EcoSta 2019: Start Registration
View Submission - EcoSta2019
A0770
Title: Multiple response logistic regression with structure constraints and its applications to Cancer Cell Line Encyclopedia Authors:  Seyoung Park - Sungkyunkwan University (Korea, South) [presenting]
Abstract: Cancer cell lines (CCLs) play a critical role in enabling the screening of drug candidates at an early stage of drug discovery. Due to the complex interactions between cell lines and drug molecules, identifying the correlation between the variability in molecular profiles and pharmacological responses is challenging. We propose a multiple response logistic regression framework with structure constraints that exploits information on gene expression of CCLs and multiple drug response binary data to incorporate similarity among drugs. We identify a limited set of genes that might be directly involved in drug sensitivity or resistance.