BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:2897@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20190426T140000
DTEND;TZID=Europe/Paris:20190426T150000
DTSTAMP:20190411T120000Z
URL:https://www.i2m.univ-amu.fr/evenements/kernel-methods-for-genomic-data
 -fusion-a-application-of-geometric-kernel-data-fusion-in-protein-fold-reco
 gnition-and-gene-prioritization/
SUMMARY: (...): Kernel methods for genomic data fusion: a application of ge
 ometric kernel data fusion in protein fold recognition and gene prioritiza
 tion
DESCRIPTION:: It has been shown that while a single genomic data source mig
 ht not be sufficiently informative\, fusing several complementary genomic 
 data sources delivers more accurate predictions. In this regard\, genomic 
 data fusion has garnered much interest across biological research communit
 ies. Consequently\, finding efficient and effective techniques for fusing 
 heterogeneous biological data sources has gained growing attention over th
 e past few years.-Kernel methods\, in particular\, are an interesting clas
 s of techniques for data fusion. We look into the possibility of using the
  geometric mean of matrices instead of the arithmetic mean for kernel data
  fusion. While computing geometric means of matrices is challenging\, it h
 ints at an intriguing research direction in data fusion. We will discuss t
 he application of geometric kernel data fusion in protein fold recognition
  and gene prioritization.-Our kernel data fusion frameworks offer a signif
 icant improvement over multiple kernel learning approaches proposed for pr
 otein fold recognition. Furthermore\, our kernel-based protein fold recogn
 izers\, which were developed by fusing twenty-six different protein featur
 es through the geometric mean of their corresponding kernel matrices\, imp
 rove the state of the art.-Moreover\, the experimental results demonstrate
  that geometric kernel fusion can effectively improve the accuracy of the 
 state-of-the-art kernel fusion models for prioritizing disease-associated 
 genes. In particular\, for gene prioritization\, we design a geometric ker
 nel data fusion model using the log-Euclidean mean of kernel matrices\, wh
 ich offers scalability to large data sets. Moreover\, to deliver more accu
 rate gene prioritization predictions\, we introduce a heuristic weighted a
 pproach for integrating kernel matrices using a log-Euclidean mean of kern
 el matrices. http://www.researchgate.net/profile/Pooya_Zakeri
CATEGORIES:Groupe de travail,Maths Bio
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20190331T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR