PCOSDB: PolyCystic Ovary Syndrome Database for manually curated disease associated genes

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.

An update on polycystic ovary syndrome: A review of the current state of knowledge in diagnosis, genetic etiology, and emerging treatment options

Polycystic ovary syndrome is the most common endocrine disorder in women of reproductive age, which is still incurable. However, the symptoms can be successfully managed with proper medication and lifestyle interventions. Despite its prevalence, little is known about its etiology. In this review article, the up-to-date diagnostic features and parameters recommended on the grounds of evidence-based data and different guidelines are explored. The ambiguity and insufficiency of data when diagnosing adolescent women have been put under special focus. We look at some of the most recent research done to establish relationships between different gene polymorphisms with polycystic ovary syndrome in various populations along with the underestimated impact of environmental factors like endocrine-disrupting chemicals on the reproductive health of these women. Furthermore, the article concludes with existing treatments options and the scopes for advancement in the near future. Various therapies have been considered as potential treatment through multiple randomized controlled studies, and clinical trials conducted over the years are described in this article. Standard therapies ranging from metformin to newly found alternatives based on vitamin D and gut microbiota could shine some light and guidance toward a permanent cure for this female reproductive health issue in the future.

PCOSKBR2: a database of genes, diseases, pathways, and networks associated with polycystic ovary syndrome

PolyCystic Ovary Syndrome KnowledgeBase (PCOSKBR2) is a manually curated database with information on 533 genes, 145 SNPs, 29 miRNAs, 1,150 pathways, and 1,237 diseases associated with PCOS. This data has been retrieved based on evidence gleaned by critically reviewing literature and related records available for PCOS in databases such as KEGG, DisGeNET, OMIM, GO, Reactome, STRING, and dbSNP. Since PCOS is associated with multiple genes and comorbidities, data mining algorithms for comorbidity prediction and identification of enriched pathways and hub genes are integrated in PCOSKBR2, making it an ideal research platform for PCOS. PCOSKBR2 is freely accessible at http://www.pcoskb.bicnirrh.res.in/ .

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.

Computational characterization and identification of human polycystic ovary syndrome genes

Human polycystic ovary syndrome (PCOS) is a highly heritable disease regulated by genetic and environmental factors. Identifying PCOS genes is time consuming and costly in wet-lab. Developing an algorithm to predict PCOS candidates will be helpful. In this study, for the first time, we systematically analyzed properties of human PCOS genes. Compared with genes not yet known to be involved in PCOS regulation, known PCOS genes display distinguishing characteristics: (i) they tend to be located at network center; (ii) they tend to interact with each other; (iii) they tend to enrich in certain biological processes. Based on these features, we developed a machine-learning algorithm to predict new PCOS genes. 233 PCOS candidates were predicted with a posterior probability >0.9. Evidence supporting 7 of the top 10 predictions has been found.

Dysregulated genes and their functional pathways in luteinized granulosa cells from PCOS patients after cabergoline treatment

Polycystic ovarian syndrome (PCOS) is a common reproductive disorder frequently associated with a substantial risk factor for ovarian hyperstimulation syndrome (OHSS). Dopamine receptor 2 (D2) agonists, like cabergoline (Cb2), have been used to reduce the OHSS risk. However, lutein granulosa cells (LGCs) from PCOS patients treated with Cb2 still show a deregulated dopaminergic tone (decreased D2 expression and low dopamine production) and increased vascularization compared to non-PCOS LGCs. Therefore, to understand the PCOS ovarian physiology, it is important to explore the mechanisms that underlie syndrome based on the therapeutic effects of Cb2. Here, LGCs from non-PCOS and PCOS patients were cultured with hCG in the absence/presence of Cb2 (n = 12). Subsequently, a transcriptomic-paired design that compared untreated vs treated LGCs within each patient was performed. After transcriptomic analysis, functions and genes were prioritized by systems biology approaches and validated by RT-qPCR. We identified that similar functions were altered in both PCOS and non-PCOS LGCs treated with Cb2; however, PCOS-treated LGCs exhibited more significant changes than non-PCOS. Among the prioritized functions, dopaminergic synapse, vascular endothelial growth factor (VEGF) signaling, apoptosis and ovarian steroidogenesis were highlighted. Finally, network modeling showed CASP9, VEGFA, AKT1, CREB, AIF, MAOA, MAPK14 and BMAL1 as key genes implicated in these pathways in Cb2 response, which might be potential biomarkers for further studies in PCOS.

Polymorphism of the PAI-1gene (4G/5G) may be linked with Polycystic Ovary Syndrome and associated pregnancy disorders in South Indian Women

Polycystic Ovary syndrome (PCOS) is the most common endocrine disorder affecting 5 - 10% of all women of reproductive age group. The present research was carried out to study the impact of Plasminogen Activator Inhibitor (PAI-1) 4G/5G polymorphism (rs1799889) in PCOS, and the risk of developing PCOS in South Indian Population. The study was carried out in 60 subjects of South Indian population (30 PCOS and 30 Non PCOS) recruited from ARC Research and Fertility Centre, Chennai, India. Genotype and Allelic frequencies were compared by Fisher exact test, Hardy Weinberg equilibrium. p<0.05 was considered statistically significant. The Genotype frequency difference between PCOS and non-PCOS was observed as statistically non-significant (p=0.4647, OR=1.3077, 95% CI 0.63-2.68). The allelic frequency distribution in Spontaneous Abortion (SAB) cases in total subjects is not found to be statistically significant (p=0. 29), however the PCOS women carrying mutant homozygous and heterozygous genotype are more prone to recurrent pregnancy loss. Out of 17 Implantation failure cases, 23.52% were found to carry mutant homozygous (4G/4G), and 66.66% carried mutant heterozygous (4G/5G), and 5.88% carried wild type homozygous (5G/5G), the allelic difference was highly significant with 4G (62.5%), and 5G (37.5%). P value is highly significant and recorded at p=0.0164. The positive correlation between PAI-1 4G/5G polymorphism and PCOS risk was not observed in this study, however, the correlation between Recurrent Pregnancy Loss (RPL) and Implantation failures were observed in PCOS cases.