|
Activity Number:
|
355
- Contributed Poster Presentations: Biopharmaceutical Section
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 30, 2019 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
|
Abstract #307061
|
|
|
Title:
|
High-Throughput Screening of Features Which Moderate Treatment Effect on Clinical Outcome
|
|
Author(s):
|
Kushal Shah* and Michael Kosorok
|
|
Companies:
|
University of North Carolina (UNC) and University of North Carolina at Chapel Hill
|
|
Keywords:
|
precision medicine;
patient-derived xenografts;
dimension reduction;
gene-treatment interaction;
multiple outcomes;
biomarkers
|
|
Abstract:
|
High-dimensional precision medicine settings propose statistical challenges with regard to the selection of genetic covariates. We present a high-throughput nonparametric method which screens for genetic features that have an interaction effect with the treatment in predicting clinical outcomes. This screening technique can be applied to settings with multiple potential outcomes. We evaluate this method on simulated data and compare our approach with existing alternatives using genomic datasets that include treatments and outcomes, such as patient-derived xenograft (PDX) data and other similar datasets.
|
Authors who are presenting talks have a * after their name.
