Dysregulated immunological and metabolic functions discovered by a polygenic integrative analysis for PCOS

Identification and validation of senescence-related genes in polycystic ovary syndrome

BACKGROUND

Polycystic ovary syndrome (PCOS) is an exceedingly intractable issue affecting female endocrine and reproductive health. However, the etiology and intricate pathological mechanisms of PCOS remain unclear. Nowadays, aging was found to share multiple common pathological mechanisms with PCOS, which causes probing into the pathogenesis of PCOS from senescence. However, no bioinformatics analyses have specifically focused on connection between PCOS and ovarian aging.

METHODS

Differentially expressed aging-related genes in PCOS were identified and then analyzed using function enrichment method. Hub genes were determined based on multiple algorithms, and expression validation of hub genes was performed in both datasets and experiments (human granulosa-like tumor cell line, KGN; human Granulosa Cell, hGCs). Finally, a transcription factor-miRNA-gene network of hub genes was constructed.

RESULTS

Here, we identified 73 aging-related differential expression genes (ARDEGs) by intersecting DEGs in PCOS and senescence-related gene set. Furthermore, we performed biological functions and potential pathways of ARDEGs and potential hub genes were also screened by multiple algorithms. From the perspective of immune dysfunction, we analyzed the correlation between PCOS and immune cells. Finally, TF-miRNA-gene networks were constructed. Finally, TF-miRNA-gene networks were constructed.

CONCLUSIONS

Our work aimed to elucidate the relation between PCOS and cellular senescence based on bioinformatics strategy, deepening the understanding of mechanisms and to seek for novel therapy strategies for improving reproductive lifespan and female health. Exploring the potential molecular mechanism of cell aging in PCOS is expected to bring a new breakthrough for PCOS diagnosis and therapy strategies. And this, might deepen our understanding about intricate mechanisms of ovarian aging.

Establishment and Analysis of an Artificial Neural Network Model for Early Detection of Polycystic Ovary Syndrome Using Machine Learning Techniques

Background

To identify novel gene combinations and to develop an early diagnostic model for Polycystic Ovary Syndrome (PCOS) through the integration of artificial neural networks (ANN) and random forest (RF) methods.

Methods

We retrieved and processed gene expression datasets for PCOS from the Gene Expression Omnibus (GEO) database. Differential expression analysis of genes (DEGs) within the training set was performed using the "limma" R package. Enrichment analyses on DEGs using gene ontology (GO) and the Kyoto Encyclopedia of Genes and Genomes (KEGG), and immune cell infiltration. The identification of critical genes from DEGs was then performed using random forests, followed by the developing of new diagnostic models for PCOS using artificial neural networks.

Results

We identified 130 up-regulated genes and 132 down-regulated genes in PCOS compared to normal samples. Gene Ontology analysis revealed significant enrichment in myofibrils and highlighted crucial biological functions related to myofilament sliding, myofibril, and actin-binding. Compared with normal tissues, the types of immune cells expressed in PCOS samples are different. A random forest algorithm identified 10 significant genes proposed as potential PCOS-specific biomarkers. Using these genes, an artificial neural network diagnostic model accurately distinguished PCOS from normal samples. The diagnostic model underwent validation using the independent validation set, and the resulting area under the receiver operating characteristic curve (AUC) values was consistent with the anticipated outcomes.

Conclusion

Utilizing unique gene combinations, this research created a diagnostic model by merging random forest techniques with artificial neural networks. The AUC indicated a notably superior performance of the diagnostic model.

Machine learning classification of polycystic ovary syndrome based on radial pulse wave analysis

BACKGROUND

Patients with Polycystic ovary syndrome (PCOS) experienced endocrine disorders that may present vascular function changes. This study aimed to classify and predict PCOS by radial pulse wave parameters using machine learning (ML) methods and to provide evidence for objectifying pulse diagnosis in traditional Chinese medicine (TCM).

