MSGCL: inferring miRNA–disease associations based on multi-view self-supervised graph structure contrastive learning

Abstract

Potential miRNA–disease associations (MDA) play an important role in the discovery of complex human disease etiology. Therefore, MDA prediction is an attractive research topic in the field of biomedical machine learning. Recently, several models have been proposed for this task, but their performance limited by over-reliance on relevant network information with noisy graph structure connections. However, the application of self-supervised graph structure learning to MDA tasks remains unexplored. Our study is the first to use multi-view self-supervised contrastive learning (MSGCL) for MDA prediction. Specifically, we generated a learner view without association labels of miRNAs and diseases as input, and utilized the known association network to generate an anchor view that provides guiding signals for the learner view. The graph structure was optimized by designing a contrastive loss to maximize the consistency between the anchor and learner views. Our model is similar to a pre-trained model that continuously optimizes upstream tasks for high-quality association graph topology, thereby enhancing the latent representation of association predictions. The experimental results show that our proposed method outperforms state-of-the-art methods by 2.79$\%$ and 3.20$\%$ in area under the receiver operating characteristic curve (AUC) and area under the precision/recall curve (AUPR), respectively.

HGCLAMIR: Hypergraph contrastive learning with attention mechanism and integrated multi-view representation for predicting miRNA-disease associations

“…MSGCL [ 26 ]: The method employs self-supervised contrastive learning to optimize the graph structure and utilizes a graph convolutional network encoder to infer the associations between miRNAs and diseases.…”

MGCNSS: miRNA–disease association prediction with multi-layer graph convolution and distance-based negative sample selection strategy

“…Here, we mainly select eleven competitive methods to compare with the proposed model, which are SVM [ 18 ], RF [ 53 ], XGBoost [ 54 ], GCN [ 55 ], GAT [ 56 ], DTIGAT [ 57 ], DTICNN [ 58 ], NeoDTI [ 59 ], MSGCL [ 3 ], AMHMDA [ 35 ] and GATMDA [ 13 ]:…”

“…MSGCL [ 3 ]: adopts the multi-view self-supervised contrastive learning for MDA prediction that could enhance the latent representation by maximizing the consistency between different views.…”

“…Research has demonstrated that many miRNAs could participate in the regulation of gene expression after transcription in both animals and plants [ 2 ]. They could also serve as potential diagnostic markers and therapeutic targets [ 3 ]. These miRNAs regulate about one-third of human genes that are highly associated with complex human diseases.…”

DEJKMDR: miRNA-disease association prediction method based on graph convolutional network

“…A strategy predicting miRNA-Disease Associations via Node-Level Attention Graph Auto-Encoder was conducted by Zhang et al ( 8 ). The MSGCL, an approach that utilizes multi-view self-supervised graph-based contrastive modeling for inferring miRNA–disease associations, was recommended by Ruan et al ( 9 ). A study to explore disease regulation by investigating microRNA-dependent modulation of gene expression in GABAergic interneurons was offered by Kołosowska et al ( 10 ).…”