Rank Matrix Approach for Endometriosis: Integrating Data and Constructing Diagnostic Models

Ranze Xie, Deqing Hong, Jiaqi Yuan, Peng Xu, Wenbin Liu, Zheng Ye
In: Current Bioinformatics · 2024 · vol. 20(5) , pp. 402–412 · doi:10.2174/0115748936296151240605053713 · W4400512267
article OA: closed CC0
Full text JSON View on OpenAlex View at publisher
⚙ AI-generated summary by claude@2026-06, 2026-06-06 ⓘ

This study integrated endometriosis gene expression data using a rank matrix approach and developed an 11-gene diagnostic model that achieved robust performance in predicting the condition.

One-sentence paraphrase of the abstract; not a substitute for reading it. No clinical advice. How this works

⚙ AI-generated deep summary by claude@2026-07, 2026-07-08 · read from full text ⓘ

This paper develops a gene rank matrix-based machine learning framework to integrate endometriosis gene-expression cohorts across multiple platforms, addressing batch effects, and to build a diagnostic model. After batch effect removal, the authors identified 83 endometriosis-associated genes and then trained and validated models using 11 of these genes across four platforms, comparing algorithms including SVM, Random Forest, Logistic Regression, and gradient boosting. The gene rank matrix integration mitigated batch effects and a gradient boosting classifier achieved AUCs around 0.77 with validation performance closely matching training, with the selected 11 genes reported as associated with immunosuppression. The study’s main caveat noted is that further validation is needed to clarify the functional significance of these 11 genes. This paper is centrally about endometriosis — constructing and evaluating an integrated gene rank matrix diagnostic model for endometriosis using a subset of immunosuppression-associated genes.

Read from the paper's body, not the abstract. Not a substitute for reading the paper. No clinical advice. How this works

Abstract

Background: Endometriosis is a debilitating gynecological disorder characterized by chronic pain, infertility, and the growth of endometrial tissue outside the uterus. Accurate and early detection of this condition is crucial for effective management and treatment. Methods: We developed a gene rank matrix-based model to integrate endometriosis cohorts across multiple platforms. After removing batch effects, we identified 83 genes associated with endometriosis and further refined a diagnostic model using 11 of these genes. The model was trained on two platforms and validated on two others using SVM, Random Forest, Logistic Regression, and gradient-boosting machine learning algorithms. Results: The integration via the gene rank matrix effectively mitigated batch effects. Utilizing a gradient boosting classifier with a subset of 11 genes, the model demonstrated commendable diagnostic efficacy, achieving an Area Under the Curve (AUC) of 0.77, an accuracy of 0.72, and an F1 score of 0.72 for the training dataset. When subjected to validation, the model maintained its performance, yielding an AUC of 0.769, an accuracy of 0.719, and an F1 score of 0.732. These 11 genes were found to be associated with immunosuppression. Conclusion: Our approach to integrating gene rank matrices effectively consolidates endometriosis data across diverse platforms. The diagnostic model, harnessing the predictive power of 11 specific genes, surpasses alternative models, thereby offering promising prospects for aiding clinical diagnosis of endometriosis. Further validation is imperative to elucidate the functional significance of these 11 genes. Our study underscores the potential of data integration coupled with machine learning techniques in advancing the diagnosis of intricate diseases, such as endometriosis.
Full text 6,093 characters · extracted from oa-doi-fallback · 5 sections · click to expand

Abstract

Background: Endometriosis is a debilitating gynecological disorder characterized by chronic pain, infertility, and the growth of endometrial tissue outside the uterus. Accurate and early detection of this condition is crucial for effective management and treatment.

Methods

We developed a gene rank matrix-based model to integrate endometriosis cohorts across multiple platforms. After removing batch effects, we identified 83 genes associated with endometriosis and further refined a diagnostic model using 11 of these genes. The model was trained on two platforms and validated on two others using SVM, Random Forest, Logistic Regression, and gradient-boosting machine learning algorithms.

