Interpretable Graph Kolmogorov-Arnold Networks for Multi-Cancer Classification and Biomarker Identification using Multi-Omics Data
arXiv:2503.22939v4 Announce Type: replace Abstract: The integration of heterogeneous multi-omics datasets at a systems level remains a central challenge for developing analytical and computational models in precision cancer diagnostics. This paper introduces Multi-Omics Graph Kolmogorov-Arnold Network (MOGKAN), a deep learning framework that utilizes messenger-RNA, micro-RNA sequences, and DNA methylation samples together with Protein-Protein Interaction (PPI) networks for cancer classification across 31 different cancer types. The proposed approach combines differential gene expression with D
Advances in deep learning and computational biology are converging, enabling more sophisticated integration of complex biological datasets for medical applications.
This development offers a more comprehensive and interpretable approach to cancer diagnostics and biomarker discovery, potentially leading to more targeted and effective treatments.
The ability to classify multiple cancer types simultaneously and identify biomarkers using an interpretable AI framework could accelerate the development of precision oncology.
- · Precision medicine companies
- · Oncology researchers
- · Pharmaceutical industry
- · Cancer patients
- · Traditional diagnostic methods
Improved early detection rates and personalized treatment strategies for various cancers.
Reduced healthcare costs due to more effective and less trial-and-error based therapies.
The acceleration of drug discovery and development for oncology, leading to a paradigm shift in cancer treatment approaches.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG