NrGe-DTL: a computational framework for cancer drug response prediction based on deep transfer learning from combined denoised genomic profiles and chemical structure embedding of drugs

In recent years, precision medicine has been consistently studied and employed in cancer treatment. One of the main challenges in precision medicine is accurately predicting a cancer patient’s response to a specific drug(s) using computational models. Due to the heterogeneity of cancer, the distribution between the drug response profiles based on cell lines and real samples is often different, which leads to out-of-data distribution problems that affect putting the existing predictive models into practical application. To overcome this limitation, a novel framework to predict cancer drug response based on transfer learning from combined genomic profiles and chemical structure embedding of drugs is proposed in this paper. This framework features a denoising auto-encoder (DAE) module designed to remove noise from genomics profiles and a graph convolutional network (GCN) employed to extract the embedding of pharmaceutical chemical structures. Through the experiments, our model outperforms recently published methods on Genomics of Drug Sensitivity in Cancer (GDSC) datasets, and gives promising results on personalized drug response prediction on TCGA pan-cancer datasets, especially for the response of two commonly used anti-cancer drugs―Gemcitabine and Cisplatin. In summary, our study designed a computational framework with the potential capability of predicting personalized cancer drug response, which has been preliminarily validated for its effectiveness.