Activity Number:
|
663
- Regression, Clustering and Gene Set Methods in Genomics
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 1, 2019 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Statistics in Genomics and Genetics
|
Abstract #307141
|
|
Title:
|
Integrating Pathway Information with Boosting to Construct a Sufficient Gene Set for Phenotype Classification
|
Author(s):
|
Nusrat Jahan* and Huining Kang and Li Luo
|
Companies:
|
James Madison University and University of New Mexico and University of New Mexico
|
Keywords:
|
Boosting ;
Sufficient dimension reduction;
Sufficient gene set;
RNA sequence;
Pathway;
AML
|
Abstract:
|
In this work, we propose a 2-step phenotype classification method based on functional genomic data. In the first step, pathways relevant to specific phenotype conditions are identified, then a sufficient dimension reduction (SDR) within each pathway is achieved. The SDR process identifies the most relevant sufficient sets of predictors from each pathway. In the second step, boosting – a machine learning approach is used to identify most significantly differential sets of sufficient pathway based predictors. We demonstrate our method using an RNA-sequencing dataset from a study of pediatric acute myeloid leukemia (AML).
|
Authors who are presenting talks have a * after their name.