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 Author: Maram Fahaad Almufareh. Email: email ; Samabia Tehsin. Email: email
(This article belongs to the Special Issue: Mathematical Aspects of Computational Biology and Bioinformatics-III)

Computer Modeling in Engineering & Sciences https://doi.org/10.32604/cmes.2026.081129

Received 24 February 2026; Accepted 12 May 2026; Published online 03 June 2026

Download PDF

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

Computational biology; bioinformatics; cancer computational biology; transcriptomics; interpretable deep learning; pan-cancer analysis; gene expression analysis; machine learning in genomics

Downloads
- Full-Text PDF
Citation Tools
- BibTex
- EndNote
- RIS

144

View
35

Download
0

Like

Introduction to the Special Issue on Mathematical Aspects of Computational Biology and Bioinformatics
Dumitru Baleanu, Carla M. A. Pinto,...
Enhanced Temporal Correlation for Universal Lesion Detection
Muwei Jian, Yue Jin, Hui Yu
Introduction to the Special Issue on Recent Developments on Computational Biology-I
Carlo Cattani, Haci Mehmet Baskonus,...
Evolutionary Safe Padé Approximation Scheme for Dynamical Study of Nonlinear Cervical Human Papilloma Virus Infection Model
Javaid Ali, Armando Ciancio, Kashif...
Data-Driven Healthcare: The Role of Computational Methods in Medical Innovation
Hariharasakthisudhan Ponnarengan,...

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

Abstract

Keywords

144

35

0

Further Information

Guidelines

Follow Us

Join Us

Contact Us

WhatsApp:

Share Link