PCGS: biomarker and risk group identification for Pediatric Cancers via explainable Graph neural networks with Shapley values
This framework outperforms previous supervised multi-omics integration baseline approaches based on glioma and Wilms tumor cohorts and enables GNN model explainability via Shapley value-based feature attribution approaches to explain the contributions of gene-level features across various biomedical tasks, including classification and survival.
Z. Shi, A. Budhkar, W. Amin et al.
· medRxiv · 0 citations