METHODS

A case-control study with 459 subjects divided into a PCOS group and a healthy (non-PCOS) group. The pulse wave parameters were measured and analyzed between the two groups. Seven supervised ML classification models were applied, including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Trees, Random Forest, Logistic Regression, Voting, and Long Short Term Memory networks (LSTM). Parameters that were significantly different were selected as input features and stratified k-fold cross-validations training was applied to the models.

RESULTS

There were 316 subjects in the PCOS group and 143 subjects in the healthy group. Compared to the healthy group, the pulse wave parameters h3/h1 and w/t from both left and right sides were increased while h4, t4, t, As, h4/h1 from both sides and right t1 were decreased in the PCOS group (P < 0.01). Among the ML models evaluated, both the Voting and LSTM with ensemble learning capabilities, demonstrated competitive performance. These models achieved the highest results across all evaluation metrics. Specifically, they both attained a testing accuracy of 72.174% and an F1 score of 0.818, their respective AUC values were 0.715 for the Voting and 0.722 for the LSTM.

CONCLUSION

Radial pulse wave signal could identify most PCOS patients accurately (with a good F1 score) and is valuable for early detection and monitoring of PCOS with acceptable overall accuracy. This technique can stimulate the development of individualized PCOS risk assessment using mobile detection technology, furthermore, gives physicians an intuitive understanding of the objective pulse diagnosis of TCM.

TRIAL REGISTRATION

Not applicable.

Signaling pathways and targeted therapeutic strategies for polycystic ovary syndrome

Polycystic ovary syndrome (PCOS) is the most common endocrine disorder among women of reproductive age. Although promising strides have been made in the field of PCOS over the past decades, the distinct etiologies of this syndrome are not fully elucidated. Prenatal factors, genetic variation, epigenetic mechanisms, unhealthy lifestyles, and environmental toxins all contribute to the development of this intricate and highly heterogeneous metabolic, endocrine, reproductive, and psychological disorder. Moreover, interactions between androgen excess, insulin resistance, disruption to the hypothalamic-pituitary-ovary (HPO) axis, and obesity only make for a more complex picture. In this review, we investigate and summarize the related molecular mechanisms underlying PCOS pathogenesis from the perspective of the level of signaling pathways, including PI3K/Akt, TGF-β/Smads, Wnt/β-catenin, and Hippo/YAP. Additionally, this review provides an overview of prospective therapies, such as exosome therapy, gene therapy, and drugs based on traditional Chinese medicine (TCM) and natural compounds. By targeting these aberrant pathways, these interventions primarily alleviate inflammation, insulin resistance, androgen excess, and ovarian fibrosis, which are typical symptoms of PCOS. Overall, we hope that this paper will pave the way for better understanding and management of PCOS in the future.

Application of machine learning and artificial intelligence in the diagnosis and classification of polycystic ovarian syndrome: a systematic review

Introduction

Polycystic Ovarian Syndrome (PCOS) is the most common endocrinopathy in women of reproductive age and remains widely underdiagnosed leading to significant morbidity. Artificial intelligence (AI) and machine learning (ML) hold promise in improving diagnostics. Thus, we performed a systematic review of literature to identify the utility of AI/ML in the diagnosis or classification of PCOS.

Methods

We applied a search strategy using the following databases MEDLINE, Embase, the Cochrane Central Register of Controlled Trials, the Web of Science, and the IEEE Xplore Digital Library using relevant keywords. Eligible studies were identified, and results were extracted for their synthesis from inception until January 1, 2022.

Results

135 studies were screened and ultimately, 31 studies were included in this study. Data sources used by the AI/ML interventions included clinical data, electronic health records, and genetic and proteomic data. Ten studies (32%) employed standardized criteria (NIH, Rotterdam, or Revised International PCOS classification), while 17 (55%) used clinical information with/without imaging. The most common AI techniques employed were support vector machine (42% studies), K-nearest neighbor (26%), and regression models (23%) were the commonest AI/ML. Receiver operating curves (ROC) were employed to compare AI/ML with clinical diagnosis. Area under the ROC ranged from 73% to 100% (n=7 studies), diagnostic accuracy from 89% to 100% (n=4 studies), sensitivity from 41% to 100% (n=10 studies), specificity from 75% to 100% (n=10 studies), positive predictive value (PPV) from 68% to 95% (n=4 studies), and negative predictive value (NPV) from 94% to 99% (n=2 studies).

