Machine Learning-Based Diagnosis of Adenomyosis Uteri Using Serum and Urine miRNA Profiles
Ontology highlight
ABSTRACT:
ORGANISM(S): Homo sapiens
PROVIDER: GSE298298 | GEO | 2026/05/27
REPOSITORIES: GEO
Similar Datasets
Project description:Adenomyosis, defined as ectopic endometrial tissue within the myometrium, can often be misdiagnosed as multiple uterine leiomyomata or endometrial thickening. We therefore performed a combined mRNA and long noncoding (lnc)RNA microarray and bioinformatic analysis of eutopic and ectopic endometrium in women with adenomyosis to better understand its pathogenesis and help in the development of a semi-invasive diagnostic test. A total of 586 mRNAs were increased and 305 mRNAs decreased in ectopic endometrium of adenomyosis compared with eutopic endometrium, while 388 lncRNA transcripts were up-regulated and 188 down-regulated in ectopic compared with paired eutopic endometrial tissue. Bioinformatic analysis suggested a series of metabolic and molecular abnormalities in adenomyosis, which have many similarities with endometriosis. Furthermore, our study constitutes the first known report of lncRNA expression patterns in human adenomyosis ectopic and eutopic endometrial tissue. Two-condition experiment, ectopic endometrium vs. eutopic endometrium. 3 samples,self-control
2015-10-28 | E-GEOD-74373 | biostudies-arrayexpress
Project description:We experimented how well various supervised machine learning methods such as decision tree, partial least squares discriminant analysis (PLSDA), support vector machine and random forest perform in classifying endometriosis from the control samples trained on both transcriptomics and methylomics data. The assessment was done from two different perspectives for improving classification performances: (a) implication of three different normalization techniques, and (b) implication of differential analysis using the generalized linear model (GLM). We concluded that an appropriate machine learning diagnostic pipeline for endometriosis should use TMM normalization for transcriptomics data, and quantile or voom normalization for methylomics data, GLM for feature space reduction and classification performance maximization.
2019-07-18 | GSE134056 | GEO
Project description:We experimented how well various supervised machine learning methods such as decision tree, partial least squares discriminant analysis (PLSDA), support vector machine and random forest perform in classifying endometriosis from the control samples trained on both transcriptomics and methylomics data. The assessment was done from two different perspectives for improving classification performances: (a) implication of three different normalization techniques, and (b) implication of differential analysis using the generalized linear model (GLM). We concluded that an appropriate machine learning diagnostic pipeline for endometriosis should use TMM normalization for transcriptomics data, and quantile or voom normalization for methylomics data, GLM for feature space reduction and classification performance maximization.
2019-07-18 | GSE134052 | GEO
Project description:Adenomyosis, defined as ectopic endometrial tissue within the myometrium, can often be misdiagnosed as multiple uterine leiomyomata or endometrial thickening. We therefore performed a combined mRNA and long noncoding (lnc)RNA microarray and bioinformatic analysis of eutopic and ectopic endometrium in women with adenomyosis to better understand its pathogenesis and help in the development of a semi-invasive diagnostic test. A total of 586 mRNAs were increased and 305 mRNAs decreased in ectopic endometrium of adenomyosis compared with eutopic endometrium, while 388 lncRNA transcripts were up-regulated and 188 down-regulated in ectopic compared with paired eutopic endometrial tissue. Bioinformatic analysis suggested a series of metabolic and molecular abnormalities in adenomyosis, which have many similarities with endometriosis. Furthermore, our study constitutes the first known report of lncRNA expression patterns in human adenomyosis ectopic and eutopic endometrial tissue.
