Back to all available

Elucidating the molecular contributions of DEHP as a risk factor for PCOS: an integrated approach combining machine learning, SHAP and network toxicology

bioinformatics
computational-biology
womens-health

Abstract

Background: Polycystic ovary syndrome (PCOS) is a common endocrine disorder influenced by genetic and environmental factors. Di(2-ethylhexyl) Phthalate (DEHP), a widespread endocrine disruptor, is suspected to increase PCOS risk, yet its molecular mechanisms remain unclear.

Methods: We integrated transcriptomic data from human ovarian granulosa cells across five GEO datasets. Following batch correction, differential expression analysis, and WGCNA, we identified PCOS-related genes. DEHP targets were sourced from ChEMBL, SwissTargetPrediction, CTD, and SEA. The intersection formed the DEHP-PCOS gene set, which underwent functional enrichment and immune infiltration analysis via CIBERSORT. A machine learning framework (including Lasso, Ridge, Elastic Net, SVM, and boosting) was trained on two datasets and validated on three independent sets. SHAP analysis interpreted the optimal model to identify hub genes. Molecular Docking (MD) and 100 ns Molecular Dynamics Simulations assessed DEHP-protein interactions.

Results: We identified 247 DEHP-PCOS genes significantly enriched in pathways related to secretion regulation, extracellular matrix organization, growth factor signaling, and steroid hormone metabolism. The RF model demonstrates superior predictive performance (Area Under the Curve, AUC = 0.793). SHAP analysis prioritized five hub genes: SPNS3, GBP2, MRC1, SLCO2B1, and RAB27A. These hub genes exhibited high individual predictive accuracy (AUCs: 0.823~0.883). Immune infiltration analysis revealed significant alterations in T cells, follicular helper, and Monocytes. SPNS3 expression was positively correlated with the B-cell memory infiltration. MD confirmed stable binding between DEHP and all five hub proteins, with SPNS3 showing the strongest affinity (binding energy: -7.0 kcal/mol). Molecular Dynamics Simulations further affirmed the stability of the DEHP-SPNS3 complex.

Conclusion: Our study defined a novel gene network and established a robust toxicity prediction model, which provides a computational tool for assessing PCOS risk by linking signature gene expression associated with DEHP exposure. We identify five hub genes as robust predictive biomarkers, with SPNS3 emerging as a key mediator, and we link its expression to the immune microenvironment. These findings provide mechanistic insights into how DEHP exposure may be a risk factor for PCOS.

Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.
  • PeerJ does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].