EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable computational framework for subtype classification and biomarker identification in head and neck squamous cell carcinoma using machine learning

Erklärbarer computergestützter Rahmen zur Subtypklassifikation und Biomarker-Identifikation beim Plattenepithelkarzinom des Kopf-Hals-Bereichs mithilfe von Machine Learning

Anagha Rajan, Christopher Leela Biji, Mangalam Goutam Sinha iD, Iyappan Ramalakshmi Oviya

PLOS One · 04.11.2026 · 21 (11) · e0360612

DOI: 10.1371/journal.pone.0360612 ↗

Auf einen Blick

Eine XAI-Methode klassifizierte molekulare HNSCC-Subtypen anhand von Transkriptomdaten. Das XGBoost-Modell erreichte nach Tuning und Cross-Validation 95 % Genauigkeit.

Fragestellung

Lässt sich ein erklärbares Machine-Learning-Modell zur Klassifikation der molekularen HNSCC-Subtypen entwickeln und zur Identifikation von Biomarkern nutzen?

Methode

XAI-Modell mit Transkriptomdaten aus TCGA-HNSC und GSE65858; SHAP zur Genbewertung, STRING und MCC für Hub-Gene; Vergleich mehrerer ML-Verfahren einschließlich XGBoost.

Ergebnisse

Das XGBoost-Modell erreichte 95 % Genauigkeit. Es wurden subtypspezifische Biomarker identifiziert; zusätzlich erfolgten Pathway-Analyse, Survival-Analyse und Druggability-Bewertung.

Schlussfolgerung der Autor:innen

Die Autor:innen berichten, dass die identifizierten Biomarker Potenzial für die Entwicklung zielgerichteter Therapien zeigen.

Kernaussagen

  • XGBoost erreichte 95 % Genauigkeit
  • SHAP, STRING und MCC dienten zur Biomarker-Priorisierung
  • Subtypspezifische Biomarker und Signalwege wurden identifiziert

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 04.11.2026. Verfasst von Anagha Rajan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Sciences, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Chennai, India. Hauptthemen laut MEDLINE: Biomarkers, Tumor, Machine Learning, Head and Neck Neoplasms, Squamous Cell Carcinoma of Head and Neck. Die Arbeit nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The precise classification of basal, classical, atypical, and mesenchymal subtypes of Head and Neck Squamous Cell Carcinoma (HNSCC) is crucial for advancing precision oncology. Our research aims to develop an explainable subtype classification model for HNSCC.These molecular subtypes have been previously defined; reliable and meaningful computational methods for the classification of molecular subtypes and prioritization of molecular biomarkers for each subtype do not exist. We developed an explainable artificial intelligence (XAI) model that classifies molecular subtypes based on combined transcriptomic profiles from The Cancer Genome Atlas (TCGA-HNSC) and Gene Expression Omnibus (GSE65858). SHapley Additive exPlanations (SHAP) were used to quantify the importance of genes for model predictions. Subsequently, genes with high predictive importance were analyzed in protein-protein interactions using STRING, and hub genes were identified by Maximum Clique Centrality (MCC) and used for the identification of candidate biomarkers for each of the subtypes. We employed machine learning methods such as Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), AdaBoost (AB), Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Gaussian Naive Bayes (GNB), XGBoost (XGB), and Gradient Boosting (GB). The XGBoost model achieved an accuracy of 95% after hyperparameter tuning and cross-validation. Biologically relevant subtype-specific biomarkers associated with each molecular subtype were identified. To highlight the potential biological functions of these biomarkers, pathway analysis was performed. Further assessment of these genes, such as survival analysis and druggability, showed promise for the development of targeted therapies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Biomarkers, TumorMachine LearningHead and Neck NeoplasmsSquamous Cell Carcinoma of Head and NeckComputational BiologyHumansBoosting Machine Learning AlgorithmsClassification AlgorithmsGene Expression ProfilingRandom ForestSupport Vector MachineGene Expression Regulation, NeoplasticPredictive Learning Models

Substanzen

Biomarkers, Tumor

Autor:innen und Institutionen

  • Department of Sciences, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Chennai, India.
  • School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India.
  • Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Chennai, India.

ORCID-Profile: Mangalam Goutam Sinha

Zitieren

APA

Rajan, A., Biji, C. L., Sinha, M. G., & Oviya, I. R. (2026). Explainable computational framework for subtype classification and biomarker identification in head and neck squamous cell carcinoma using machine learning. PLOS One, 21(11), e0360612. https://doi.org/10.1371/journal.pone.0360612

Vancouver

Rajan A, Biji CL, Sinha MG, Oviya IR. Explainable computational framework for subtype classification and biomarker identification in head and neck squamous cell carcinoma using machine learning. PLOS One. 2026;21(11):e0360612. doi:10.1371/journal.pone.0360612

BibTeX
@article{Rajan2026,
  author = {Rajan, Anagha and Biji, Christopher Leela and Sinha, Mangalam Goutam and Oviya, Iyappan Ramalakshmi},
  title = {Explainable computational framework for subtype classification and biomarker identification in head and neck squamous cell carcinoma using machine learning},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {11},
  pages = {e0360612},
  doi = {10.1371/journal.pone.0360612}
}
Kostenlos starten →