@article{Almufareh2026, 
author = {Maram Fahaad Almufareh and Samabia Tehsin},
title = {Interpretable Deep Representation Learning for Pan-Cancer Diagnosis via Pathway-Constrained Transcriptomics},
year = {2026},
journal = {Computer Modeling in Engineering & Sciences},
volume = {147},
number = {3},
pages = {29},
keywords = {Computational biology, bioinformatics, cancer computational biology, transcriptomics, interpretable deep learning, pan-cancer analysis, gene expression analysis, machine learning in genomics},
url = {https://www.sciopen.com/article/10.32604/cmes.2026.081129},
doi = {10.32604/cmes.2026.081129},
abstract = {This article presents a Hierarchical Pathway-Masked Attention Autoencoder (H-PAAE), a biologically inspired representation-learning framework that enables explainable AI-guided cancer diagnosis. The model directly integrates the curated MSigDB Hallmark pathways, introducing pathway-constrained information flow and mechanistic interpretability through multi-level attention mechanisms. Based on TCGA RNA-seq data from 33 tumor types, H-PAAE compresses approximately 20,000 genes into a 128-dimensional latent space while preserving biologically meaningful structure. When used with XGBoost classification, H-PAAE delivers 92.37% test accuracy and 99.38% macro-AUROC with robust cross-validation results (92.5  ± 0.6%). SHAP analysis identifies a small number of key latent features, corresponding to conserved oncogenic processes, and pathway enrichment analysis shows strong overlap with cancer hallmarks. H-PAAE provides a clear and interpretable biological foundation for pan-cancer classification, with well-calibrated posterior probabilities that can be used for clinical decision-making, and can be easily integrated into multimodal diagnostic workflows.}
}