JSM 2015 Preliminary Program

Online Program Home
My Program

Abstract Details

Activity Number: 9
Type: Invited
Date/Time: Sunday, August 9, 2015 : 2:00 PM to 3:50 PM
Sponsor: WNAR
Abstract #318029 View Presentation
Title: Integrated predictive models for multidimensional cancer omics data
Author(s): Xuefeng Wang* and Xinyu Tian and Lizhen Peng and Jun Chen
Companies: Stony Brook University and Stony Brook University and Stony Brook University and Mayo Clinic
Keywords:
Abstract:

Constructing scalable prediction models based on molecular data has important implications for cancer screening, prevention and treatment. Linking information generated from different sources remains a challenge and a pressing goal for this field. In the first part of this talk, we will describe a multinomial logit model that is capable of addressing both the high dimensionality of predictors and the underlying network information. Group lasso was used to induce model sparsity, and a networkconstraint was imposed to induce the smoothness of the coefficients with respect to the underlying network structure. The second portion of this talk will focus on multiple kernel learning as a promising framework for prognostic prediction. This technology is particularly appealing for its generality on incorporating heterogeneous data. However, the efficiency and performance of variant algorithms when applied to genomic data remains unexplored. We will discuss some important theoretical and practical aspects of multiple kernel learning and speculate on how to build efficient supervised learning models based on largescale cancer datasets. We demonstrate and benchmark the implementation of the proposed methods using omics data from The Cancer Genome Atlas (TCGA).


Authors who are presenting talks have a * after their name.

Back to the full JSM 2015 program





For program information, contact the JSM Registration Department or phone (888) 231-3473.

For Professional Development information, 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.

2015 JSM Online Program Home