BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:iCalendar-Ruby
BEGIN:VEVENT
CATEGORIES:Lectures & Presentations
DESCRIPTION:Bayesian Variable Selection for Compositional Microbiome Data\n
 \nOngoing advancements in microbiome profiling have provided unprecedented 
 insights into the\nmolecular dynamics of microbial communities\, sparking a
  surge of interest in uncovering the\nmicrobiome’s critical role in human h
 ealth. Identifying microbial features linked to clinical\noutcomes\, howeve
 r\, remains challenging due to the high-dimensional\, sparse\, and composit
 ional nature of microbiome data. Additionally\, many microbial taxa\, altho
 ugh classified as distinct\, may share functional roles\, complicating trad
 itional variable selection methods.\nTo address this\, we developed two com
 plementary Bayesian frameworks. Our first\napproach\, BRACE\, provides a un
 ified nonparametric approach for data-adaptive feature\naggregation and sel
 ection. By clustering regression coefficients\, BRACE identifies groups of 
 taxa with similar functional impacts\, yielding interpretable models and ef
 fective dimension reduction without relying on external information. In con
 trast\, our second approach\, GRACE\, investigates the role of external fea
 ture similarity graphs. It combines variable selection with outcome-driven 
 graph learning\, characterizing how recovery of outcome-relevant networks c
 hanges when guided by external\, outcome-agnostic graphs such as phylogeny 
 or co-occurrence. Both methods explicitly respect compositionality and have
  shown strong performance in oral microbiome applications\, together offeri
 ng new strategies for interpretable regression models in compositional data
  settings.
DTEND:20261114T202000Z
DTSTAMP:20260410T154724Z
DTSTART:20261114T193000Z
LOCATION:Coates Hall\, 145
SEQUENCE:0
SUMMARY:Experimental Statistics Seminar: Satabdi Saha Postdoctoral Fellow\,
  Department of Biostatistics\, The University of Texas MD Anderson Cancer C
 enter
UID:tag:localist.com\,2008:EventInstance_51135450740211
URL:https://calendar.lsu.edu/event/experimental-statistics-seminar-satabdi-
 saha-postdoctoral-fellow-department-of-biostatistics-the-university-of-texa
 s-md-anderson-cancer-center
END:VEVENT
END:VCALENDAR
