Abstract Details
Activity Number:
|
186
|
Type:
|
Contributed
|
Date/Time:
|
Monday, August 4, 2014 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Biometrics Section
|
Abstract #311412
|
|
Title:
|
Power Calculation in Candidate Marker Detection in RNA-Seq Experiment
|
Author(s):
|
Ge Liao*+ and George Tseng
|
Companies:
|
University of Pittsburgh and University of Pittsburgh
|
Keywords:
|
RNA-seq ;
power calculation ;
mixture model ;
sample size ;
coverage
|
Abstract:
|
Although the experimental cost of Next Generation Sequencing (NGS) technology continues to drop rapidly, the high sequencing expenses and bioinformatic complexity will continue to be an obstacle. Modelling of NGS data not only involves sample size and genome-wide inference, but also includes sequencing depth and count data statistics. The optimal design is beyond one-dimensional dual problem between sample size versus statistical power. In this work, we propose a novel strategy to predict power of detecting differential expression (DE) in RNA-seq experiment under different sample size (n) and coverage(r) with a given pilot data. Instead of using summary statistics for power computation, we direct model p-value distribution by a mixture model, so that heterogeneity across genes could be maintained. To predict power of detection in a new sample size (N), a parametric bootstrap procedure is implemented, followed by 5-parameter log logistic curve fitting for expected discovery rate (EDR, or genome-wide power). To extend power prediction to other coverage, a downward sub-sampling scheme is implemented. We compare with three existing methods for evaluation.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.