Prediction of Drug Response in Cancer Using Hybrid Deep Neural Networks

Abstract

Assessing the best treatment option for each patient is the main goal of precision medicine. Patients with the same diagnosis may display varying sensitivity to the applied treatment due to genetic heterogeneity, especially in cancers. Here, we propose DeepResponse, a machine learning-based system that predicts drug responses (sensitivity) of cancer cells. DeepResponse employs multi-omics profiles of different cancer cell-lines obtained from large-scale screening projects, together with drugs’ molecular features at the input level, and processing them via hybrid convolutional and graph-transformer deep neural networks to learn the relationship between multi- omics features of the tumor and its sensitivity to the administered drug. DeepResponse has reached a Root Mean Squared Error (RMSE) of 1.014 ± 0.001 in random split, 1.105 ± 0.013 in cell stratified split, and 1.142 ± 0.104 in drug stratified split test datasets, showcasing its effectiveness in predicting drug responses. Performance results indicated DeepResponse successfully predicts drug sensitivity of cancer cells, and especially the multi-omics aspect benefited the learning process and yielded better performance compared to the state-of-the-art on all the splits. An ablation study was conducted to assess the impact of each omics data type on the performance of DeepResponse, providing further insights into the importance of multi- omics integration in drug response prediction. As a use case analysis, Eprinomectin was proposed as a drug repurposing candidate against hepatocellular carcinoma cancer cell lines, which was validated in wet lab experiments. The code base, datasets, and results of DeepResponse are openly shared at https://github.com/HUBioDataLab/DeepResponse. DeepResponse can be used for early-stage discovery of new drug candidates and for repurposing the existing ones against resistant tumors.