Conclusion

Artificial intelligence and machine learning provide a high diagnostic and classification performance in detecting PCOS, thereby providing an avenue for early diagnosis of this disorder. However, AI-based studies should use standardized PCOS diagnostic criteria to enhance the clinical applicability of AI/ML in PCOS and improve adherence to methodological and reporting guidelines for maximum diagnostic utility.

Systematic review registration

https://www.crd.york.ac.uk/prospero/, identifier CRD42022295287.

Modulation of the Inflammatory Response in Polycystic Ovary Syndrome (PCOS)-Searching for Epigenetic Factors

Polycystic ovary syndrome (PCOS) is the most common endocrine disorder in women of reproductive age. Despite its incidence, the syndrome is poorly understood and remains underdiagnosed, and female patients are diagnosed with a delay. The heterogenous nature of this complex disorder results from the combined occurrence of genetic, environmental, endocrine, and behavioral factors. Primary clinical manifestations of PCOS are derived from the excess of androgens (anovulation, polycystic ovary morphology, lack of or scanty, irregular menstrual periods, acne and hirsutism), whereas the secondary manifestations include multiple metabolic, cardiovascular, and psychological disorders. Dietary and lifestyle factors play important roles in the development and course of PCOS, which suggests strong epigenetic and environmental influences. Many studies have shown a strong association between PCOS and chronic, low-grade inflammation both in the ovarian tissue and throughout the body. In the vast majority of PCOS patients, elevated values of inflammatory markers or their gene markers have been reported. Development of the vicious cycle of the chronic inflammatory state in PCOS is additionally stimulated by hyperinsulinemia and obesity. Changes in DNA methylation, histone acetylation and noncoding RNA levels are presented in this review in the context of oxidative stress, reactive oxygen species, and inflammatory signaling in PCOS. Epigenetic modulation of androgenic activity in response to inflammatory signaling is also discussed.

Molecular Features of Polycystic Ovary Syndrome Revealed by Transcriptome Analysis of Oocytes and Cumulus Cells

Polycystic ovary syndrome (PCOS) is typically characterized by a polycystic ovarian morphology, hyperandrogenism, ovulatory dysfunction, and infertility. Furthermore, PCOS patients undergoing ovarian stimulation have more oocytes; however, the poor quality of oocytes leads to lower fertilization and implantation rates, decreased pregnancy rates, and increased miscarriage rates. The complex molecular mechanisms underlying PCOS and the poor quality of oocytes remain to be elucidated. We obtained matched oocytes and cumulus cells (CCs) from PCOS patients, compared them with age-matched controls, and performed RNA sequencing analysis to explore the transcriptional characteristics of their oocytes and CCs. Moreover, we validated our newly confirmed candidate genes for PCOS by immunofluorescence. Unsupervised clustering analysis showed that the overall global gene expression patterns and transposable element (TE) expression profiles of PCOS patients tightly clustered together, clearly distinct from those of controls. Abnormalities in functionally important pathways are found in PCOS oocytes. Notably, genes involved in microtubule processes, TUBB8 and TUBA1C, are overexpressed in PCOS oocytes. The metabolic and oxidative phosphorylation pathways are also dysregulated in both oocytes and CCs from PCOS patients. Moreover, in oocytes, differentially expressed TEs are not uniformly dispersed in human chromosomes. Endogenous retrovirus 1 (ERV1) elements located on chromosomes 2, 3, 4, and 5 are rather highly upregulated. Interestingly, these correlate with the most highly expressed protein-coding genes, including tubulin-associated genes TUBA1C, TUBB8P8, and TUBB8, linking the ERV1 elements to the occurrence of PCOS. Our comprehensive analysis of gene expression in oocytes and CCs, including TE expression, revealed the specific molecular features of PCOS. The aberrantly elevated expression of TUBB8 and TUBA1C and ERV1 provides additional markers for PCOS and may contribute to the compromised oocyte developmental competence in PCOS patients. Our findings may also have implications for treatment strategies to improve oocyte maturation and the pregnancy outcomes for women with PCOS.

