Test performance of a DNA methylation–based liquid biopsy biomarker for detection and classification of pleural mesothelioma (PM).
Bibliographic record
Abstract
8082 Background: Circulating tumor DNA (ctDNA) profiling in pleural mesothelioma (PM) is challenging due to its molecular heterogeneity and lack of mesothelioma-specific mutations. Diagnosis can be challenging and may require repeat biopsies. Cell-free methylated DNA immunoprecipitation sequencing (cfMeDIP-seq) of plasma cell-free DNA (cfDNA) offers a non-invasive approach to analyzing differentially methylated regions (DMRs), providing insights into epigenetic changes that could serve as potential biomarkers for diagnosis, histological differentiation, and prognosis in PM. Methods: cfMeDIP-seq was performed on plasma samples from 55 PM patients and 24 asbestos-exposed non-cancer controls (NCC). Libraries were sequenced to an average depth of 70 million reads, and chromosomes 1-22 were binned into 300 bp windows for read tallying. For NCCs, bins with a mean beta-value <0.3 and CG density >2 (n = 3,537,691 windows) were analyzed. DMR analysis and pathway enrichment were conducted using R packages (limma, clusterProfiler), and machine learning models were developed with Python modules (pandas, numpy, sklearn). Results: Among the 55 PM patients (72% epithelioid, 13% biphasic, 15% sarcomatoid), the median age was 70 years, 85% were male, and 78% had prior asbestos exposure. Using a stringent filter (mean beta-value <0.1; CG density >5), a random forest classifier was developed with 141 windows, distinguishing PM from NCC with 91% accuracy, 88% precision (or positive predictive value, PPV), and an area under the ROC curve (AUC) of 0.94 across 5-fold cross-validation cohorts. DMR analysis of epithelioid vs. sarcomatoid PM revealed 1,585 significantly different windows (adjusted p < 0.05), achieving 83% accuracy, 74% precision, and an AUC of 0.98. Gene ontology analysis indicated significant enrichment in RNA processing pathways. Among epithelioid PM patients, distinct DMRs were identified between those with overall survival (OS) ≤ 6 months and >6 months (n = 1,824 windows, adjusted p < 0.05). Patients with OS ≥ 36 months and <36 months showed 37 significantly differential windows (adjusted p < 0.05), though test performance assessment was limited by the small sample size. Conclusions: If validated, global methylome profiling of ctDNA via cfMeDIP-seq offers a novel, non-invasive method that may enhance accurate diagnosis and histological differentiation. Additionally, identifying epigenetic biomarkers could provide deeper insights into PM biology, paving the way for personalized medicine and improved patient outcomes.
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 | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".