 , Argonne National Laboratory)\n\nCausal discovery of genome-scale network
 s is important for identifying pathways from genes to observable traits --
 e.g. differences in cell function, disease, drug resistance and others. Ca
 usal learners based on graphical models rely on interventional samples to 
 orient edges in the network. However, these models have not been shown to 
 scale up the size of the genome which on the order of 1e3-1e4 genes. We in
 troduce a new learner, SP-GIES, that jointly learns from interventional an
 d observational datasets and achieves almost 4x speedup against an existin
 g learner for 1,000 node networks. SP-GIES achieves an AUC-PR score of 0.9
 1 on 1,000 node networks, and scales up to 2,000 node networks -- this is 
 4x larger than existing works. We also show how SP-GIES improves downstrea
 m optimal experimental design strategies for selecting interventional expe
 riments to perform on the system. This is an important step forward in rea
 lizing causal discovery at scale via autonomous experimental design.\n\nDo
 main: Life Sciences\n\nSession Chair: Yan Liu (EPFL)
END:VEVENT
END:VCALENDAR