A Novel Deep Neural Network Technique for Drug-Target Interaction
Drug-Target Interaction; DTI prediction; Deep learning; Convolutional Neural Network.
Drug discovery (DD) is a time consuming and expensive process. Thus, the industry employs strategies as drug repositioning and drug repurposing, which allows to application of already approved drugs to treat a different disease, as occurred in the first months of 2020, during the COVID-19 pandemic. The prediction of drug-target interaction is an essential part of the DD process because it can accelerate it and reduce the required costs. DTI prediction performed \textit{in silico} have used approaches based on molecular docking simulation, similarity-based and network and graph based. This paper presents MPS2IT-DTI, a DTI prediction model obtained from a research conducted in the following steps: the definition of a new method for encoding molecule and protein sequences into images; and the definition of a deep-learning approach based on a convolutional neural-network in order to create a new method for DTI prediction. Training results conducted with the Davis and KIBA datasets show that MPS2IT-DTI is viable compared to other state-of-the-art (SOTA) approaches in terms of performance and complexity of the neural network model. With Davis dataset, we obtained 0.876 for concordance index and 0.276 for MSE; and with KIBA dataset, 0.836 and 0.226, respectively. Also, MPS2IT-DTI model represents molecule and protein sequence as images, instead of treating them as an NLP task and, as such, does not employ an embedding layer, which is present in other models.