GONNMDA: A Ordered Message Passing GNN Approach for miRNA-Disease Association Prediction

Abstract

Small non-coding molecules known as microRNAs (miRNAs) play a critical role in disease diagnosis, treatment, and prognosis evaluation. Traditional wet-lab methods for validating miRNA-disease associations are often time-consuming and inefficient. With the advancement of high-throughput sequencing technologies, deep learning methods have become effective tools for uncovering potential patterns in miRNA-disease associations and revealing novel biological insights. Most of the existing approaches focus primarily on individual molecular behavior, overlooking interactions at the multi-molecular level. Conventional graph neural network (GNN) models struggle to generalize to heterogeneous graphs, and as network depth increases, node representations become indistinguishable due to over-smoothing, resulting in reduced predictive performance. GONNMDA first integrates similarity features from multiple data sources and applies noise reduction to obtain a reconstructed, comprehensive similarity representation. It then constructs heterogeneous graphs and applies a root-tree hierarchical alignment, along with an ordered gating message-passing mechanism, effectively addressing the challenges of heterogeneity and over-smoothing. Finally, a multilayer perceptron is employed to produce the final association predictions. To evaluate the effectiveness of GONNMDA, we conducted extensive experiments where the model achieved an AUC of 95.49% and an AUPR of 95.32%. The results demonstrate that GONNMDA outperforms several recent state-of-the-art methods. In addition, case studies and survival analyses on three common human cancers-breast cancer, rectal cancer, and lung cancer-further validate the effectiveness and reliability of GONNMDA in predicting miRNA-disease associations.

Keywords: heterogeneous graph; miRNA–disease association; ordered GNN; singular value decomposition.

Figure 1

The performance of GONNMDA on 5-fold cross-validation. (a) ROC curves; (b) P-R curves.

Figure 2

The performance of GONNMDA on 10-fold cross-validation. (a) ROC curves; (b) P-R curves.

Figure 3

Comparison with the state-of-the-art method on 5-fold cross-validation (a) ROC curves; (b) P-R curves.

Figure 4

Comparison with the state-of-the-art method on 10-fold cross-validation (a) ROC curves; (b) P-R curves.

Figure 5

Ablation experiments with different models of GONNMDA.

Figure 6

Parameter analysis for hidden layer size.

Figure 7

Parameter analysis for ordered GNN layers (a) The values of AUC and AUPR under different layers; (b) The values of ACC and F1 and recall and precision under different layers.

Figure 8

Parameter analysis for chunk size.

Figure 9

Visualization of miRNA and disease nodes embedded in different ordered GNN layers. (a) Layer 1; (b) Layer 2; (c) Layer 3; (d) Layer 4; (e) Layer 5.

Figure 9

Visualization of miRNA and disease nodes embedded in different ordered GNN layers. (a) Layer 1; (b) Layer 2; (c) Layer 3; (d) Layer 4; (e) Layer 5.

Figure 10

Survival analysis of top 3 predictive miRNA in breast cancer.(a) hsa-mir-21 survival curve; (b) hsa-mir-146a survival curve; (c) hsa-mir-29a survival curve.

Figure 11

Survival analysis of top 3 predictive miRNA in rectal cancer.(a) hsa-mir-15a survival curve; (b) hsa-mir-24 survival curve; (c) hsa-mir-223 survival curve.

Figure 12

Survival analysis of top 3 predictive miRNA in lung cancer.(a) hsa-mir-29c survival curve; (b) hsa-mir-150 survival curve; (c) hsa-mir-21 survival curve.

Figure 13

The framework of GONNMDA.(A) Reconstructed similarity feature; (B) Ordered GNN; (C) Multilayer perceptron.