Abstract 4239: Development of pan-cancer transcriptional signatures that predict chemosensitivity

Abstract

Abstract Background: Despite increasing understanding of the molecular characteristics of cancer, chemotherapy success rates remain low for many cancer types. Studies have attempted to identify patient and tumor characteristics that predict sensitivity or resistance to different types of conventional chemotherapies, yet a concise model that predicts chemosensitivity based on gene expression signatures across cancer types remains to be formulated. We attempted to generate a pan-cancer chemosensitivity predictive model using publicly available data from multiple sources. Such a model may increase the likelihood of identifying the type of chemotherapy most likely to succeed for a given patient based on the gene expression signature of their tumor. Methods: Data used to build predictive models were obtained from the Genomics of Drug Sensitivity in Cancer (GDSC) database, consisting of gene expression profiles from 962 cancer cell lines via RNA sequencing (RNA-seq) and drug sensitivity profiles reported as ln(IC50). Predictive gene signatures were generated using a cross-validated generalized linear model using elastic net penalization parameters. Models were generated for individual chemotherapy drugs, and accuracy of the models was determined by multi-class area under the curve (AUC). Models were then validated using publicly available data from Cancer Cell Line Encyclopedia (CCLE) and NCI-60 as well as publicly available human tumor datasets such as The Cancer Genome Atlas (TCGA). As the training data used to generate the models were from RNA-seq and some of the validation data were generated using microarray technology, feature-specific quantile normalization was used to enable cross-platform analyses. Results: We developed pan-cancer models to predict chemosensitivity to 8 individual chemotherapy drugs from GDSC data. For most models, multi-class AUC ranged from 0.63 to 0.68 when considering all available cancer types. Other models, specifically for etoposide and methotrexate, showed poor performance overall (AUC 0.54-0.55) but performed well when predicting chemosensitivity for bone cancers (AUC 0.70-0.73), which proved difficult with models for other drugs. When considering how well the models predicted chemosensitivity within cancer types, accuracy was improved in some cancer types (e.g., thyroid cancer), with more heterogeneous cancer types (e.g., breast cancer) giving less accuracy. Conclusions: Our results show that these models can predict chemosensitivity across cancer types with clinically useful levels of accuracy, with some cancer types resulting in a high rate of accuracy across several classes of chemotherapy. The inclusion of future clinical datasets, particularly from those cancer types in which chemosensitivity has been difficult to predict, may provide opportunities to strengthen model accuracy as well as decrease the numbers of genes needed to assess chemosensitivity. Citation Format: Jason D. Wells, Todd W. Miller. Development of pan-cancer transcriptional signatures that predict chemosensitivity [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2019; 2019 Mar 29-Apr 3; Atlanta, GA. Philadelphia (PA): AACR; Cancer Res 2019;79(13 Suppl):Abstract nr 4239.