Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 49 min ago
Peer-reviewedCC BY 4.0PLOS One

Graph neural network-based risk stratification of prostate cancer using gene expression and SHAP interpretability

  • Saeed Pirmoradi1
  • Sevil Vaghefi Moghaddam2
  • Mohammadreza Ardalan3
  • Mir Mohsen Sharifi Bonab4
  • Mohammad Teshnehlab
  • Sepideh Zununi Vahed
4 affiliations
  1. 1Neurosciences Research Center, Tabriz University of Medical Sciences, Tabriz, Iran
  2. 2Faculty of Electronic and Computer Engineering Department, K.N. Toosi University of Technology, Tehran, Iran
  3. 3Clinical Research Development Unit of Tabriz Valiasr Hospital, Tabriz University of Medical Sciences, Tabriz, Iran
  4. 4Kidney Research Center, Tabriz University of Medical Sciences, Tabriz, Iran
Open at sourcePDFDOICite

Abstract

Accurate risk stratification is essential for guiding treatment decisions and preventing over treatment of prostate cancer, which remains one of the most prevalent cancers among adult men. While the Gleason score, obtained from prostate biopsies, is routinely used to assess tumor aggressiveness, the biopsy procedure carries risks such as pain, infection, and, in some cases, serious complications such as sepsis. In this study, we proposed an artificial intelligence-based framework that integrates mRNA expression profiles with functional interaction networks to classify prostate cancer patients into low-, medium-, and high-risk groups defined by Gleason scores. The pipeline comprised five steps: (1) data collection from The Cancer Genome Atlas (TCGA), (2) preprocessing of gene expression data, (3) two-stage feature selection to identify informative biomarkers, (4) risk classification using a dual-branch graph neural network (GNN) that combines gene-gene interaction graphs with sample-level expression features, and (5) model interpretation using SHAP to quantify feature contributions. Differentially expressed genes were identified in the High (ASPN, GMNN, PEBP4, C2, KNCK17), Medium (C2, IGSF1, ASPN, CDKN3, AMH), and Low (TNMD, VWA5B2, ST6GALNAC5, CYP3A5, PHGR1) risk groups, underscoring the molecular heterogeneity of disease progression. On an independent held-out test set, the model achieved AUCs of 0.86, 0.88, and 0.95 for the low-, medium-, and high-risk groups, respectively, with an overall accuracy of 80%. These results suggest that combining GNN-based modeling with explainable AI can capture both global and local molecular patterns relevant to tumor aggressiveness. However, as the model was developed and evaluated solely on the TCGA cohort, the findings should be regarded as exploratory, and external validation will be required to establish generalizability. Within these limitations, the proposed framework highlights the potential of molecular profiling and graph-based deep learning to support more precise, potentially less invasive, risk assessment and individualized treatment planning in prostate cancer.

Related

  1. Artificial intelligence-based prostate cancer risk stratification via large-scale ultrasound images paired with histopathology
    Qiong Zhang, Qiang Lu, Yu Liang +3
    Quantitative imaging in medicine and surgeryPeer-reviewedCC BY-NC-NDFull textMedical imaging & radiologyEurope PMC
  2. Machine learning-assisted serum Raman spectroscopy for risk stratification in men with suspected prostate cancer: a retrospective proof-of-concept study
    K. Milligan, I. Smith, A. Flugge +3
    medRxivPreprintAll rights reservedFull textOncologymedRxiv
  3. Molecular stratification of SPOP-mutant prostate cancer demonstrates Wnt signaling and replication stress signatures in diverse patient populations
    Kinza Rizwan, Sai Prasada Rao Manikonda, Heidi Dowst +8
    Cell ReportsPeer-reviewedCC BY 4.0General medicineCrossref
  4. Ai integrated advanced facial expression recognition using hyperscale YOLOV5 capsuled convolution neural network with swarm intelligence technique
    G. NandaGopal, V. S. Arulmurugan, M. Mohammadha Hussaini
    Scientific ReportsPeer-reviewedCC BYFull textGeneral medicineDOAJ
  5. Evaluation of FGD3 Expression in Advanced Prostate Cancer
    Bartosz Malinowski, Paulina Antosik, Layla Settaf-Cherif +2
    BiomedicinesPeer-reviewedCC BYFull textGeneral medicineEurope PMC

Cite

BibTeXRIS
BibTeX
@article{pirmoradi2026graph,
  title = {{Graph neural network-based risk stratification of prostate cancer using gene expression and SHAP interpretability}},
  author = {Saeed Pirmoradi and Sevil Vaghefi Moghaddam and Mohammadreza Ardalan and Mir Mohsen Sharifi Bonab and Mohammad Teshnehlab and Sepideh Zununi Vahed},
  journal = {PLOS One},
  year = {2026},
  month = sep,
  doi = {10.1371/journal.pone.0356727},
  url = {https://doi.org/10.1371/journal.pone.0356727},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Graph neural network-based risk stratification of prostate cancer using gene expression and SHAP interpretability
AU  - Saeed Pirmoradi
AU  - Sevil Vaghefi Moghaddam
AU  - Mohammadreza Ardalan
AU  - Mir Mohsen Sharifi Bonab
AU  - Mohammad Teshnehlab
AU  - Sepideh Zununi Vahed
PY  - 2026
DA  - 2026/09/08
JO  - PLOS One
DO  - 10.1371/journal.pone.0356727
UR  - https://doi.org/10.1371/journal.pone.0356727
AB  - Accurate risk stratification is essential for guiding treatment decisions and preventing over treatment of prostate cancer, which remains one of the most prevalent cancers among adult men. While the Gleason score, obtained from prostate biopsies, is routinely used to assess tumor aggressiveness, the biopsy procedure carries risks such as pain, infection, and, in some cases, serious complications such as sepsis. In this study, we proposed an artificial intelligence-based framework that integrates mRNA expression profiles with functional interaction networks to classify prostate cancer patients into low-, medium-, and high-risk groups defined by Gleason scores. The pipeline comprised five steps: (1) data collection from The Cancer Genome Atlas (TCGA), (2) preprocessing of gene expression data, (3) two-stage feature selection to identify informative biomarkers, (4) risk classification using a dual-branch graph neural network (GNN) that combines gene-gene interaction graphs with sample-level expression features, and (5) model interpretation using SHAP to quantify feature contributions. Differentially expressed genes were identified in the High (ASPN, GMNN, PEBP4, C2, KNCK17), Medium (C2, IGSF1, ASPN, CDKN3, AMH), and Low (TNMD, VWA5B2, ST6GALNAC5, CYP3A5, PHGR1) risk groups, underscoring the molecular heterogeneity of disease progression. On an independent held-out test set, the model achieved AUCs of 0.86, 0.88, and 0.95 for the low-, medium-, and high-risk groups, respectively, with an overall accuracy of 80%. These results suggest that combining GNN-based modeling with explainable AI can capture both global and local molecular patterns relevant to tumor aggressiveness. However, as the model was developed and evaluated solely on the TCGA cohort, the findings should be regarded as exploratory, and external validation will be required to establish generalizability. Within these limitations, the proposed framework highlights the potential of molecular profiling and graph-based deep learning to support more precise, potentially less invasive, risk assessment and individualized treatment planning in prostate cancer.
SN  - 1932-6203
ER  -