SNUH methylation classifier for CNS tumors

Abstract Background Methylation profiling of central nervous system (CNS) tumors, pioneered by the German Cancer Research Center, has significantly improved diagnostic accuracy. This study aimed to further enhance the performance of methylation classifiers by leveraging publicly available data and i...

Full description

Saved in:
Bibliographic Details
Main Authors: Kwanghoon Lee, Jaemin Jeon, Jin Woo Park, Suwan Yu, Jae-Kyung Won, Kwangsoo Kim, Chul-Kee Park, Sung-Hye Park
Format: Article
Language:English
Published: BMC 2025-03-01
Series:Clinical Epigenetics
Subjects:
Online Access:https://doi.org/10.1186/s13148-025-01824-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850039469226328064
author Kwanghoon Lee
Jaemin Jeon
Jin Woo Park
Suwan Yu
Jae-Kyung Won
Kwangsoo Kim
Chul-Kee Park
Sung-Hye Park
author_facet Kwanghoon Lee
Jaemin Jeon
Jin Woo Park
Suwan Yu
Jae-Kyung Won
Kwangsoo Kim
Chul-Kee Park
Sung-Hye Park
author_sort Kwanghoon Lee
collection DOAJ
description Abstract Background Methylation profiling of central nervous system (CNS) tumors, pioneered by the German Cancer Research Center, has significantly improved diagnostic accuracy. This study aimed to further enhance the performance of methylation classifiers by leveraging publicly available data and innovative machine-learning techniques. Results Seoul National University Hospital Methylation Classifier (SNUH-MC) addressed data imbalance using the Synthetic Minority Over-sampling Technique (SMOTE) algorithm and incorporated OpenMax within a Multi-Layer Perceptron to prevent labeling errors in low-confidence diagnoses. Compared to two published CNS tumor methylation classification models (DKFZ-MC: Deutsches Krebsforschungszentrum Methylation Classifier v11b4: RandomForest, 767-MC: Multi-Layer Perceptron), our SNUH-MC showed improved performance in F1-score. For ‘Filtered Test Data Set 1,’ the SNUH-MC achieved higher F1-micro (0.932) and F1-macro (0.919) scores compared to DKFZ-MC v11b4 (F1-micro: 0.907, F1-macro: 0.627). We evaluated the performance of three classifiers; SNUH-MC, DKFZ-MC v11b4, and DKFZ-MC v12.5, using specific criteria. We set established ‘Decisions’ categories based on histopathology, clinical information, and next-generation sequencing to assess the classification results. When applied to 193 unknown SNUH methylation data samples, SNUH-MC notably improved diagnosis compared to DKFZ-MC v11b4. Specifically, 17 cases were reclassified as ‘Match’ and 34 cases as ‘Likely Match’ when transitioning from DKFZ-MC v11b4 to SNUH-MC. Additionally, SNUH-MC demonstrated similar results to DKFZ-MC v12.5 for 23 cases that were unclassified by v11b4. Conclusions This study presents SNUH-MC, an innovative methylation-based classification tool that significantly advances the field of neuropathology and bioinformatics. Our classifier incorporates cutting-edge techniques such as the SMOTE and OpenMax resulting in improved diagnostic accuracy and robustness, particularly when dealing with unknown or noisy data.
format Article
id doaj-art-2e6a0d8ccaf342dbbdfd8c54fe024f2a
institution DOAJ
issn 1868-7083
language English
publishDate 2025-03-01
publisher BMC
record_format Article
series Clinical Epigenetics