Results

The integration via the gene rank matrix effectively mitigated batch effects. Utilizing a gradient boosting classifier with a subset of 11 genes, the model demonstrated commendable diagnostic efficacy, achieving an Area Under the Curve (AUC) of 0.77, an accuracy of 0.72, and an F1 score of 0.72 for the training dataset. When subjected to validation, the model maintained its performance, yielding an AUC of 0.769, an accuracy of 0.719, and an F1 score of 0.732. These 11 genes were found to be associated with immunosuppression.

Conclusion

Our approach to integrating gene rank matrices effectively consolidates endometriosis data across diverse platforms. The diagnostic model, harnessing the predictive power of 11 specific genes, surpasses alternative models, thereby offering promising prospects for aiding clinical diagnosis of endometriosis. Further validation is imperative to elucidate the functional significance of these 11 genes. Our study underscores the potential of data integration coupled with machine learning techniques in advancing the diagnosis of intricate diseases, such as endometriosis.

Keywords

Endometriosis, rank matrix, remove batch effect, machine learning, genetic diagnosis, immune microenvironment. [http://dx.doi.org/10.3390/life12091321] [PMID: 36143357] [http://dx.doi.org/10.1007/978-3-030-14358-9_15] [http://dx.doi.org/10.3390/ijms221910554] [PMID: 34638893] [http://dx.doi.org/10.1016/j.ajog.2018.12.039] [http://dx.doi.org/10.3390/ijms24054254] [PMID: 36901685] [http://dx.doi.org/10.1016/j.bpobgyn.2007.10.001] [PMID: 18036995] [http://dx.doi.org/10.1196/annals.1434.007] [PMID: 18443335] [http://dx.doi.org/10.1196/annals.1290.026] [PMID: 14644830] [http://dx.doi.org/10.1097/AOG.0000000000002469] [PMID: 29420391] [http://dx.doi.org/10.3390/jcm10081616] [PMID: 33920306] [http://dx.doi.org/10.1093/biolre/ioaa011] [PMID: 31965165] [http://dx.doi.org/10.1155/2015/130854] [http://dx.doi.org/10.3389/fgene.2019.00839] [PMID: 31572446] [http://dx.doi.org/10.1093/nar/gkv007] [PMID: 25605792] [http://dx.doi.org/10.1016/S0076-6879(06)11019-8] [PMID: 16939800] [http://dx.doi.org/10.3389/fgene.2019.00766] [PMID: 31552087] [http://dx.doi.org/10.3389/fmolb.2021.743012] [PMID: 34790699] [http://dx.doi.org/10.1210/en.2014-1490] [PMID: 25243856] [http://dx.doi.org/10.1073/pnas.0703451104] [PMID: 17640886] [http://dx.doi.org/10.1186/s12958-019-0465-z] [PMID: 30760267] [http://dx.doi.org/10.1093/bioinformatics/btr671] [PMID: 22321699] [http://dx.doi.org/10.1093/bioinformatics/btaa1018] [PMID: 33315104] [http://dx.doi.org/10.1038/s41467-019-09234-6] [PMID: 30944313] [http://dx.doi.org/10.1093/nar/28.1.27] [PMID: 10592173] [http://dx.doi.org/10.1093/nar/gkg034] [PMID: 12519996] [http://dx.doi.org/10.1186/s13059-017-1349-1] [PMID: 29141660] [http://dx.doi.org/10.1007/978-1-0716-0327-7_19] [http://dx.doi.org/10.1111/cpr.13379] [PMID: 36515067] [http://dx.doi.org/10.1038/s41598-023-34384-5] [PMID: 37202447] [http://dx.doi.org/10.1023/B:AMAI.0000018580.96245.c6] [http://dx.doi.org/10.14569/IJACSA.2020.0110277] [http://dx.doi.org/10.1109/BRACIS.2013.10] [http://dx.doi.org/10.1080/01443615.2021.1882967] [PMID: 