Related Experiment Video
Updated: Aug 23, 2025
10:27
In Silico Identification and Characterization of circRNAs During Host-Pathogen Interactions
Published on: October 21, 2022
1.6K
XGBCDA: a multiple heterogeneous networks-based method for predicting circRNA-disease associations
Siyuan Shen1, Junyi Liu2, Cheng Zhou2
1School of Software, Xinjiang University, Wulumuqi, 830091, China.
BMC Medical Genomics
|November 4, 2022
Summary
A new computational model, XGBCDA, efficiently predicts circular RNA (circRNA)-disease associations. This method aids researchers by identifying potential links, reducing experimental costs and time.
Area of Science:
- Bioinformatics
- Computational Biology
- Genomics
Background:
- Circular RNAs (circRNAs) are crucial in biological processes and diseases.
- Experimental detection of circRNA-disease associations is time-consuming and expensive.
Purpose of the Study:
- To develop an efficient computational model for predicting circRNA-disease associations.
- To reduce the cost and time associated with experimental methods.
Main Methods:
- Proposed a multiple heterogeneous networks-based method (XGBCDA).
- Extracted statistical and graph theory features from integrated circRNA and disease networks.
- Utilized XGBoost classifier to learn latent features and combined them with original features for prediction.
Main Results:
- Achieved an Area Under the ROC Curve of 0.9860 in tenfold cross-validation.
- Demonstrated strong performance in case studies for colorectal, gastric, and cervical cancers.
Conclusions:
- XGBCDA effectively predicts potential circRNA-disease associations.
- The method shows promise in assisting biomedical researchers in this field.
