CNN-Siam: multimodal siamese CNN-based deep learning approach for drug‒drug interaction prediction

Drug‒drug interactions (DDIs) are reactions between two or more drugs, i.e., possible situations that occur when two or more drugs are used simultaneously. DDIs act as an important link in both drug development and clinical treatment. Since it is not possible to study the interactions of such a large number of drugs using experimental means, a computer-based deep learning solution is always worth investigating. We propose a deep learning-based model that uses twin convolutional neural networks to learn representations from multimodal drug data and to make predictions about the possible types of drug effects.

In this paper, we propose a novel convolutional neural network algorithm using a Siamese network architecture called CNN-Siam. CNN-Siam uses a convolutional neural network (CNN) as a backbone network in the form of a twin network architecture to learn the feature representation of drug pairs from multimodal data of drugs (including chemical substructures, targets and enzymes). Moreover, this network is used to predict the types of drug interactions with the best optimization algorithms available (RAdam and LookAhead). The experimental data show that the CNN-Siam achieves an area under the precision-recall (AUPR) curve score of 0.96 on the benchmark dataset and a correct rate of 92%. These results are significant improvements compared to the state-of-the-art method (from 86 to 92%) and demonstrate the robustness of the CNN-Siam and the superiority of the new optimization algorithm through ablation experiments.

The experimental results show that our multimodal siamese convolutional neural network can accurately predict DDIs, and the Siamese network architecture is able to learn the feature representation of drug pairs better than individual networks. CNN-Siam outperforms other state-of-the-art algorithms with the combination of data enhancement and better optimizers. But at the same time, CNN-Siam has some drawbacks, longer training time, generalization needs to be improved, and poorer classification results on some classes.