A Novel Method for Rapid Molecular Subgrouping of Medulloblastoma
Bibliographic record
Abstract
Abstract Purpose: The classification of medulloblastoma into WNT, SHH, group 3, and group 4 subgroups has become of critical importance for patient risk stratification and subgroup-tailored clinical trials. Here, we aimed to develop a simplified, clinically applicable classification approach that can be implemented in the majority of centers treating patients with medulloblastoma. Experimental Design: We analyzed 1,577 samples comprising previously published DNA methylation microarray data (913 medulloblastomas, 457 non-medulloblastoma tumors, 85 normal tissues), and 122 frozen and formalin-fixed paraffin-embedded medulloblastoma samples. Biomarkers were identified applying stringent selection filters and Linear Discriminant Analysis (LDA) method, and validated using DNA methylation microarray data, bisulfite pyrosequencing, and direct-bisulfite sequencing. Results: Using a LDA-based approach, we developed and validated a prediction method (EpiWNT-SHH classifier) based on six epigenetic biomarkers that allowed for rapid classification of medulloblastoma into the clinically relevant subgroups WNT, SHH, and non-WNT/non-SHH with excellent concordance (>99%) with current gold-standard methods, DNA methylation microarray, and gene signature profiling analysis. The EpiWNT-SHH classifier showed high prediction capacity using both frozen and formalin-fixed material, as well as diverse DNA methylation detection methods. Similarly, we developed a classifier specific for group 3 and group 4 tumors, based on five biomarkers (EpiG3-G4) with good discriminatory capacity, allowing for correct assignment of more than 92% of tumors. EpiWNT-SHH and EpiG3-G4 methylation profiles remained stable across tumor primary, metastasis, and relapse samples. Conclusions: The EpiWNT-SHH and EpiG3-G4 classifiers represent a new simplified approach for accurate, rapid, and cost-effective molecular classification of single medulloblastoma DNA samples, using clinically applicable DNA methylation detection methods. Clin Cancer Res; 24(6); 1355–63. ©2018 AACR.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".