LCASPMDA: a computational model for predicting potential microbe-drug associations based on learnable graph convolutional attention networks and self-paced iterative sampling ensemble

Abstract

Introduction: Numerous studies show that microbes in the human body are very closely linked to the human host and can affect the human host by modulating the efficacy and toxicity of drugs. However, discovering potential microbe-drug associations through traditional wet labs is expensive and time-consuming, hence, it is important and necessary to develop effective computational models to detect possible microbe-drug associations.

Methods: In this manuscript, we proposed a new prediction model named LCASPMDA by combining the learnable graph convolutional attention network and the self-paced iterative sampling ensemble strategy to infer latent microbe-drug associations. In LCASPMDA, we first constructed a heterogeneous network based on newly downloaded known microbe-drug associations. Then, we adopted the learnable graph convolutional attention network to learn the hidden features of nodes in the heterogeneous network. After that, we utilized the self-paced iterative sampling ensemble strategy to select the most informative negative samples to train the Multi-Layer Perceptron classifier and put the newly-extracted hidden features into the trained MLP classifier to infer possible microbe-drug associations.

Results and discussion: Intensive experimental results on two different public databases including the MDAD and the aBiofilm showed that LCASPMDA could achieve better performance than state-of-the-art baseline methods in microbe-drug association prediction.

Keywords: drug-microbe association; learnable graph convolutional attention network; multi-layer perceptron classifier; prediction model; self-paced iterative sampling ensemble.

Figure 1

The overall framework of LCASPMDA. Step1: a heterogeneous network of microbes and drugs is constructed based on newly-downloaded known microbe-drug associations and an integrated similarity of microbes and drugs. Step2: the heterogeneous network is inputted into the LCAT to learn the feature representations of nodes. Step 3: The Self-Paced Iterative Sampling Ensemble is adopted to select the most informative samples for training the MLP classifier while ensuring the balance of training samples. Step 4: potential associations between microbes and drugs are inferred by the trained MLP.

Figure 2

A new perspective on understanding the LCAT principle.

Figure 3

Effects of different IR on LCASPMDA.

Figure 4

ROC and PR curves achieved by LCASPMDA and state-of-the-art methods based on MDAD and aBiofilm separately. (A) ROC curves based on MDAD, (B) PR curves based on MDAD, (C) ROC curves based on aBiofilm, (D) PR curves based on aBiofilm.

Figure 5

ROC and PR curves achieved by LCASPMDA based on the DrugVirus database. (A) ROC curves based on DrugVirus, (B) PR curves based on DrugVirus.

Figure 6

Effects of different Out-dimension on LCASPMDA.

Figure 7

SPISE can improve the prediction performance of LCASPMDA. (A) ROC curves based on MDAD, (B) PR curves based on MDAD, (C) ROC curves based on aBiofilm, (D) PR curves based on aBiofilm.

Figure 8

SPIE has an important effect on the overall model performance of LCASPMDA. (A) ROC curves, (B) PR curves.

Figure 9

LCAT can improve the prediction performance of LCASPMDA. (A) ROC curves based on MDAD, (B) PR curves based on MDAD, (C) ROC curves based on aBiofilm, (D) PR curves based on aBiofilm.