A multi-representation deep-learning framework for accurate multicancer classification
These findings demonstrate GraphVar as a robust and interpretable framework for multicancer classification. The model's high accuracy and its ability to identify functionally meaningful genomic signatures indicate its potential as a tool to support precision diagnostics and therapeutic strategies, warranting further translational studies.
Authors
- Guojing He (ORCID: https://orcid.org/0000-0003-0716-0464)
- Mingze Bai (ORCID: https://orcid.org/0000-0002-9782-2056)
- Kunxian Shu (ORCID: https://orcid.org/0000-0003-4487-2727)
- Yu Wang (ORCID: https://orcid.org/0000-0002-0431-1039)
- Dan Pu (ORCID: https://orcid.org/0000-0002-0156-898X)
- Xiao Yang (ORCID: https://orcid.org/0000-0001-5649-7763)
Institutions
- Chongqing University of Posts and Telecommunications (CN)
Publication Details
- Journal
- Journal of Translational Medicine
- Published
- 2025-11-19
- DOI
- https://doi.org/10.1186/s12967-025-07325-1
- Citations
- 2
- Primary Topic
- Bioinformatics and Genomic Networks
- Type
- article
- Field-Weighted Citation Impact
- 1.61
Funders
- Natural Science Foundation of Chongqing
- Centre Scientifique et Technique du Bâtiment