Search

Abstract Background The advent of high-throughput transcriptomic screening technologies has resulted in a wealth of publicly available gene expression data associated with chemical treatments. From a regulatory perspective, data sets that cover a large chemical space and contain reference chemicals offer utility for the prediction of molecular initiating events associated with chemical exposure. Here, we integrate data from a large compendium of transcriptomic responses to chemical exposure with a comprehensive database of chemical-protein associations to train binary classifiers that predict mechanism(s) of action from transcriptomic responses. First, we linked reference chemicals present in the LINCS L1000 gene expression data collection to chemical identifiers in RefChemDB, a database of chemical-protein interactions. Next, we trained binary classifiers on MCF7 human breast cancer cell line derived gene expression profiles and chemical-protein labels using six classification algorithms to identify optimal analysis parameters. To validate classifier accuracy, we used holdout data sets, training-excluded reference chemicals, and empirical significance testing of null models derived from permuted chemical-protein associations. To identify classifiers that have variable predicting performance across training data derived from different cellular contexts, we trained a separate set of binary classifiers on the PC3 human prostate cancer cell line. Results We trained classifiers using expression data associated with chemical treatments linked to 51 molecular initiating events. This analysis identified and validated 9 high-performing classifiers with empirical p-values lower than 0.05 and internal accuracies ranging from 0.73 to 0.94 and holdout accuracies of 0.68 to 0.92. High-ranking predictions for training-excluded reference chemicals demonstrating that predictive accuracy extends beyond the set of chemicals used in classifier training. To explore differences in classifier performance as a function of training data cellular context, MCF7-trained classifier accuracies were compared to classifiers trained on the PC3 gene expression data for the same molecular initiating events. Conclusions This methodology can offer insight in prioritizing candidate perturbagens of interest for targeted screens. This approach can also help guide the selection of relevant cellular contexts for screening classes of candidate perturbagens using cell line specific model performance.