The epiMelanoma test enables plasma-based detection of melanoma and prediction of immunotherapy response
Bibliographic record
Abstract
BACKGROUND: Melanoma is one of the most serious skin cancers worldwide, often progressing without obvious symptoms. Early detection is crucial to enable timely intervention, reducing morbidity and mortality. However, no standardized high-throughput test exists for non-invasive melanoma detection. METHODS: This diagnostic study aimed to develop and validate a high-throughput targeted DNA methylation-based test for detecting melanoma in cell-free DNA (cfDNA) from plasma and predicting response to immune checkpoint inhibitors (ICIs). A multiplexed next-generation sequencing assay targeting these five melanoma-specific DNA regions, named epiMelanoma, was developed and tested on a clinical cohort of 199 participants, including 121 melanoma patients (stages I-IV) from oncology clinics and 78 healthy donors sourced from biorepositories. Plasma cfDNA was collected from 187 participants, and biopsies from 35 patients. RESULTS: Here we show that epiMelanoma shows high classification accuracy in both biopsies and plasma cfDNA. First, four DNA regions categorically methylated across diverse cancers, including melanoma, but unmethylated in other tissues, were identified using TCGA and GEO datasets (n = 160), showing high classification accuracy (AUC = 0.9987, sensitivity 98.67%, specificity 100%). A fifth melanoma-specific region was discovered (cg04652957, sensitivity 100%, specificity 90.91%) and validated in 5479 samples. In clinical samples, sensitivity for early- and late-stage melanoma was 27% and 60%, respectively, with high specificity (98.15%). Sensitivity in biopsies exceeded 90%. Furthermore, a significant correlation was observed between the methylation signature and response to ICIs (p = 0.012), with lower M-scores associated with improved overall survival (log-rank p = 0.001, Kaplan-Meier). CONCLUSIONS: The epiMelanoma assay represents a promising non-invasive tool for early melanoma detection and personalized treatment, by enabling timely intervention and identifying patients most likely to benefit from immunotherapy, and therefore, potentially improving patient outcomes and reducing healthcare burdens.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| 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".