Methylation-Based Signatures for Gastroesophageal Tumor Classification
Bibliographic record
Abstract
Contention exists within the field of oncology with regards to gastroesophageal junction (GEJ) tumors, as in the past, they have been classified as gastric cancer, esophageal cancer, or a combination of both. Misclassifications of GEJ tumors ultimately influence treatment options, which may be rendered ineffective if treating for the wrong cancer attributes. It has been suggested that misclassification rates were as high as 45%, which is greater than reported for junctional cancer occurrences. Here, we aimed to use the methylation profiles of GEJ tumors to improve classifications of GEJ tumors. Four cohorts of DNA methylation profiles, containing ~27,000 (27k) methylation sites per sample, were collected from the Gene Expression Omnibus and The Cancer Genome Atlas. Tumor samples were assigned into discovery (nEC = 185, nGC = 395; EC, esophageal cancer; GC gastric cancer) and validation (nEC = 179, nGC = 369) sets. The optimized Multi-Survival Screening (MSS) algorithm was used to identify methylation biomarkers capable of distinguishing GEJ tumors. Three methylation signatures were identified: They were associated with protein binding, gene expression, and cellular component organization cellular processes, and achieved precision and recall rates of 94.7% and 99.2%, 97.6% and 96.8%, and 96.8% and 97.6%, respectively, in the validation dataset. Interestingly, the methylation sites of the signatures were very close (i.e., 170–270 base pairs) to their downstream transcription start sites (TSSs), suggesting that the methylations near TSSs play much more important roles in tumorigenesis. Here we presented the first set of methylation signatures with a higher predictive power for characterizing gastroesophageal tumors. Thus, they could improve the diagnosis and treatment of gastroesophageal tumors.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".