Impact of Increased Oxidative Stress on Cardiovascular Diseases in Women With Polycystic Ovary Syndrome

Polycystic ovary syndrome (PCOS) is a complex disorder that affects around 5% to 10% of women of childbearing age worldwide, making it the most common source of anovulatory infertility. PCOS is defined by increased levels of androgens, abnormal ovulation, irregular menstrual cycles, and polycystic ovarian morphology in one or both ovaries. Women suffering from this condition have also been shown to frequently associate certain cardiovascular comorbidities, including obesity, hypertension, atherosclerosis, and vascular disease. These factors gradually lead to endothelial dysfunction and coronary artery calcification, thus posing an increased risk for adverse cardiac events. Traditional markers such as C-reactive protein (CRP) and homocysteine, along with more novel ones, specifically microRNAs (miRNAs), can accurately signal the risk of cardiovascular disease (CVD) in PCOS women. Furthermore, studies have also reported that increased oxidative stress (OS) coupled with poor antioxidant status significantly add to the increased cardiovascular risk among these patients. OS additionally contributes to the modified ovarian steroidogenesis, consequently leading to hyperandrogenism and infertility. The present review is therefore aimed not only at bringing together the most significant information regarding the role of oxidative stress in promoting CVD among PCOS patients, but also at highlighting the need for determining the efficiency of antioxidant therapy in these patients.

Bisphenol-A and polycystic ovary syndrome: a review of the literature

Polycystic ovary syndrome (PCOS) is the most common endocrine disorder among women of reproductive age with reproductive, metabolic and endocrine implications. While the exact pathophysiological mechanisms of the syndrome are unknown, its heterogeneity suggests a multifactorial causal background. In the last two decades, numerous environmental chemicals, including Bisphenol-A (BPA) that is used in the synthesis of polycarbonate plastics, have been proposed as potential contributors to the aetiology of PCOS. This review provides a holistic overview of the available data regarding the possible relation of PCOS with BPA exposure. We have included a total number of 24 studies. Eleven human case-control and 13 animal studies provided data regarding this potential relation. Accumulating evidence suggests that a correlation between high levels of BPA and the presence of PCOS may exist. Contradicting results from human and animal studies, however, render it difficult to conclude on the exact role of BPA in the pathogenesis of PCOS. BPA may constitute a consequence of the syndrome rather than a cause, but further research is still needed to clarify this. Continued efforts to study the early origins of PCOS, using prospective-designed studies, are required to identify the exact effect of BPA on women with PCOS.

Establishment and Analysis of a Combined Diagnostic Model of Polycystic Ovary Syndrome with Random Forest and Artificial Neural Network

Polycystic ovary syndrome (PCOS) is one of the most common metabolic and reproductive endocrinopathies. However, few studies have tried to develop a diagnostic model based on gene biomarkers. In this study, we applied a computational method by combining two machine learning algorithms, including random forest (RF) and artificial neural network (ANN), to identify gene biomarkers and construct diagnostic model. We collected gene expression data from Gene Expression Omnibus (GEO) database containing 76 PCOS samples and 57 normal samples; five datasets were utilized, including one dataset for screening differentially expressed genes (DEGs), two training datasets, and two validation datasets. Firstly, based on RF, 12 key genes in 264 DEGs were identified to be vital for classification of PCOS and normal samples. Moreover, the weights of these key genes were calculated using ANN with microarray and RNA-seq training dataset, respectively. Furthermore, the diagnostic models for two types of datasets were developed and named neuralPCOS. Finally, two validation datasets were used to test and compare the performance of neuralPCOS with other two set of marker genes by area under curve (AUC). Our model achieved an AUC of 0.7273 in microarray dataset, and 0.6488 in RNA-seq dataset. To conclude, we uncovered gene biomarkers and developed a novel diagnostic model of PCOS, which would be helpful for diagnosis.