GraphCDA: a hybrid graph representation learning framework based on GCN and GAT for predicting disease-associated circRNAs

Abstract

Motivation: CircularRNA (circRNA) is a class of noncoding RNA with high conservation and stability, which is considered as an important disease biomarker and drug target. Accumulating pieces of evidence have indicated that circRNA plays a crucial role in the pathogenesis and progression of many complex diseases. As the biological experiments are time-consuming and labor-intensive, developing an accurate computational prediction method has become indispensable to identify disease-related circRNAs. Results: We presented a hybrid graph representation learning framework, named GraphCDA, for predicting the potential circRNA–disease associations. Firstly, the circRNA–circRNA similarity network and disease–disease similarity network were constructed to characterize the relationships of circRNAs and diseases, respectively. Secondly, a hybrid graph embedding model combining Graph Convolutional Networks and Graph Attention Networks was introduced to learn the feature representations of circRNAs and diseases simultaneously. Finally, the learned representations were concatenated and employed to build the prediction model for identifying the circRNA–disease associations. A series of experimental results demonstrated that GraphCDA outperformed other state-of-the-art methods on several public databases. Moreover, GraphCDA could achieve good performance when only using a small number of known circRNA–disease associations as the training set. Besides, case studies conducted on several human diseases further confirmed the prediction capability of GraphCDA for predicting potential disease-related circRNAs. In conclusion, extensive experimental results indicated that GraphCDA could serve as a reliable tool for exploring the regulatory role of circRNAs in complex diseases.

Drug–target interaction predictions with multi-view similarity network fusion strategy and deep interactive attention mechanism

“…Ten competitive approaches are selected for comparison with MIDTI and we evaluate them with ACC, AUC and AUPR metrics. They are Random Forests (RF) ( Pedregosa et al 2011 ), Support-Vector Machine (SVM) ( Chang and Lin 2011 ), eXtreme Gradient Boosting (XGBoost) ( Chen and Guestrin 2016 ), GCN ( Kipf and Welling 2016 ), Graph Attention Networks (GAT) ( Veličković et al 2017 ), DTI-CNN ( Peng et al 2020 ), GCNMDA ( Long et al 2020 ), MVGCN ( Fu et al 2022 ), MMGCN ( Tang et al 2021 ), GraphCDA ( Dai et al 2022 ), and DTINet ( Luo et al 2017 ). The description for these comparison approaches is presented in Supplementary Section S5 .…”

KGETCDA: an efficient representation learning framework based on knowledge graph encoder from transformer for predicting circRNA-disease associations

“…Following previous studies (19, 28, 38), 5-fold cross-validation (CV) method is adopted to evaluate KGETCDA and compare with other SOTA models in this paper. Specially, in the 5-fold CV, all samples of the whole dataset are randomly divided into five equal parts and each part is selected for testing in turn while the remaining parts is utilized to train the model.…”

“…To further evaluate the effectiveness of KGETCDA, case studies are conducted on both two datasets. Following (23, 38, 62), we train the model KGETCDA on all known CDA, and then predict potential probabilities for all unknown CDA and sort them in descending order. Moreover, we collect experimental evidence to verify them in public databases and newly published literatures, and the results are listed in Table 2.…”

A Biological Feature and Heterogeneous Network Representation Learning-Based Framework for Drug–Target Interaction Prediction

“…The random forest algorithm can make the optimal classification decision based on the extracted drug target features, thus improving the prediction performance of DTI [ 47 ]. In addition, although BG-DTI is mainly used to predict DTI, it is a portable method and it can be widely used to solve problems in bioinformatics fields such as predicting the correlation between circRNAs and diseases [ 48 , 49 , 50 , 51 ].…”