GATNNCDA: A Method Based on Graph Attention Network and Multi-Layer Neural Network for Predicting circRNA-Disease Associations

• Published in: International journal of molecular sciences 2021-08, Vol.22 (16), p.8505
• Main Authors: Ji, Cunmei, Liu, Zhihao, Wang, Yutian, Ni, Jiancheng, Zheng, Chunhou
• Format: Article
• Language: English
• Subjects: Accuracy; Alzheimer's disease; Biomarkers; Biosynthesis; Breast cancer; Breast Neoplasms - genetics; Breast Neoplasms - metabolism; Carcinoma, Hepatocellular - genetics; Carcinoma, Hepatocellular - metabolism; circRNA–disease associations; Closed loops; Computational Biology; Computer applications; Databases, Nucleic Acid; Datasets; Deep learning; Experiments; Female; Gastric cancer; graph attention network; Hepatocellular carcinoma; Humans; Liver Neoplasms - genetics; Liver Neoplasms - metabolism; Methods; multi-layer neural network; Multilayers; Neural networks; Neural Networks, Computer; Performance evaluation; RNA, Circular - genetics; RNA, Circular - metabolism; RNA, Neoplasm - genetics; RNA, Neoplasm - metabolism; Semantics; Similarity
• ISSN: 1422-0067; 1661-6596; 1422-0067
• DOI: 10.3390/ijms22168505

Circular RNAs (circRNAs) are a new class of endogenous non-coding RNAs with covalent closed loop structure. Researchers have revealed that circRNAs play an important role in human diseases. As experimental identification of interactions between circRNA and disease is time-consuming and expensive, effective computational methods are an urgent need for predicting potential circRNA-disease associations. In this study, we proposed a novel computational method named GATNNCDA, which combines Graph Attention Network (GAT) and multi-layer neural network (NN) to infer disease-related circRNAs. Specially, GATNNCDA first integrates disease semantic similarity, circRNA functional similarity and the respective Gaussian Interaction Profile (GIP) kernel similarities. The integrated similarities are used as initial node features, and then GAT is applied for further feature extraction in the heterogeneous circRNA-disease graph. Finally, the NN-based classifier is introduced for prediction. The results of fivefold cross validation demonstrated that GATNNCDA achieved an average AUC of 0.9613 and AUPR of 0.9433 on the CircR2Disease dataset, and outperformed other state-of-the-art methods. In addition, case studies on breast cancer and hepatocellular carcinoma showed that 20 and 18 of the top 20 candidates were respectively confirmed in the validation datasets or published literature. Therefore, GATNNCDA is an effective and reliable tool for discovering circRNA-disease associations.