Prediction of the Antioxidant Response Elements' Response of Compound by Deep Learning

Abstract

The antioxidant response elements (AREs) play a significant role in occurrence of oxidative stress and may cause multitudinous toxicity effects in the pathogenesis of a variety of diseases. Determining if one compound can activate AREs is crucial for the assessment of potential risk of compound. Here, a series of predictive models by applying multiple deep learning algorithms including deep neural networks (DNN), convolution neural networks (CNN), recurrent neural networks (RNN), and highway networks (HN) were constructed and validated based on Tox21 challenge dataset and applied to predict whether the compounds are the activators or inactivators of AREs. The built models were evaluated by various of statistical parameters, such as sensitivity, specificity, accuracy, Matthews correlation coefficient (MCC) and receiver operating characteristic (ROC) curve. The DNN prediction model based on fingerprint features has best prediction ability, with accuracy of 0.992, 0.914, and 0.917 for the training set, test set, and validation set, respectively. Consequently, these robust models can be adopted to predict the ARE response of molecules fast and accurately, which is of great significance for the evaluation of safety of compounds in the process of drug discovery and development.

Keywords: antioxidant response elements (AREs); deep learning; machine learning; prediction; toxicity.

Figure 1

The distribution of samples in the training set and test set by principle component analysis (PCA) based on the molecular fingerprint features.

Figure 2

The structure of deep neural network (DNN). Neurons are represented by circles. The colored circles indicate the activated neurons while the circles without color are inactivated neurons. In addition, the arrows represent heavy-weight transmissions between neurons, and the dashed arrows mean the invalid neuronal connections.

Figure 3

Radar plot of the descriptors-based classification models.

Figure 4

ROC curve of descriptors-based model (the left one is test set, the right one is validation set).

Figure 5

The frequency of fingerprints occurred in compounds.

Figure 6

Radar plot of the fingerprints-based classification model.

Figure 7

ROC curve of fingerprints-based model (left: test set, right: validation set).