Search

Background and objectives: Breast cancer is the most prevalent type of cancer among women. The effectiveness of anticancer pharmacological therapy may get adversely affected by tumor heterogeneity that includes genetic and transcriptomic features. This leads to clinical variability in patient response to therapeutic drugs. Anticancer drug design and cancer understanding require precise identification of cancer drug responses. The performance of drug response prediction models can be improved by integrating multi-omics data and drug structure data. Methods: In this paper, we propose an Autoencoder (AE) and Graph Convolutional Network (AGCN) for drug response prediction, which integrates multi-omics data and drug structure data. Specifically, we first converted the high dimensional representation of each omic data to a lower dimensional representation using an AE for each omic data set. Subsequently, these individual features are combined with drug structure data obtained using a Graph Convolutional Network and given to a Convolutional Neural Network to calculate IC 5 0 values for every combination of cell lines and drugs. Then a threshold IC 5 0 value is obtained for each drug by performing K-means clustering of their known IC 5 0 values. Finally, with the help of this threshold value, cell lines are classified as either sensitive or resistant to each drug. Results: Experimental results indicate that AGCN has an accuracy of 0.82 and performs better than many existing methods. In addition to that, we have done external validation of AGCN using data taken from The Cancer Genome Atlas (TCGA) clinical database, and we got an accuracy of 0.91. Conclusion: According to the results obtained, concatenating multi-omics data with drug structure data using AGCN for drug response prediction tasks greatly improves the accuracy of the prediction task. [ABSTRACT FROM AUTHOR]

Background and Objective: High-throughput Next Generation Sequencing tools have generated immense quantity of genome-wide methylation and expression profiling data, resulting in an unprecedented opportunity to unravel the epigenetic regulatory mechanisms underlying cancer. Identifying differentially methylated regions within gene networks is an important step towards revealing the cancer epigenome blueprint. Approaches that integrate gene methylation and expression profiles assume their negative correlation and build a single scaffold network to cluster. However, the exact regulatory mechanism between gene expression and methylation is not precisely deciphered., Methods: A consensus-based clustering framework, namely, Differentially Methylated Gene Communities based on Multi-network (DMGC-M) is proposed, that takes multiple gene networks as input and builds a community structure out of evidences from all network types., Results: Experiments on six cancer datasets from The Cancer Genome Atlas (TCGA) reveal that multi-network approaches produce more discriminative gene communities than integrated approaches., Conclusion: The proposed method will be useful to a number of researchers who seek to identify epigenetic dysregulations in pathways or molecular networks. The findings can also advance recent research efforts in Molecular Pathologic Epidemiology., (Copyright © 2019 Elsevier B.V. All rights reserved.)