34009084] [http://dx.doi.org/10.1097/01.NME.0000554597.81822.03] [http://dx.doi.org/10.1177/1933719116654991] [PMID: 27368878] [http://dx.doi.org/10.1016/j.bpobgyn.2004.03.002] [PMID: 15157643] [http://dx.doi.org/10.3389/fgene.2022.848116] [PMID: 35350240] [PMID: 36474131] [http://dx.doi.org/10.1007/s00335-024-10039-2] [PMID: 38600211] [http://dx.doi.org/10.1016/j.gene.2021.145643] [PMID: 33848577] [http://dx.doi.org/10.1186/s12859-016-1369-y] [PMID: 28155651] [http://dx.doi.org/10.1038/s41467-022-28865-w] [PMID: 35273146] [http://dx.doi.org/10.1093/bib/bbx135] [PMID: 29040359] [http://dx.doi.org/10.1038/tpj.2010.57] [PMID: 20676067] [http://dx.doi.org/10.1038/s41421-019-0114-x] [PMID: 31636959] [http://dx.doi.org/10.1038/s41467-020-15851-3] [PMID: 32393754] [http://dx.doi.org/10.1093/bib/bbs037] [PMID: 22851511] [http://dx.doi.org/10.1038/nrg.2016.10] [PMID: 26996076] [http://dx.doi.org/10.1016/j.ebiom.2016.04.017] [PMID: 27428416] [http://dx.doi.org/10.1093/biolre/iox187] [PMID: 29325014] [http://dx.doi.org/10.1016/0167-4889(96)00097-3] [PMID: 8898862] [http://dx.doi.org/10.3389/fendo.2020.00007] [PMID: 32038499] [http://dx.doi.org/10.1042/BJ20060195] [PMID: 16683912] [http://dx.doi.org/10.3390/cells11152274] [PMID: 35892571] [http://dx.doi.org/10.1016/j.bcp.2006.05.017] [PMID: 16846592] [http://dx.doi.org/10.1161/res.131.suppl_1.P1071] [http://dx.doi.org/10.3389/fmolb.2022.837393] [PMID: 35647025] [http://dx.doi.org/10.1146/annurev.immunol.18.1.767] [PMID: 10837075] [http://dx.doi.org/10.1016/j.jri.2021.103462] [PMID: 34915278] [http://dx.doi.org/10.1111/jog.13559] [PMID: 29316073] [http://dx.doi.org/10.1093/humrep/dep071] [PMID: 19321495] [http://dx.doi.org/10.1002/advs.202206617] [PMID: 36658699] [http://dx.doi.org/10.3390/ijms221910792] [PMID: 34639133] [http://dx.doi.org/10.1111/j.1749-6632.2002.tb02779.x] [PMID: 11949947] [http://dx.doi.org/10.1016/j.celrep.2020.108325] [PMID: 33147452] [http://dx.doi.org/10.1007/s43032-020-00211-9] [PMID: 32572831] [http://dx.doi.org/10.1016/j.jri.2017.04.003] [PMID: 28463710] [http://dx.doi.org/10.1093/humrep/deq020] [PMID: 20150173] [http://dx.doi.org/10.1007/s00404-023-06964-3] [PMID: 36840769] [http://dx.doi.org/10.1016/j.jmig.2024.02.004]

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

⚙ Ask this paper AI returns verbatim quotes from the full text · source: oa-doi-fallback ⓘ

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Condition tags

endometriosisinfertility

Citation neighborhood

Papers in the corpus that this work cites (lower rings, blue) and that cite this one (upper rings, green). Dot size scales with the paper's in-corpus citation count — bigger dot = more influential within the endo/adeno field. Click a dot to open that paper. [ expand to 2 hops ] — adds papers reached through this work's immediate citers/citees. Heavier; up to 60 extra dots.

References (72)

Source provenance

openalex
last seen: 2026-06-04T00:00:01.174412+00:00
unpaywall
last seen: 2026-06-13T06:42:57.164913+00:00
License: CC0 · commercial use OK