spelling doaj-art-2e6a0d8ccaf342dbbdfd8c54fe024f2a2025-08-20T02:56:20ZengBMCClinical Epigenetics1868-70832025-03-0117111910.1186/s13148-025-01824-0SNUH methylation classifier for CNS tumorsKwanghoon Lee0Jaemin Jeon1Jin Woo Park2Suwan Yu3Jae-Kyung Won4Kwangsoo Kim5Chul-Kee Park6Sung-Hye Park7Department of Pathology, Seoul National University College of MedicineInterdisciplinary Program in Bioinformatics, Seoul National UniversityDepartment of Pathology, Yonsei University College of MedicineInterdisciplinary Program in Bioinformatics, Seoul National UniversityDepartment of Pathology, Seoul National University College of MedicineDepartment of Transdisciplinary Medicine, Seoul National University HospitalDepartment of Neurosurgery, Seoul National University College of MedicineDepartment of Pathology, Seoul National University College of MedicineAbstract Background Methylation profiling of central nervous system (CNS) tumors, pioneered by the German Cancer Research Center, has significantly improved diagnostic accuracy. This study aimed to further enhance the performance of methylation classifiers by leveraging publicly available data and innovative machine-learning techniques. Results Seoul National University Hospital Methylation Classifier (SNUH-MC) addressed data imbalance using the Synthetic Minority Over-sampling Technique (SMOTE) algorithm and incorporated OpenMax within a Multi-Layer Perceptron to prevent labeling errors in low-confidence diagnoses. Compared to two published CNS tumor methylation classification models (DKFZ-MC: Deutsches Krebsforschungszentrum Methylation Classifier v11b4: RandomForest, 767-MC: Multi-Layer Perceptron), our SNUH-MC showed improved performance in F1-score. For ‘Filtered Test Data Set 1,’ the SNUH-MC achieved higher F1-micro (0.932) and F1-macro (0.919) scores compared to DKFZ-MC v11b4 (F1-micro: 0.907, F1-macro: 0.627). We evaluated the performance of three classifiers; SNUH-MC, DKFZ-MC v11b4, and DKFZ-MC v12.5, using specific criteria. We set established ‘Decisions’ categories based on histopathology, clinical information, and next-generation sequencing to assess the classification results. When applied to 193 unknown SNUH methylation data samples, SNUH-MC notably improved diagnosis compared to DKFZ-MC v11b4. Specifically, 17 cases were reclassified as ‘Match’ and 34 cases as ‘Likely Match’ when transitioning from DKFZ-MC v11b4 to SNUH-MC. Additionally, SNUH-MC demonstrated similar results to DKFZ-MC v12.5 for 23 cases that were unclassified by v11b4. Conclusions This study presents SNUH-MC, an innovative methylation-based classification tool that significantly advances the field of neuropathology and bioinformatics. Our classifier incorporates cutting-edge techniques such as the SMOTE and OpenMax resulting in improved diagnostic accuracy and robustness, particularly when dealing with unknown or noisy data.https://doi.org/10.1186/s13148-025-01824-0MethylationBrain tumorsClassificationNext-generation sequencingTargeted therapy
spellingShingle Kwanghoon Lee
Jaemin Jeon
Jin Woo Park
Suwan Yu
Jae-Kyung Won
Kwangsoo Kim
Chul-Kee Park
Sung-Hye Park
SNUH methylation classifier for CNS tumors
Clinical Epigenetics
Methylation
Brain tumors
Classification
Next-generation sequencing
Targeted therapy
title SNUH methylation classifier for CNS tumors
title_full SNUH methylation classifier for CNS tumors
title_fullStr SNUH methylation classifier for CNS tumors
title_full_unstemmed SNUH methylation classifier for CNS tumors
title_short SNUH methylation classifier for CNS tumors
title_sort snuh methylation classifier for cns tumors
topic Methylation
Brain tumors
Classification
Next-generation sequencing
Targeted therapy
url https://doi.org/10.1186/s13148-025-01824-0
work_keys_str_mv AT kwanghoonlee snuhmethylationclassifierforcnstumors
AT jaeminjeon snuhmethylationclassifierforcnstumors
AT jinwoopark snuhmethylationclassifierforcnstumors
AT suwanyu snuhmethylationclassifierforcnstumors
AT jaekyungwon snuhmethylationclassifierforcnstumors
AT kwangsookim snuhmethylationclassifierforcnstumors
AT chulkeepark snuhmethylationclassifierforcnstumors
AT sunghyepark snuhmethylationclassifierforcnstumors