Advancing CNS tumor diagnostics with expanded DNA methylation-based classification.

Area of Science:

• Neuro-oncology
• Molecular Diagnostics
• Genomics

Background:

• DNA methylation profiling is crucial for classifying central nervous system (CNS) tumors, as recognized by the World Health Organization (WHO).
• Previous versions of the Heidelberg CNS Tumor Methylation Classifier have aided in tumor classification.

Purpose of the Study:

• To introduce and validate the Heidelberg CNS Tumor Methylation Classifier version 12.8 (v12.8).
• To expand the classification of CNS tumors by incorporating novel subclasses.
• To enhance diagnostic precision in neuro-oncology.

Main Methods:

• Training the v12.8 classifier on 7,495 DNA methylation profiles.
• Utilizing a random forest methodology for classification.
• Performing five-fold nested cross-validation for rigorous validation.

Main Results:

• The v12.8 classifier recognizes 184 CNS tumor subclasses, a significant expansion from 91 classes.
• Achieved 95% accuracy at the subclass level with a Brier score of 0.028.
• Demonstrated superior performance compared to previous versions and traditional WHO diagnostics.

Conclusions:

• The Heidelberg CNS Tumor Methylation Classifier v12.8 offers enhanced precision and practical utility for neuro-oncological diagnostics.
• The expanded classification and validated accuracy support its role in personalized neuro-oncology.
• DNA methylation profiling is pivotal for advancing CNS tumor classification and patient care.