Classification of Thyroid Tumors Based on DNA Methylation Patterns
Authors' conclusion
Our data provide novel insights into the epigenetic alterations of thyroid tumors.
Study context
- Population
- Follicular cell-derived thyroid neoplasms (benign and malignant) and normal thyroid tissue256 discovery, 554 validation
- Participants
- 810 thyroid samples
- Comparison
- Normal-like vs Follicular-like vs papillary thyroid carcinoma (PTC)-like
- Outcome
- Methylation subtypes
Methodological detailsunsupervised machine learning, unsupervised machine learning class discovery, discovery and validation sets
- Unsupervised machine learning
- Unsupervised machine learning class discovery
- Discovery and validation sets
Performance
As reported in the abstract
- Subtypes associated with histological diagnosis
- p < 0.001
- BRAFV600E-driven cancers PTC-like
- 98.7%
- RAS-driven cancers follicular-like
- 96.0%
Further findings
| Outcome | Follicular-like | PTC-like | P value |
|---|---|---|---|
| FVPTC split into follicular-like and PTC-like clusters: driver alterationsFollicular-like vs PTC-like · FVPTC samples only | 36.4% | 8.0% | P < 0.001 |
| FVPTC split into follicular-like and PTC-like clusters: driver alterationsPTC-like vs Follicular-like · FVPTC samples only | 0% | 52.0% | Fisher exact p = 0.004 |
| FVPTC split into follicular-like and PTC-like clusters: driver alterationsPTC-like vs Follicular-like · FVPTC samples only | 0% | 16.0% | Fisher exact p = 0.003 |
Original publication
Classification of Thyroid Tumors Based on DNA Methylation Patterns. Thyroid. Published 10 August 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →