Open Access

ARTICLE

Interpretable Deep Representation Learning for Pan-Cancer Diagnosis via Pathway-Constrained Transcriptomics

Maram Fahaad Almufareh^1,*, Samabia Tehsin^2,*

1 Department of Information Systems, College of Computer and Information Sciences, Jouf University, Al-Jawf, Saudi Arabia
2 Center of Excellence–AI, Bahria University, Islamabad, Pakistan

* Corresponding Authors: Maram Fahaad Almufareh. Email: ; Samabia Tehsin. Email:

(This article belongs to the Special Issue: Mathematical Aspects of Computational Biology and Bioinformatics-III)

Computer Modeling in Engineering & Sciences 2026, 147(3), 29 https://doi.org/10.32604/cmes.2026.081129

Received 24 February 2026; Accepted 12 May 2026; Issue published 30 June 2026

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.

---

Keywords

---