American Statistical Association
The human microbiome consists of microbes that live throughout the human body, and many studies have now shown that certain characteristics of the microbiome might be associated with various diseases. The microbiome is a dynamic environment, where microbes are known to both exchange nutrients and compete for the same nutrients. Understanding these complex relationships may help further elucidate the association between the microbiome and human health. To assess bacterial composition in a patient sample, the 16S rDNA gene is frequently sequenced since regions of this gene vary widely across bacteria, and the number of reads matching specific bacteria is proportional to its abundance. this talk, we will discuss a nonparametric ensemble learning method for prognostic modeling for a binary outcome using relative abundance of bacteria. The algorithm follows a random forest framework, where the objective function is defined in the space of pairwise relationships of different bacteria.
|Date:||Wednesday, June 8, 2016|
|Time:||4:00 - 5:00 P.M.|
Memorial Sloan-Kettering Cancer Center
Department of Epidemiology and Biostatistics
485 Lexington Avenue
(Between 46th & 47th Streets)
2nd Floor Conference Room B
New York, New York
**Note: Outside visitors please email email@example.com, for building access. You must be on the security list to enter our floor.