Protein kinases play a vital role in a wide range of cellular processes, and compounds that inhibit kinase activity emerging as a primary focus for targeted therapy development, especially in cancer. Consequently, efforts to characterize the behavior of kinases in response to inhibitor treatment, as well as downstream cellular responses, have been performed at increasingly large scales. Previous work with smaller datasets have used baseline profiling of cell lines and limited kinome profiling data to attempt to predict small molecule effects on cell viability, but these efforts did not use multi-dose kinase profiles and achieved low accuracy with very limited external validation. This work focuses on two large-scale primary data types, kinase inhibitor profiles and gene expression, to predict the results of cell viability screening. We describe the process by which we combined these data sets, examined their properties in relation to cell viability and finally developed a set of computational models that achieve a reasonably high prediction accuracy (R-2 of 0.78 and RMSE of 0.154). Using these models, we identified a set of kinases, several of which are understudied, that are strongly influential in the cell viability prediction models. In addition, we also tested to see if a wider range of multiomics data sets could improve the model results and found that proteomic kinase inhibitor profiles were the single most informative data type. Finally, we validated a small subset of the model predictions in several triple-negative and HER2 positive breast cancer cell lines demonstrating that the model performs well with compounds and cell lines that were not included in the training data set. Overall, this result demonstrates that generic knowledge of the kinome is predictive of very specific cell phenotypes, and has the potential to be integrated into targeted therapy development pipelines. Author summaryBeing able to predict how a patient's tumor will respond to a specific drug treatment is a core goal in the field of precision oncology. An emerging trend in targeted therapies is a focus on protein kinases, a family of over 500 proteins that form an integrated communication network that plays a central role in the development and progression of nearly all cancers. Despite the growing importance of these drugs in the oncologist's therapeutic toolbox, our ability to predict the response of a tumor to a given treatment is poor. To see if we could improve our ability to predict a cancer's response to kinase inhibitor treatment, we leveraged a large experimental dataset that quantifies the effect of these drugs on the kinases. Using these kinase inhibition state data within machine learning models, we found that we could predict the response of cancer cell lines representing over 27 cancer types with high accuracy. Including cell line-specific gene expression data that could be gathered in a clinical setting further improved the accuracy of predictions. Together, these results suggest that knowledge of the inhibition state of the kinome has significant potential to improve our ability to design and deliver more effective targeted cancer treatments.
展开▼
