Title:Prediction of Human Microbe-Drug Association based on Layer
Attention Graph Convolutional Network
Volume: 31
Issue: 31
Author(s): Jia Qu*, Jie Ni, Tong-Guang Ni, Ze-Kang Bian and Jiu-Zhen Liang
Affiliation:
- School of Computer Science and Artificial Intelligence & Aliyun School of Big Data, Changzhou University,
Changzhou, 213164, China
Keywords:
Human microbe, drug, association prediction, heterogeneous network, deep learning, attention mechanism.
Abstract:
Human microbes are closely associated with a variety of complex diseases and
have emerged as drug targets. Identification of microbe-related drugs is becoming a key
issue in drug development and precision medicine. It can also provide guidance for solving
the increasingly serious problem of drug resistance enhancement in viruses.
Methods: In this paper, we have proposed a novel model of layer attention graph convolutional
network for microbe-drug association prediction. First, multiple biological data
have been integrated into a heterogeneous network. Then, the heterogeneous network has
been incorporated into a graph convolutional network to determine the embedded microbe
and drug. Finally, the microbe-drug association scores have been obtained by decoding
the embedding of microbe and drug based on the layer attention mechanism.
Results: To evaluate the performance of our proposed model, leave-one-out crossvalidation
(LOOCV) and 5-fold cross-validation have been implemented on the two datasets
of aBiofilm and MDAD. As a result, based on the aBiofilm dataset, our proposed
model has attained areas under the curve (AUC) of 0.9178 and 0.9022 on global LOOCV
and local LOOCV, respectively. Based on aBiofilm dataset, the proposed model has attained
an AUC value of 0.9018 and 0.8902 on global LOOCV and local LOOCV, respectively.
In addition, the average AUC and standard deviation of the proposed model for 5-
fold cross-validation on the aBiofilm and MDAD datasets were 0.9141±6.8556e-04 and
0.8982±7.5868e-04, respectively. Also, two kinds of case studies have been further conducted
to evaluate the proposed models.
Conclusion: Traditional methods for microbe-drug association prediction are timeconsuming
and laborious. Therefore, the computational model proposed was used to predict
new microbe-drug associations. Several evaluation results have shown the proposed
model to achieve satisfactory results and that it can play a role in drug development and
precision medicine.
