Related Experiment Video
Updated: Jan 2, 2026
08:51
Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts
Published on: September 20, 2024
1.9K
An efficient approach based on multi-sources information to predict circRNA-disease associations using deep
Lei Wang1, Zhu-Hong You1, Yu-An Huang2
1Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences, Urumqi 830011, China.
Bioinformatics (Oxford, England)
|December 4, 2019
Summary
This study introduces a computational method to predict circular RNA (circRNA) and disease associations. The novel approach accurately identifies potential biomarkers, aiding disease diagnosis and research.
Area of Science:
- Biochemistry
- Genomics
- Computational Biology
Background:
- Circular RNAs (circRNAs) are increasingly recognized for their roles in human diseases.
- Biomarkers derived from circRNAs offer new diagnostic and pathogenetic insights.
- Experimental detection of circRNA-disease associations is limited by scale, cost, and time.
Purpose of the Study:
- To develop an efficient computational method for predicting circRNA-disease associations.
- To provide a large-scale, rapid, and cost-effective approach for identifying potential circRNA-disease links.
- To offer promising candidates for experimental validation in biological research.
Main Methods:
- A computational method integrating multi-source information was developed.
- Disease semantic similarity and Gaussian interaction profile kernel similarities were fused.
- Deep features were extracted using a deep convolutional neural network (CNN).
- Predictions were made using an extreme learning machine classifier.
Main Results:
- The proposed method achieved 87.21% prediction accuracy and 88.50% sensitivity.
- The model demonstrated superior performance compared to state-of-the-art SVM classifiers.
- Experimental validation confirmed 7 out of the top 15 predicted circRNA-disease pairs through literature search.
Conclusions:
- The developed computational model is effective for predicting circRNA-disease associations.
- The method provides reliable candidates for guiding future biological experiments.
- This approach accelerates the understanding of circRNA roles in disease pathogenesis.
