Predicting Endometriosis Status and Menstrual Cycle Phase Using DNA Methylation
- 1Bakar Computational Health Sciences Institute, University of California, San Francisco, CA, USA; Department of Pediatrics, University of California, San Francis
Abstract
Endometriosis is a chronic inflammatory disease associated with pelvic pain, infertility, and delayed diagnosis. Growing evidence suggests that altered DNA methylation contributes to disease development and could serve as a biomarker for disease. We developed a leakage-safe machine learning pipeline to classify endometriosis case-control status and menstrual cycle phase using genome-wide DNA methylation data from eutopic endometrial tissue. The dataset consisted of 984 samples profiled using the Illumina Infinium MethylationEPIC array, with measurements across approximately 759,000 CpG sites. Technical variation was corrected using SmartSVA batch correction. Ridge logistic regression models were trained using stratified 80/20 train-test splits, with regularization strength selected via stratified cross-validation. Feature selection approaches included ridge coefficient ranking, per-CpG t-tests, and univariate logistic regression with FDR correction. Model validity was evaluated using label-shuffling analyses. Menstrual cycle phase classification showed strong performance (mean cross-validation AUROC: 0.971, held-out test AUROC: 0.989), reflecting genome-wide hormonally driven methylation. Ridge regression produced lower but meaningful performance for endometriosis classification (mean cross-validation AUROC: 0.854, held-out test AUROC: 0.875). Ridge coefficient-based feature selection identified compact predictive CpG sets, supporting the hypothesis that endometriosis-associated methylation signal is distributed across many loci rather than a few highly predictive CpGs. Pathway enrichment analyses identified substantial enrichment for menstrual cycle phase but limited enrichment for disease status following FDR correction, consistent with a diffuse endometriosis-associated signal. These findings demonstrate that ridge regression can detect methylation patterns associated with both endometriosis and menstrual cycle phase, highlighting the importance of accounting for cycle-related epigenetic variation in endometrial DNA methylation studies.
Related
- Menstrual cycle and hormonal contraceptive intake alter the electrophysiological signature of selective auditory spatial attention
- Feasibility of an anterior abdominal electrode array for non-invasive measurement of uterine contractions across the menstrual cycle
- Dynamic Changes in Endometrial Folding and Secretory Activity Across the Menstrual Cycle
- Menstrual cycle phase and premenstrual symptoms in relation with the stress response: an fMRI study
- The Role of Menstrual Cycle Phase in PTSD: A Scoping Review of Symptom Expression, Neuropsychology and Psychotherapy Response in Women
BibTeX
@misc{nagasuri2026predicting,
title = {{Predicting Endometriosis Status and Menstrual Cycle Phase Using DNA Methylation}},
author = {A. Nagasuri and U. Khan and P. Grosjean and A. Siddharth and I. Kosti and S. Mortlock and S. Houshdaran and N. Rahmioglu and S. A. Missmer and K. T. Zondervan and G. Montgomery and C. M. Becker and P. Rogers and J. Irwin and T. Oskotsky and K. Lindquist and C. Seaman and L. C. Giudice and M. Sirota},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.02.749016},
url = {https://www.biorxiv.org/content/10.64898/2026.09.02.749016v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Predicting Endometriosis Status and Menstrual Cycle Phase Using DNA Methylation
AU - A. Nagasuri
AU - U. Khan
AU - P. Grosjean
AU - A. Siddharth
AU - I. Kosti
AU - S. Mortlock
AU - S. Houshdaran
AU - N. Rahmioglu
AU - S. A. Missmer
AU - K. T. Zondervan
AU - G. Montgomery
AU - C. M. Becker
AU - P. Rogers
AU - J. Irwin
AU - T. Oskotsky
AU - K. Lindquist
AU - C. Seaman
AU - L. C. Giudice
AU - M. Sirota
PY - 2026
DA - 2026/09/02
PB - bioRxiv
DO - 10.64898/2026.09.02.749016
UR - https://www.biorxiv.org/content/10.64898/2026.09.02.749016v1
AB - Endometriosis is a chronic inflammatory disease associated with pelvic pain, infertility, and delayed diagnosis. Growing evidence suggests that altered DNA methylation contributes to disease development and could serve as a biomarker for disease. We developed a leakage-safe machine learning pipeline to classify endometriosis case-control status and menstrual cycle phase using genome-wide DNA methylation data from eutopic endometrial tissue. The dataset consisted of 984 samples profiled using the Illumina Infinium MethylationEPIC array, with measurements across approximately 759,000 CpG sites. Technical variation was corrected using SmartSVA batch correction. Ridge logistic regression models were trained using stratified 80/20 train-test splits, with regularization strength selected via stratified cross-validation. Feature selection approaches included ridge coefficient ranking, per-CpG t-tests, and univariate logistic regression with FDR correction. Model validity was evaluated using label-shuffling analyses. Menstrual cycle phase classification showed strong performance (mean cross-validation AUROC: 0.971, held-out test AUROC: 0.989), reflecting genome-wide hormonally driven methylation. Ridge regression produced lower but meaningful performance for endometriosis classification (mean cross-validation AUROC: 0.854, held-out test AUROC: 0.875). Ridge coefficient-based feature selection identified compact predictive CpG sets, supporting the hypothesis that endometriosis-associated methylation signal is distributed across many loci rather than a few highly predictive CpGs. Pathway enrichment analyses identified substantial enrichment for menstrual cycle phase but limited enrichment for disease status following FDR correction, consistent with a diffuse endometriosis-associated signal. These findings demonstrate that ridge regression can detect methylation patterns associated with both endometriosis and menstrual cycle phase, highlighting the importance of accounting for cycle-related epigenetic variation in endometrial DNA methylation studies.
ER -