Integrating BERT pre-training with graph common neighbours for predicting ceRNA interactions
Our findings demonstrate that by integrating RNA sequence information with interaction relationships within the graph, the BCGP model significantly enhances the accuracy of association prediction. This provides a new computational tool for understanding complex gene regulatory networks.
Authors
- Shiyang Liang (ORCID: https://orcid.org/0000-0002-6941-2404)
- Junhua Liu (ORCID: https://orcid.org/0000-0003-1460-7244)
- Jing Ge
- Zhengxing Xie
- Lianghua Tang
- Tianping Ying
Institutions
- The University of Melbourne (AU)
- Guizhou University (CN)
- Jiuquan Iron & Steel (China) (CN)
- Affiliated Hospital of Guizhou Medical University (CN)
Publication Details
- Journal
- Frontiers in Genetics
- Published
- 2025-09-03
- DOI
- https://doi.org/10.3389/fgene.2025.1606016
- Primary Topic
- Cancer-related molecular mechanisms research
- Type
- article
- Field-Weighted Citation Impact
- 0.00