EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Self-Normalizing Multi-Omics Neural Network for Pan-Cancer Prognostication

Asim Waqas iD, Aakash Tripathi iD, Sabeen Ahmed iD, Ashwin Mukund iD, Hamza Farooq iD, Joseph O Johnson, Paul A Stewart iD, Mia Naeini iD, Matthew B Schabath iD, Ghulam Rasool iD

International Journal of Molecular Sciences · 30.07.2025 · 26 (15) · 7358

DOI: 10.3390/ijms26157358 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Molecular Sciences, online erschienen am 30.07.2025. Verfasst von Asim Waqas und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cancer Epidemiology, Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA. Hauptthemen laut MEDLINE: Neoplasms, Neural Networks, Computer. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, NIH HHS, State of Florida Bankhead Coley Research Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Prognostic markers such as overall survival (OS) and tertiary lymphoid structure (TLS) ratios, alongside diagnostic signatures like primary cancer-type classification, provide critical information for treatment selection, risk stratification, and longitudinal care planning across the oncology continuum. However, extracting these signals solely from sparse, high-dimensional multi-omics data remains a major challenge due to heterogeneity and frequent missingness in patient profiles. To address this challenge, we present SeNMo, a self-normalizing deep neural network trained on five heterogeneous omics layers—gene expression, DNA methylation, miRNA abundance, somatic mutations, and protein expression—along with the clinical variables, that learns a unified representation robust to missing modalities. Trained on more than 10,000 patient profiles across 32 tumor types from The Cancer Genome Atlas (TCGA), SeNMo provides a baseline that can be readily fine-tuned for diverse downstream tasks. On a held-out TCGA test set, the model achieved a concordance index of 0.758 for OS prediction, while external evaluation yielded 0.73 on the CPTAC lung squamous cell carcinoma cohort and 0.66 on an independent 108-patient Moffitt Cancer Center cohort. Furthermore, on Moffitt’s cohort, baseline SeNMo fine-tuned for TLS ratio prediction aligned with expert annotations (p < 0.05) and sharply separated high- versus low-TLS groups, reflecting distinct survival outcomes. Without altering the backbone, a single linear head classified primary cancer type with 99.8% accuracy across the 33 classes. By unifying diagnostic and prognostic predictions in a modality-robust architecture, SeNMo demonstrated strong performance across multiple clinically relevant tasks, including survival estimation, cancer classification, and TLS ratio prediction, highlighting its translational potential for multi-omics oncology applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NeoplasmsNeural Networks, ComputerHumansPrognosisBiomarkers, TumorDNA MethylationMutationMicroRNAsGene Expression Regulation, NeoplasticMultiomics

Stichwörter der Autor:innen

cancerclassificationdeep learningmachine learningmulti-omicsmultimodaloncologypan-cancersurvival

Substanzen

Biomarkers, TumorMicroRNAs

Autor:innen und Institutionen

  • Department of Cancer Epidemiology, Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA.
  • Department of Machine Learning, Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA.
  • Department of Electrical Engineering, University of South Florida, Tampa, FL 33620, USA.
  • Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN 55455, USA.
  • Analytic Microscopy Core Facility, Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA.
  • Huntsman Cancer Institute, University of Utah, Salt Lake City, UT 84112, USA.

ORCID-Profile: Asim Waqas, Aakash Tripathi, Sabeen Ahmed, Ashwin Mukund, Hamza Farooq, Paul A Stewart, Mia Naeini, Matthew B Schabath, Ghulam Rasool

Förderung

  • National Science Foundation
  • NIH HHS
  • State of Florida Bankhead Coley Research Program
  • Moffitt Cancer Center Biostatistics and Bioinformatics Shared Resource
  • NIH
  • Biostatistics and Bioinformatics Shared Resource at the H. Lee Moffitt Cancer Center &amp; Research Institute
  • Huntsman Cancer Foundation and the National Cancer Institute of the National Institutes of Health

Zitieren

APA

Waqas, A., Tripathi, A., Ahmed, S., Mukund, A., Farooq, H., Johnson, J. O., Stewart, P. A., Naeini, M., Schabath, M. B., & Rasool, G. (2025). Self-Normalizing Multi-Omics Neural Network for Pan-Cancer Prognostication. International Journal of Molecular Sciences, 26(15), 7358. https://doi.org/10.3390/ijms26157358

Vancouver

Waqas A, Tripathi A, Ahmed S, Mukund A, Farooq H, Johnson JO, et al. Self-Normalizing Multi-Omics Neural Network for Pan-Cancer Prognostication. International Journal of Molecular Sciences. 2025;26(15):7358. doi:10.3390/ijms26157358

BibTeX
@article{Waqas2025,
  author = {Waqas, Asim and Tripathi, Aakash and Ahmed, Sabeen and Mukund, Ashwin and Farooq, Hamza and Johnson, Joseph O and Stewart, Paul A and Naeini, Mia and Schabath, Matthew B and Rasool, Ghulam},
  title = {Self-Normalizing Multi-Omics Neural Network for Pan-Cancer Prognostication},
  journal = {International Journal of Molecular Sciences},
  year = {2025},
  volume = {26},
  number = {15},
  pages = {7358},
  doi = {10.3390/ijms26157358}
}
Kostenlos starten →