iPiDA-LGE: a local and global graph ensemble learning framework for identifying piRNA-disease associations

Abstract

Background: Exploring piRNA-disease associations can help discover candidate diagnostic or prognostic biomarkers and therapeutic targets. Several computational methods have been presented for identifying associations between piRNAs and diseases. However, the existing methods encounter challenges such as over-smoothing in feature learning and overlooking specific local proximity relationships, resulting in limited representation of piRNA-disease pairs and insufficient detection of association patterns.

Results: In this study, we propose a novel computational method called iPiDA-LGE for piRNA-disease association identification. iPiDA-LGE comprises two graph convolutional neural network modules based on local and global piRNA-disease graphs, aimed at capturing specific and general features of piRNA-disease pairs. Additionally, it integrates their refined and macroscopic inferences to derive the final prediction result.

Conclusions: The experimental results show that iPiDA-LGE effectively leverages the advantages of both local and global graph learning, thereby achieving more discriminative pair representation and superior predictive performance.

Keywords: Graph ensemble learning; Local context graph; piRNA-disease association identification.

Fig. 1

Parameter analysis of local-level graph learning in iPiDA-LGE. a, b, c, and d illustrate the AUC and AUPR obtained by local-level graph learning module with different neighbor orders, epochs, learning rates, and GCN layers on ${\mathbb{S}}_{\text{validation}}$, respectively

Fig. 2

Comparison between local/global graph learning and their combination. a shows the AUC and AUPR achieved by iPiDA-LGE with different fusion coefficients on ${\mathbb{S}}_{\text{validation}}$. b and c show the ROC and PR curves obtained by different predictors on ${\mathbb{S}}_{\text{validation}}$, respectively. d–f show the binary distribution of true labels and association scores predicted by iPiDA-L, iPiDA-G, and iPiDA-LGE on ${\mathbb{S}}_{\text{validation}}$

Fig. 3

Analysis of features extracted by local and global graph learning. a shows the t-SNE visualization of features extracted by iPiDA-A, iPiDA-G, and iPiDA-L, respectively. b and c show local context graphs for two example positive and two example negative piRNA-disease pairs in ${\mathbb{S}}_{\text{independent}}$, respectively. d shows the heatmap of features extracted by iPiDA-G and iPiDA-L for four example piRNA-disease pairs

Fig. 4

Comparison of different methods across four comprehensive metrics on 100 partitioned independent test sets. Wilcoxon rank-sum test is used to calculate the statistical difference between two groups of results. Comparisons with p values < 0.05 are marked with *, p values < 0.01 with **, p values < 0.001 with ***, and “ns” indicates no significant difference

Fig. 5

The framework of iPiDA-LGE. There exist three primary processes: (i) Graph construction. The global graph is constructed and supplemented with piRNA sequences, disease ontology knowledge, and validated piRNA-disease relationships. In addition, the local context graph for each target pair is extracted from original bipartite graph. (ii) Local/global graph representation. The representations of piRNA and disease nodes are captured by global-level GCN, while the pair representations are obtained by local-level GCN. (iii) Association prediction. The dense layer and multi-layer perceptron are applied to reduce feature dimensionality and calculate association scores. Finally, the global-level and local-level association scores are integrated with different weight coefficients to predict the relationships between piRNAs and diseases

Algorithm 1. Local context graph extraction