Abstract
Drug response prediction is a well-studied problem in which the molecular profile of a given sample is used to predict the effect of a given drug on that sample. Effective solutions to this problem hold the key for precision medicine. In cancer research, genomic data from cell lines are often utilized as features to develop machine learning models predictive of drug response. Molecular networks provide a functional context for the integration of genomic features, thereby resulting in robust and reproducible predictive models. However, inclusion of network data increases dimensionality and poses additional challenges for common machine learning tasks. To overcome these challenges, we here formulate drug response prediction as a link prediction problem. For this purpose, we represent drug response data for a large cohort of cell lines as a heterogeneous network. Using this network, we compute “network profiles” for cell lines and drugs. We then use the associations between these profiles to predict links between drugs and cell lines. Through leave-one-out cross validation and cross-classification on independent datasets, we show that this approach leads to accurate and reproducible classification of sensitive and resistant cell line-drug pairs, with 85% accuracy. We also examine the biological relevance of the network profiles.
Highlights
Drug response prediction is a well-studied problem in which the molecular profile of a given sample is used to predict the effect of a given drug on that sample
Our method uses existing heterogeneous datasets (drug screens, cell line mutations, and protein-protein interactions (PPIs)) to predict the effect of a drug on a given cell line. This is achieved by building a series of heterogeneous networks based on data from the Genomics of Drug Sensitivity in Cancer (GDSC) dataset
For existing cell line and drug data, the method first constructs network profiles for drugs and cell lines, representing genes that are functionally related to genes mutated in the respective cell line
Summary
Drug response prediction is a well-studied problem in which the molecular profile of a given sample is used to predict the effect of a given drug on that sample. Both projects performed molecular profiling (somatic mutation, copy number variation (CNV), and gene expression screening) for hundreds of cancer cell lines and treated them with multiple established compounds Data from these two projects are publicly available and have been studied extensively to develop and test methods of drug response prediction. This entails learning drug models in which weights correspond to the importance of each feature for predicting cell line response, typically represented by IC50 values (the drug concentration required for 50% inhibition of cell growth) Following this procedure, another large drug prediction project, carried out by Jang et al, tested over 100,000 models based on well-known machine learning algorithms using combinations of molecular data from either the GDSC or CCLE8. Since it is more difficult to learn from binary or discrete-valued features, effective use of mutation or copy number information in drug response prediction is challenging
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
