Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 57 min ago
Peer-reviewedCC BYAdvanced intelligent systems (Weinheim an der Bergstrasse, Germany)

MetaPaCS: A Novel Meta-Learning Framework for Pancreatic Cancer Subtype Identification.

  • Nick B Peterson1
  • Mengtao Sun1
  • Xinchao Wu1
  • Jieqiong Wang2
  • Shibiao Wan1,3
  1. 1Department of Genetics, Cell Biology and Anatomy, University of Nebraska Medical Center, Omaha, Nebraska, USA.
  2. 2Department of Neurological Sciences, University of Nebraska Medical Center, Omaha, Nebraska, USA.
  3. 3Fred and Pamela Buffett Cancer Center, University of Nebraska Medical Center, Omaha, Nebraska, USA.
Read full textPDFDOICite

Abstract

Pancreatic cancer (PaC), the third leading cause of cancer related deaths in the United States, is a highly heterogenous malignancy with a multitude of potential subtypes. Each PaC subtype has unique molecular pathways and therapeutic characteristics, which can be used in downstream patient risk stratification and tailored treatment design. Conventional wet-lab approaches for PaC subtyping (microdissection, histopathological studies, etc.) are laborious, costly, and time-consuming. To address these concerns, we present MetaPaCS, a novel meta-learning framework to accurately identify PaC subtypes based on transcriptomics data. Specifically, after preprocessing, the transcriptome-based feature vectors are classified by multiple base machine learning classifiers, whose diverse prediction outputs are combined with the initial preprocessed feature vectors to constitute a new set of ensemble feature vectors for a meta-learning classifier. Leave-one-out cross-validation demonstrates that MetaPaCS performs remarkably better optimized individual base classifiers. We believe that MetaPaCS is a promising tool for downstream risk stratification and personalized treatment design.

Related

  1. Explainable computational framework for subtype classification and biomarker identification in head and neck squamous cell carcinoma using machine learning
    Anagha Rajan, Christopher Leela Biji, Mangalam Goutam Sinha +1
    PLOS OnePeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationBioinformatics & computational biologyPLOSPMC
  2. Machine learning-supported identification of necrosis in colorectal and pancreatic cancer spheroids
    Miguel Martínez Lozano, Heinz D. Wanzenboeck, Sonia Prado-López
    PLOS OnePeer-reviewedCC BY 4.0Full textOncologyPLOS
  3. Epigenetic progression of pancreatic cancer to aggressive subtypes involves alternate routes of lineage reprogramming in subtype-intermediate progenitor cells
    K. A. Hawthorne, J. R. Eng, M. Tsuda +12
    bioRxivPreprintAll rights reservedFull textOncologybioRxiv
  4. MetScore and classical-basal subtype intersect to define chemotherapy response and tumor microenvironment architecture in pancreatic ductal adenocarcinoma
    R. E. Preston, H. Huang, M. A. Hall +7
    bioRxivPreprintCC BY-NCFull textOncologybioRxiv
  5. Coordinated upregulation of Hippo, NF-κB and interferon pathway genes in pancreatic ductal adenocarcinoma: a retrospective tissue qRT-PCR profiling study with external tumour-versus-non-tumour validation, molecular subtype and survival analyses.
    Eda Balkan, Murat Kızılkaya, Sevilay Özmen +5
    BMC gastroenterologyPeer-reviewedCC BY-NC-NDFull textOncologyEurope PMCDOAJ

Cite

BibTeXRIS
BibTeX
@article{peterson2026metapacs,
  title = {{MetaPaCS: A Novel Meta-Learning Framework for Pancreatic Cancer Subtype Identification.}},
  author = {Nick B Peterson and Mengtao Sun and Xinchao Wu and Jieqiong Wang and Shibiao Wan},
  journal = {Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)},
  year = {2026},
  month = oct,
  doi = {10.1002/aisy.70576},
  url = {https://europepmc.org/article/MED/42997493},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - MetaPaCS: A Novel Meta-Learning Framework for Pancreatic Cancer Subtype Identification.
AU  - Nick B Peterson
AU  - Mengtao Sun
AU  - Xinchao Wu
AU  - Jieqiong Wang
AU  - Shibiao Wan
PY  - 2026
DA  - 2026/10/15
JO  - Advanced intelligent systems (Weinheim an der Bergstrasse, Germany)
DO  - 10.1002/aisy.70576
UR  - https://europepmc.org/article/MED/42997493
AB  - Pancreatic cancer (PaC), the third leading cause of cancer related deaths in the United States, is a highly heterogenous malignancy with a multitude of potential subtypes. Each PaC subtype has unique molecular pathways and therapeutic characteristics, which can be used in downstream patient risk stratification and tailored treatment design. Conventional wet-lab approaches for PaC subtyping (microdissection, histopathological studies, etc.) are laborious, costly, and time-consuming. To address these concerns, we present MetaPaCS, a novel meta-learning framework to accurately identify PaC subtypes based on transcriptomics data. Specifically, after preprocessing, the transcriptome-based feature vectors are classified by multiple base machine learning classifiers, whose diverse prediction outputs are combined with the initial preprocessed feature vectors to constitute a new set of ensemble feature vectors for a meta-learning classifier. Leave-one-out cross-validation demonstrates that MetaPaCS performs remarkably better optimized individual base classifiers. We believe that MetaPaCS is a promising tool for downstream risk stratification and personalized treatment design.
SN  - 2640-4567
ER  -