Ensemble transfer learning for the prediction of anti-cancer drug response

Abstract

Transfer learning, which transfers patterns learned on a source dataset to a related target dataset for constructing prediction models, has been shown effective in many applications. In this paper, we investigate whether transfer learning can be used to improve the performance of anti-cancer drug response prediction models. Previous transfer learning studies for drug response prediction focused on building models to predict the response of tumor cells to a specific drug treatment. We target the more challenging task of building general prediction models that can make predictions for both new tumor cells and new drugs. Uniquely, we investigate the power of transfer learning for three drug response prediction applications including drug repurposing, precision oncology, and new drug development, through different data partition schemes in cross-validation. We extend the classic transfer learning framework through ensemble and demonstrate its general utility with three representative prediction algorithms including a gradient boosting model and two deep neural networks. The ensemble transfer learning framework is tested on benchmark in vitro drug screening datasets. The results demonstrate that our framework broadly improves the prediction performance in all three drug response prediction applications with all three prediction algorithms.

Figure 1

Analysis scenario framework. The analysis scheme on the left is ensemble transfer learning (ETL). The middle and right analysis schemes are standard cross-validation (SCV) and ensemble cross-validation (ECV), respectively, which do not apply transfer learning but instead analyze only the target dataset.

Figure 2

Flowchart of ensemble transfer learning (ETL).

Figure 3

Architectures of two DNN models used in the analysis. (a) Single-network DNN (sDNN) model. Gene expressions and drug descriptors are concatenated to form the input. (b) Two-subnetwork DNN (tDNN) model. The subnetworks take gene expressions and drug descriptors as separate inputs.