Methylomic classifiers of anal cancer outcomes: An NRG Oncology / RTOG 98-11 tissue study.
Bibliographic record
Abstract
588 Background: Genome-wide epigenetic events appear to play a role in the development and behavior of HPV+ cancers. The value of adjuvant therapy following chemoradiation for localized anal cancer (AC) remains unclear. Molecular prognostication to identify patients (pts) who may be at higher risk for recurrence would be valuable. The goal was to define methylomic profiles predictive of disease-free (DFS) and overall (OS) survival in pts with AC. Methods: Genomic DNA was extracted, processed and methylation status at ~450,000 CpG loci examined (Illumina HumanMethylation450 Array). A multistep bioinformatics methodology was applied to develop a prognostic methylomic classifier for OS and DFS: (1) feature selection for methylated regions (β-value interquartile range ≥ 0.2, ≥ 2 adjacent significant probes within a CpG Island and p < 0.05 by univariate Cox proportional hazards) (2) selected features were entered into a supervised principal component analysis (PCA) and 3 components (PC1, PC2, PC3) were derived (3) classifier was built using forward selection multivariate regression models [PC1, PC2, PC3 alone and in combination with clinical features (size: > T2 vs. ≤ T2, nodal status: N0 vs N+)] using a 10-fold cross-validation (4) final model prediction risk score was generated, dichotomized and evaluated for prognostic values in Cox regression analysis. Results: 121 AC specimens from RTOG 98-11 were examined. The methylomic-only classifier model trended towards statistical significance (log-rank p = 0.05; HR = 1.96; 95% CI 0.99-3.88) in DFS (PC1, PC3 selected). In the combined model with clinical features, the final classifier included T status and epigenetic features (PC1, PC3) and was strongly predictive for DFS (p < 0.0001, HR = 4.45; 2.02-9.76). Final OS classifier models [methylomic-only (p = 0.28 HR = 1.55; 0.70-3.44) or combined (p = 0.013 HR = 2.88; 1.20-6.89)] were not as accurate. Conclusions: Methylomic and clinical features synergize to predict DFS in AC. Multivariate modeling reveal independent contributions from clinical and methylomic variables. Epigenomic profiling may contribute to identification of high-risk pts who may benefit from adjuvant strategies. Support: U10CA180822, U10CA180868, U24CA196067
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.003 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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 teacher head, 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".