2015-10-28 | GSE74373 | GEO
Project description:Abstract: Objective: Adenomyosis is a clinical disorder defined by the presence of endometrial glands and stroma within the myometrium, the pathogenesis of which is poorly understood. We postulate that dysregulation of genes and pathways in eutopic endometrium may predispose to ectopic implantation. No study, to our knowledge, has examined the global transcriptome of isolated eutopic endometrium from women with clinically significant adenomyosis. Design: Laboratory-based study with full IRB approval and consents. Material and Methods: Endometrial sampling was performed on hysterectomy specimens (proliferative phase) from symptomatic women with pathologically-confirmed diffuse adenomyosis (n=3). Controls (n=5) were normo-ovulatory subjects without adenomyosis. All subjects were free from leiomyoma, endometriosis, and hormonal exposures. Isolated purified total RNA was subjected to microarray analysis using the Gene 1.0 ST Affymetrix platform. Data were analyzed with GeneSpring and Ingenuity Pathway analysis. Validation of several genes was undertaken by QRT-PCR. Results: Comparison of transcriptomes of proliferative endometrium from women with and without adenomyosis revealed 140 up-regulated and 884 down-regulated genes in samples from women with adenomyosis compared to controls. Highly differentially expressed genes include those involved in regulation of apoptopsis, steroid hormone responsiveness, and proteins involved in extracellular matrix remodeling, as well as microRNAs of unknown significance. Affected canonical pathways included eukaryotic initiation factor 2 signaling, oxidative phosphorylation, mitochondrial dysfunction, estrogen receptor signaling, and mTOR signaling. Conclusions: The eutopic endometrium in patients with adenomyosis has fundamental abnormalities that may predispose to invasion and survival beyond the myometrial interface. Key Words: adenomyosis, endometrium, microarray, microRNA, endometriosis, apoptosis, signaling. Abstract: Objective: Adenomyosis is a clinical disorder defined by the presence of endometrial glands and stroma within the myometrium, the pathogenesis of which is poorly understood. We postulate that dysregulation of genes and pathways in eutopic endometrium may predispose to ectopic implantation. No study, to our knowledge, has examined the global transcriptome of isolated eutopic endometrium from women with clinically significant adenomyosis. Design: Laboratory-based study with full IRB approval and consents. Material and Methods: Endometrial sampling was performed on hysterectomy specimens (proliferative phase) from symptomatic women with pathologically-confirmed diffuse adenomyosis (n=3). Controls (n=5) were normo-ovulatory subjects without adenomyosis. All subjects were free from leiomyoma, endometriosis, and hormonal exposures. Isolated purified total RNA was subjected to microarray analysis using the Gene 1.0 ST Affymetrix platform. Data were analyzed with GeneSpring and Ingenuity Pathway analysis. Validation of several genes was undertaken by QRT-PCR. Results: Comparison of transcriptomes of proliferative endometrium from women with and without adenomyosis revealed 140 up-regulated and 884 down-regulated genes in samples from women with adenomyosis compared to controls. Highly differentially expressed genes include those involved in regulation of apoptopsis, steroid hormone responsiveness, and proteins involved in extracellular matrix remodeling, as well as microRNAs of unknown significance. Affected canonical pathways included eukaryotic initiation factor 2 signaling, oxidative phosphorylation, mitochondrial dysfunction, estrogen receptor signaling, and mTOR signaling. Conclusions: The eutopic endometrium in patients with adenomyosis has fundamental abnormalities that may predispose to invasion and survival beyond the myometrial interface. Key Words: adenomyosis, endometrium, microarray, microRNA, endometriosis, apoptosis, signaling. A total of 8 samples were used and analyzed by disease state. Endometrial samples from hysterectomy specimens in proliferative phase of menstrual cycle from symptomatic women with pathologically-confirmed diffuse adenomyosis were compared with endometrial samples from normo-ovulatory healthy subjects with no endometrial or uterine pathology.
2016-03-03 | E-GEOD-78851 | biostudies-arrayexpress
Project description:Objective: To identify differentially expressed long noncoding RNA in the eutopic endometrium tissue of adenomyosis on a genome-wide scale. Patient(s): Seventeen women with adenomyosis and fifteen patients without adenomyosis or endometriosis receiving surgical treatment. Intervention(s): Total RNAs containing long nocoding RNAs was extracted from endometrial tissue obtained during surgery. Main Outcome Measure(s): Differentially expressed lncRNAs and mRNAs were detected by human lncRNA microarray. Result(s): We identified 165 lncRNAs and 612 mRNAs abnormally expressed (P<0.05) in the eutopic endometrium of adenomyosis. Conclusion(s): This study showed for the first time that the lncRNA expression profile was altered in women with adenomyosis.
2016-05-01 | GSE68870 | GEO
Project description:Abstract: Objective: Adenomyosis is a clinical disorder defined by the presence of endometrial glands and stroma within the myometrium, the pathogenesis of which is poorly understood. We postulate that dysregulation of genes and pathways in eutopic endometrium may predispose to ectopic implantation. No study, to our knowledge, has examined the global transcriptome of isolated eutopic endometrium from women with clinically significant adenomyosis. Design: Laboratory-based study with full IRB approval and consents. Material and Methods: Endometrial sampling was performed on hysterectomy specimens (proliferative phase) from symptomatic women with pathologically-confirmed diffuse adenomyosis (n=3). Controls (n=5) were normo-ovulatory subjects without adenomyosis. All subjects were free from leiomyoma, endometriosis, and hormonal exposures. Isolated purified total RNA was subjected to microarray analysis using the Gene 1.0 ST Affymetrix