Abstract

Info

Author(s):: GAO Chong1; 2; QIN Yufang1; 2; CHEN Ming1; 2; 1. College of Information Technology, Shanghai Ocean University, Shanghai 201306, China 2. Key Laboratory of Fisheries Information, Ministry of Agriculture and Rural Affairs of the Peoples Republic of China, Shanghai 201306, China

Keywords:: cancer drug sensitivity pathway activity gene expression personalized medicine

Abstract:: Pathway database is a knowledge base for analyzing gene functions systematically and linking genomic information and functional information. As a collection of gene functions, pathways can improve the prediction ability and interpretation ability of prediction models. Herein the pathway activity is inferred by the integration of KEGG pathway data and CCLE gene expression profile, and then is combined with drug data to establish a drug sensitivity prediction model. When inferring the activity of the pathway, the pathway is not simply treated as a collection of genes. The genes with high connectivity in the pathway are selected in the study, and the average expression level of the genes with high connectivity is taken as the pathway activity value. The pathway activity matrix which is obtained by combining the activity vector of each pathway is input to the elastic net for drug sensitivity prediction. Experimental results show that for most drugs, the use of computational analysis methods based on the genes with high connectivity in pathways is more conducive to drug sensitivity prediction, and at the same time it can identify more pathways for drug-related genes.