Abstract
Thanks to the availability of multiomics data of individual cancer patients, precision medicine or personalized medicine is becoming a promising treatment for individual cancer patients. However, the association patterns, that is, the mechanism of response (MoR) between large-scale multiomics features and drug response are complex and heterogeneous and remain unclear. Although there are existing computational models for predicting drug response using the high-dimensional multiomics features, it remains challenging to uncover the complex molecular mechanism of drug responses. To reduce the number of predictors/features and make the model more interpretable, in this study, 46 signaling pathways were used to build a deep learning model constrained by signaling pathways, consDeepSignaling, for anti–drug response prediction. Multiomics data, like gene expression and copy number variation, of individual genes can be integrated naturally in this model. The signaling pathway–constrained deep learning model was evaluated using the multiomics data of ∼1000 cancer cell lines in the Broad Institute Cancer Cell Line Encyclopedia (CCLE) database and the corresponding drug–cancer cell line response data set in the Genomics of Drug Sensitivity in Cancer (GDSC) database. The evaluation results showed that the proposed model outperformed the existing deep neural network models. Also, the model interpretation analysis indicated the distinctive patterns of importance of signaling pathways in anticancer drug response prediction.
Highlights
Precision medicine or personalized medicine is becoming feasible and widely adopted in cancer treatment due to the availability of multiomics data that comprehensively characterize individual cancer samples
A deep neural network (DNN) framework was developed to predict anticancer drug response based on gene expression data (Sakellaropoulos et al, 2019), and the results showed that the DNN models outperformed the current machine learning frameworks
Large-scale and high-dimensional multiomics data, like gene expression, copy number variation, methylation, genetic mutation, and microRNA, of individual cancer patients and >1,000 cancer cell lines have been generated, which provide the basis to fully understand the molecular mechanisms of tumor heterogeneity and diversity, as well as the heterogeneous response to anticancer drugs
Summary
Precision medicine or personalized medicine is becoming feasible and widely adopted in cancer treatment due to the availability of multiomics data that comprehensively characterize individual cancer samples. AI for Cancer Drug Prediction response of ∼1,000 cancer cell lines against ∼100 drugs and compounds is available in the Genomics of Drug Sensitivity in Cancer (GDSC) database (Garnett et al, 2012; Yang et al, 2013), with the aim of uncovering the potential associations between genetic biomarkers and drug response. About 5,232 drug combination screening of 104 drugs against 60 cancer cell lines are available in the NCI-ALMANAC Drug Combination database (Holbeck et al, 2017). These valuable data sets provide a basis for fully understanding the potential molecular mechanism of cancer heterogeneity and diversity, as well as for understanding the potential mechanism of response (MoR) to anticancer drug treatments
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.