EA-based hyperparameter optimization of hybrid deep learning models for effective drug-target interactions prediction

The identification of drug-target interactions (DTIs) is an important process in drug repositioning and drug discovery. However, it is very expensive and time-consuming to determine all possible DTIs with experimental approaches. Most existing machine learning-based methods formulate the DTIs prediction problem as a binary classification problem. Nevertheless, the lack of experimentally validated negative samples results in imbalanced class distribution within the datasets, which may have a negative influence on the DTI prediction performance. Casting DTI prediction task as a regression problem seems an interesting alternative to avoid this issue especially with the recent increase in protein structural data and DTI datasets. Within this context, a twofold contribution is described in this paper. First, we propose a novel deep learning model for predicting drug-target binding affinities called Convolution Neural Network with Attention-based bidirectional Long Short-Term Memory network (CNN-AbiLSTM), which combines a CNN with an attention-based biLSTM. Second, building a powerful hybrid CNN-AbiLSTM model can be highly complicated and requires a suitable setting of the model's hyper parameters. To handle this problem, we propose an evolutionary algorithm-based framework more specifically a Differential Evolution (DE) algorithm to find the optimal configuration of the proposed model. Experimental results show that the proposed DE-based CNN-AbiLSTM model achieves better performance compared with baseline methods.

Automated summary

The identification of drug-target interactions is crucial in drug repositioning and discovery, but can be costly and time-consuming using experimental methods. Most existing machine learning approaches formulate the prediction problem as binary classification, leading to imbalanced class distribution due to lack of negative samples. This paper introduces a novel deep learning model CNN-AbiLSTM for predicting drug-target binding affinities, and utilizes a DE algorithm for optimal model configuration, showing improved performance compared to baseline methods.