Related Experiment Video
Updated: Jul 25, 2026
Identification of Circular RNAs using RNA Sequencing
Published on: November 14, 2019
SAAED: Embedding and Deep Learning Enhance Accurate Prediction of Association Between circRNA and Disease
Qingyu Liu1, Junjie Yu2, Yanning Cai3
1School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China.
Insights
This study introduces SAAED, a novel deep learning method for predicting circular RNA (circRNA)-disease associations. SAAED effectively mines semantic information from diverse data sources, significantly improving prediction accuracy for disease mechanisms.
Area of Science:
- Computational Biology
- Genomics
- Bioinformatics
Background:
- Circular RNAs (circRNAs) play regulatory roles in various diseases, but their precise mechanisms remain unclear.
- Accurate identification of circRNA-disease associations is crucial for understanding disease pathology and developing treatments.
- Existing deep learning models for circRNA-disease association analysis are limited by insufficient data.
Purpose of the Study:
- To propose a novel deep learning method, Semantic Association Analysis by Embedding and Deep learning (SAAED), for predicting circRNA-disease associations.
- To enhance the mining of semantic information from heterogeneous biological data to improve prediction accuracy.
- To provide an efficient tool for identifying potential circRNA-disease relationships.
Main Methods:
- Developed SAAED, comprising an Entity Relation Network (ERN) for data fusion and embedding, and a Pseudo-Siamese Network (PSN) for feature extraction.
- Integrated diverse association data, including circRNA-disease, circRNA-miRNA, disease-gene, disease-miRNA, disease-lncRNA, and disease-drug relationships.
- Evaluated SAAED using the CircR2Disease benchmark dataset with fivefold cross-validation.
Main Results:
- SAAED achieved high performance metrics: 98.92% AUC, 95.39% accuracy, and 93.06% sensitivity.
- The proposed method demonstrated superior performance compared to existing state-of-the-art models.
- SAAED effectively expands the expression of biological related information for circRNA-disease association analysis.
Conclusions:
- SAAED is an efficient and effective method for predicting potential circRNA-disease associations.
- The model's ability to fuse multiple data sources and extract semantic features offers significant advantages.
- This approach holds promise for advancing our understanding of circRNA functions in disease.
Abstract:
Emerging evidence indicates that circRNA can regulate various diseases. However, the mechanisms of circRNA in these diseases have not been fully understood. Therefore, detecting potential circRNA-disease associations has far-reaching significance for pathological development and treatment of these diseases. In recent years, deep learning models are used in association analysis of circRNA-disease, but a lack of circRNA-disease association data limits further improvement. Therefore, there is an urgent need to mine more semantic information from data. In this paper, we propose a novel method called Semantic Association Analysis by Embedding and Deep learning (SAAED), which consists of two parts, a neural network embedding model called Entity Relation Network (ERN) and a Pseudo-Siamese network (PSN) for analysis. ERN can fuse multiple sources of data and express the information with low-dimensional embedding vectors. PSN can extract the feature between circRNA and disease for the association analysis. CircRNA-disease, circRNA-miRNA, disease-gene, disease-miRNA, disease-lncRNA, and disease-drug association information are used in this paper. More association data can be introduced for analysis without restriction. Based on the CircR2Disease benchmark dataset for evaluation, a fivefold cross-validation experiment showed an AUC of 98.92%, an accuracy of 95.39%, and a sensitivity of 93.06%. Compared with other state-of-the-art models, SAAED achieves the best overall performance. SAAED can expand the expression of the biological related information and is an efficient method for predicting potential circRNA-disease association.
