What question did this study set out to answer?

To develop a machine-learning model based on DNA methylation patterns in cervical scraping samples collected via routine Pap smear to noninvasively detect and classify ovarian cancer.

May 17, 2025Human GenomicsOpen Access

Exploring potential methylation markers for ovarian cancer from cervical scraping samples

View Full Paper

Ask AI

Bookmark

To develop a machine-learning model based on DNA methylation patterns in cervical scraping samples collected via routine Pap smear to noninvasively detect and classify ovarian cancer.
Collected 160 cervical scraping samples using conventional Pap smears (N=95 normal, N=37 benign, and N=28 malignant) and profiled ~850,000 CpG loci using the Illumina Infinium MethylationEPIC BeadChip.
Split data into training (N=120) and testing (N=40) sets to construct a two-step classifier: a 30-feature principal component analysis model to separate normal from tumor samples, followed by a 16-feature gradient boosting model to distinguish benign from malignant tumors.
The two-step methylation model achieved an overall accuracy of 0.88 and an F1-score of 0.86 on the independent testing set (N=40).
Differentially methylated positions associated with genes involved in olfactory transduction pathways when comparing normal to tumor samples, and immune regulation pathways when differentiating benign from malignant lesions.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Diagnostic study demonstrates high accuracy of a two-step DNA methylation model in cervical scraping samples, highlighting Pap smears as a viable screening tool for ovarian cancer.

Cite This Study

Lien et al. (2025) studied this question.

synapsesocial.com/papers/6a9ea02ef3ab6580739bdba4 https://doi.org/10.1186/s40246-025-00763-4

View Full Paper

Ask AI

Bookmark

Implication

Diagnostic study demonstrates high accuracy of a two-step DNA methylation model in cervical scraping samples, highlighting Pap smears as a viable screening tool for ovarian cancer.

Exploring potential methylation markers for ovarian cancer from cervical scraping samples

Key Points

Discussion

Implication

Cite This Study

Exploring potential methylation markers for ovarian cancer from cervical scraping samples

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider