BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250627T060811EDT-6579UdvHjn@132.216.98.100
DTSTAMP:20250627T100811Z
DESCRIPTION:Challenges and opportunities for biomarker discovery when apply
 ing machine learning techniques to large RNA-Seq cohorts\n\nSebastien Lemi
 eux (University of Montreal)\n	Tuesday September 29\, 12-1pm\n	Zoom Link: ht
 tps://mcgill.zoom.us/j/91589192037\n\nAbstract: Over two decades of statis
 tical developments have allowed transcriptomics\, from microarrays to RNA-
 Seq\, to become an indispensable tool to characterize changes in expressio
 n profiles. Computationally\, a central step is the application of special
 ized parametric statistical tests such as DESeq2\, EdgeR or Voom to single
  out differentially expressed genes. In parallel\, several new tricks have
  been developed within the machine learning framework to facilitate the tr
 aining of high-dimensional classifiers that can take advantage of the whol
 e transcriptome characterizations. Unfortunately\, identifying biomarkers 
 from these trained classifiers has proven more difficult than expected. Th
 ese computational advances\, coupled with reduced costs and protocol stabi
 lization for RNA-Seq has led to the emergence of large cohorts of hundreds
  of high-quality RNA-Seq expression profiles. I will show\, using large da
 tasets developed to refine sub-typing of acute myeloid leukemia (AML)\, th
 at standard statistical tools reveal their inadequacy for the identificati
 on of biomarkers. I will present a novel approach to the identification of
  biomarkers based on machine learning principles that scales well with lar
 ge datasets.\n
DTSTART:20200929T160000Z
DTEND:20200929T170000Z
LOCATION:CA\, QC
SUMMARY:QLS Seminar Series - Sebastien Lemieux
URL:/qls/channels/event/qls-seminar-series-sebastien-l
 emieux-324795
END:VEVENT
END:VCALENDAR