AUTHOR=Yuan Rui , Chen Shilong , Wang Yongcui 

TITLE=Computational Prediction of Drug Responses in Cancer Cell Lines From Cancer Omics and Detection of Drug Effectiveness Related Methylation Sites

JOURNAL=Frontiers in Genetics

VOLUME=Volume 11 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2020.00917

DOI=10.3389/fgene.2020.00917

ISSN=1664-8021

ABSTRACT=Accurately predicting the response of a cancer patient to a therapeutic agent remains an important challenge for precision medicine. With the rise of data science, more researchers tend to use bioinformatics to study drug response. In addition, as we all know that, DNA methylation is a common epigenetic modification, which is closely related to the occurrence and development of cancer. Therefore, it is helpful for accurate treatment of cancer through exploring the relationship between DNA methylation and drug effectiveness. Here, we proposed the computational models to predict cancer cell sensitivity to drugs, meanwhile to detect the methylation sites that closely related with drug effectiveness. After using our prediction model on cancer omics generated from Cancer Cell Line Encyclopedia (CCLE), we found that the performance of the prediction model using DNA methylation was comparable to that of the prediction model using other data sources. It indicates the important role of DNA methylation in prediction of drug responses. To detect the methylation sites that are closely related with drug effectiveness, Least Absolute Shrinkage and Selection Operator (lasso) regression model that perform both variable selection and regularization was introduced. Encyclopedia of DNA Elements (ENCODE) and Transcriptional Regulatory Relationships Unraveled by Sentence-based Text mining (TRRUST2) database analyses suggest that the methylation sites associated with drug effectiveness were mainly located in the transcription factor (TF) binding region. Therefore, we hypothesized that the sensitivity of cancer cells to drugs could be regulated by changing the methylation modification of TF binding region.