|
Activity Number:
|
372
- Statistical Methods for Microbiome Data Analysis
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Wednesday, August 10, 2022 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics in Genomics and Genetics
|
|
Abstract #322637
|
|
|
Title:
|
Bias Resistant Modeling of Microbiome Relative Abundance
|
|
Author(s):
|
Ni Zhao* and Mo Li and Glen Satten
|
|
Companies:
|
Johns Hopkins University and Johns Hopkins University and Emory University
|
|
Keywords:
|
Microbiome abundance;
bias;
rank regression
|
|
Abstract:
|
Bias is ubiquitous in microbiome sequencing studies. The observed relative abundances is a distorted version of the true relative abundances due to differences in PCR and sequencing efficiency. Bias leads to invalid statistical conclusions even in the most well-designed studies in which all samples have the same set of bias factor. Currently, there is few methods that address the bias in microbiome association studies. In this talk, we will discuss a non-parametric rank-based regression approach that is robust to the underlying bias generation procedure. We show via extensive simulations the benefit of the proposed method compared to its potential competitors.
|
Authors who are presenting talks have a * after their name.