platform. Data were analyzed with GeneSpring and Ingenuity Pathway analysis. Validation of several genes was undertaken by QRT-PCR. Results: Comparison of transcriptomes of proliferative endometrium from women with and without adenomyosis revealed 140 up-regulated and 884 down-regulated genes in samples from women with adenomyosis compared to controls. Highly differentially expressed genes include those involved in regulation of apoptopsis, steroid hormone responsiveness, and proteins involved in extracellular matrix remodeling, as well as microRNAs of unknown significance. Affected canonical pathways included eukaryotic initiation factor 2 signaling, oxidative phosphorylation, mitochondrial dysfunction, estrogen receptor signaling, and mTOR signaling. Conclusions: The eutopic endometrium in patients with adenomyosis has fundamental abnormalities that may predispose to invasion and survival beyond the myometrial interface. Key Words: adenomyosis, endometrium, microarray, microRNA, endometriosis, apoptosis, signaling. Abstract: Objective: Adenomyosis is a clinical disorder defined by the presence of endometrial glands and stroma within the myometrium, the pathogenesis of which is poorly understood. We postulate that dysregulation of genes and pathways in eutopic endometrium may predispose to ectopic implantation. No study, to our knowledge, has examined the global transcriptome of isolated eutopic endometrium from women with clinically significant adenomyosis. Design: Laboratory-based study with full IRB approval and consents. Material and Methods: Endometrial sampling was performed on hysterectomy specimens (proliferative phase) from symptomatic women with pathologically-confirmed diffuse adenomyosis (n=3). Controls (n=5) were normo-ovulatory subjects without adenomyosis. All subjects were free from leiomyoma, endometriosis, and hormonal exposures. Isolated purified total RNA was subjected to microarray analysis using the Gene 1.0 ST Affymetrix platform. Data were analyzed with GeneSpring and Ingenuity Pathway analysis. Validation of several genes was undertaken by QRT-PCR. Results: Comparison of transcriptomes of proliferative endometrium from women with and without adenomyosis revealed 140 up-regulated and 884 down-regulated genes in samples from women with adenomyosis compared to controls. Highly differentially expressed genes include those involved in regulation of apoptopsis, steroid hormone responsiveness, and proteins involved in extracellular matrix remodeling, as well as microRNAs of unknown significance. Affected canonical pathways included eukaryotic initiation factor 2 signaling, oxidative phosphorylation, mitochondrial dysfunction, estrogen receptor signaling, and mTOR signaling. Conclusions: The eutopic endometrium in patients with adenomyosis has fundamental abnormalities that may predispose to invasion and survival beyond the myometrial interface. Key Words: adenomyosis, endometrium, microarray, microRNA, endometriosis, apoptosis, signaling.
2016-03-03 | GSE78851 | GEO
Project description:A discovery study using RNA-HighSeq from 37 endometrial biopsies was performed to build classifiers that differentiate between control patients and adenomyosis, ovarian endometriosis and deep infiltrating endometriosis. Total RNA was extracted from endometrial biopsies. We found an AUC of 0.97 where the classifier differentiated almost perfectly all three diseases together from the control group when including 11 phenotypic variables of the patients in the classifier.
2024-01-31 | GSE193928 | GEO
Project description:Background: The therapeutic regimen of immune-mediated necrotizing myopathy (IMNM), a category of immune-related myopathies featuring progressive proximal muscle weakness and extremely high level of serum creatine kinase, remains a formidable barrier for clinicians. The proposed study intended to investigate new diagnostic biomarkers based on high-throughput sequencing data of IMNM and generate novel IMNM management strategies by bioinformatics technology. Methods: Eighteen IMNM patients were synthesized in a local sequencing cohort (high-throughput sequencing data) with Weighted Gene Co-expression Network Analysis (WGCNA) and differential expression analysis to pinpoint robust IMNM-related differentially expressed genes (DEGs). The definitive feature genes were categorized by employing the protein-protein interaction (PPI) network, Least Absolute Shrinkage Selection Operator (LASSO), and support vector machine recursive feature elimination (SVM-RFE), and their sample discriminatory utility was appraised by obtaining the area under the curve (AUC) of the receiver operating curve (ROC) curve. The expression difference of key genes was verified by quantitative real-time polymerase chain reaction (qRT-PCR). Enrichment analysis of predefined gene sets disclosed the hidden functions of diagnostic DEGs. The 28 immune cell abundance patterns in the IMNM cohort were measured using single-sample gene set enrichment analysis (ssGSEA). Results: We recognized 193 genes that were aberrantly upregulated in the IMNM population and were firmly affiliated with immune-inflammatory responses, regulation of skeletal and cardiac muscle contraction and lipidprotein metabolism. LTK, MYBPH, and MYL4 were authenticated as diagnostic markers for IMNM (all AUC = 1.00), and functional enrichment analysis highlighted that these genes were notably integrated with immune-inflammatory response, autophagy-lysosome pathway and myofiber differentiation and regeneration. Ultimately, ssGSEA revealed a pronounced immune cell infiltrative microenvironment in the IMNM population. The results revealed the most significant relationship among CD4 T cells, CD8 T cells, macrophages, natural killer cells, T helper cells, Th17 cells and dendritic cells. Conclusion: LTK, MYBPH, and MYL4 might be served as diagnostic molecules for IMNM and possibly yield innovative insights into the mechanisms of progression and therapeutic options for IMNM in the future.
2024-09-30 | GSE213055 | GEO
Project description:CIRCULATING SERUM MICRO-RNA AS NON-INVASIVE DIAGNOSTIC BIOMARKERS OF ENDOMETRIOSIS
| PRJNA1172704 | ENA