Drug repositioning, which recommends approved drugs to potential targets by predicting drug-target interactions (DTIs), can save the cost and shorten the period of drug development. In this work, we propose a novel knowledge graph based deep learning method, named KG-DTI, for DTIs predictions. Specifically, a knowledge graph of 29,607 positive drug-target pairs is constructed by DistMult embedding strategy. A Conv-Conv module is proposed to extract features of drug-target pairs (DTPs), which is followed by a fully connected neural network for DTIs calculation. Data experiments are conducted on randomly chosen 11,840 positive and negative samples. It is obtained that KG-DTI achieves average ACC by 88.0%, F1-Score by 87.7%, AUROC by 94.3% and AUPR by 95% in five-fold cross-validation. In practice, KG-DTI is applied to reposition drugs to Alzheimer’s disease (AD) by Apolipoprotein E target. As results, it is found that seven of the top ten recommended drugs have been used in clinic practice or with literature supported useful to AD. Ligand-target docking results show that the top one recommended drug can dock with Apolipoprotein E significantly, which gives vital hints in repositioning potential drug to AD treatment.

Traditional Chinese medicine has been used to treat and prevent infectious diseases for thousands of years, and has accumulated a large number of effective prescriptions. Deep learning methods provide powerful applications in calculating interactions between drugs and targets. In this study, we try to use the method of deep learning to reposition molecules of Chinese medicines (CMs) and the targets of syndrome coronavirus 2 (SARS-CoV-2). A deep convolution neural network with residual module (DCNN-Res) is constructed and trained on KIBA dataset. The accuracy of predicting the binding affinity of drugtarget pairs is 85.33%. By ranking binding affinity scores of 433 molecules in 35 CMs to 6 targets of SARS-Cov-2, DCNN-Res recommends 30 possible repositioning molecules. The consistency between our result and the latest research is 0.827. The molecules in Gancao and Huangqin have a strong binding affinity to targets of SARS-CoV-2, which is also consistent with the latest research.

In computational drug discovery, accurately predicting drug-target interaction (DTI) is vital for drug repositioning and developing new drugs. With DTI data rapidly accumulated in recent years, it is recently hot to use deep learning technology to predict DTIs, but still a challenge to design light learning frameworks by using less protein descriptors. In this work, to address the challenge, a novel light deep convolutional neural network (namely LDCNN) is proposed to predict DTIs, in which a small number of protein descriptors are produced by convolving amino acid sequences of different lengths. As results, it is obtained that LDCNN can reduce the number of neurons in convolution layers and filters by 50%, with lose of AUC 1.3% and AUPR 4% comparing with DeepConv method. Our LDCNN models can give hints in designing light deep learning models for DTI prediction.