GCNFORMER: graph convolutional network and transformer for predicting lncRNA-disease associations

Abstract

Background: A growing body of researches indicate that the disrupted expression of long non-coding RNA (lncRNA) is linked to a range of human disorders. Therefore, the effective prediction of lncRNA-disease association (LDA) can not only suggest solutions to diagnose a condition but also save significant time and labor costs.

Method: In this work, we proposed a novel LDA predicting algorithm based on graph convolutional network and transformer, named GCNFORMER. Firstly, we integrated the intraclass similarity and interclass connections between miRNAs, lncRNAs and diseases, and built a graph adjacency matrix. Secondly, to completely obtain the features between various nodes, we employed a graph convolutional network for feature extraction. Finally, to obtain the global dependencies between inputs and outputs, we used a transformer encoder with a multiheaded attention mechanism to forecast lncRNA-disease associations.

Results: The results of fivefold cross-validation experiment on the public dataset revealed that the AUC and AUPR of GCNFORMER achieved 0.9739 and 0.9812, respectively. We compared GCNFORMER with six advanced LDA prediction models, and the results indicated its superiority over the other six models. Furthermore, GCNFORMER's effectiveness in predicting potential LDAs is underscored by case studies on breast cancer, colon cancer and lung cancer.

Conclusions: The combination of graph convolutional network and transformer can effectively improve the performance of LDA prediction model and promote the in-depth development of this research filed.

Keywords: Graph convolutional network; LncRNA-disease association prediction; Machine learning; Multiheaded attention mechanism; transformer.

Fig. 1

The flowchart of constructing the GCNFORMER model

Fig. 2

ROC curves of seven LDA prediction models on dataset 1

Fig. 3

AUPR curves of seven LDA prediction models on dataset 1

Fig. 4

AUC results are compared for various GCN embedding sizes and layer counts