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:20210916T132450Z
LOCATION:Jean-Jacques Rousseau
DTSTART;TZID=Europe/Stockholm:20210706T143000
DTEND;TZID=Europe/Stockholm:20210706T150000
UID:submissions.pasc-conference.org_PASC21_sess139_msa309@linklings.com
SUMMARY:Embracing Complexity: Explainable-AI and Network-Based Filtering F
 or Mechanistic Understanding of Biological Systems
DESCRIPTION:Minisymposium\n\nEmbracing Complexity: Explainable-AI and Netw
 ork-Based Filtering For Mechanistic Understanding of Biological Systems\n\
 nJacobson, Sullivan, Kainer, Walker, Cliff...\n\nOne of the primary goals 
 in Systems Biology is to find genetic and omics architectures that are res
 ponsible for phenotypes or diseases.  The signal from such studies us
 ing traditional methods is subject to significant false positive and false
  negative rates.  However, information from existing data sources can
  be used to mitigate false-positive associations and improve the ability t
 o detect biological mechanisms from the data. We are using explainable-AI 
 approaches to build multiplex networks out of both publicly available and 
 novel datasests which can be used as biological filters for the results ob
 tained from Genome Wide Association Studies (GWAS).  Alleles showing 
 any associative signal in GWAS studies are mapped to genes with the use of
  Hi-C and eQTL data and the resulting geneset analyzed using Random Walk w
 ith Restart Filtering and Lines of Evidence algorithms (RWR-Filter and RWR
 -LOE). The algorithm leverages information from multiple sources allowing 
 for the ranking of biologically relevant genes strongly linked to the cand
 idate set as well as determining the presence or absence of strong biologi
 cal connections among the candidate genes. This has the benefit of screeni
 ng out false positives from the GWAS candidate set as well as providing bi
 ological and mechanistic context for the true positives.  We will pre
 sent results from several different domains of biology that show the power
  of these approaches.     \n\nDomain: CS and Math
 , Emerging Applications, Chemistry and Materials, Climate and Weather, Lif
 e Sciences
END:VEVENT
END:VCALENDAR