A network-based machine-learning framework to identify both functional modules and disease genes

Yang, Kuo; Lu, Kezhi; Wu, Yang; Yu, Jian; Liu, Baoyan; Zhao, Yi; Chen, Jianxin; Zhou, Xin

doi:10.1007/s00439-020-02253-0

Cited by 11 publications

(5 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We chose text mining evidence to screen for interactions supported by published literature. With a degree cutoff = 2, node score cutoff = 0.2, kcore = 2, and max depth = 100, 10 Molecular Complex Detection (MCODE) was applied in Cytoscape to find functional clusters of genes in the PPI network. 11 Modules with established scores >5 were screened out.…”

Section: Protein-protein Interaction (Ppi) Network Construction and H...mentioning

confidence: 99%

Identification of key proteins as potential biomarkers associated with post-infarction complications in diabetics

Wu,

Yan,

Yuan

et al. 2023

Int J Immunopathol Pharmacol

View full text Add to dashboard Cite

Background: The ability of transcriptome analysis to identify dysregulated pathways and outcome-related genes following myocardial infarction in diabetic patients remains unknown. The present study was designed to detect possible biomarkers associated with the incidence of post-infarction complications in diabetes to assist thedevelopment of novel treatments for this condition. Methods: Two gene expression datasets, GSE12639 and GSE6880, were downloaded from the Gene Expression Omnibus (GEO) database, and then differentially expressed genes (DEGs) were identified between post-infarction diabetics and healthy samples from the left ventricular wall of rats. These DEGs were then arranged into a protein–protein interaction (PPI) network, and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway and Gene Ontology (GO) enrichment analyses were performed to explore the functional roles of these genes. Results: In total, 30 DEGs (14 upregulated and 16 downregulated) were shared between these two datasets, as identified through Venn diagram analyses. GO analyses revealed these DEGs to be significantly enriched in ovarian steroidogenesis, fatty acid elongation, biosynthesis of unsaturated fatty acids, synthesis and degradation of ketone bodies, and butanoate metabolism. The PPI network of the DEGs had 14 genes and 70 edges. We identified two key proteins, 3-hydroxymethylglutaryl-CoA synthase 2 (Hmgcs2) and Δ3, Δ2-Enoyl-CoA Delta Isomerase 1 (ECI1), and the upregulated gene Hmgcs2 with the highest score in the MCC method. We generated a co-expression network for the hub genes and obtained the top ten medications suggested for infarction with diabetes. Conclusion: Taken together, the findings of these bioinformatics analyses identified key hub genes associated with the development of myocardial infarction in diabetics. These hub genes and potential drugs may become novel biomarkers for prognosis and precision treatment in the future.

show abstract

Section: Protein-protein Interaction (Ppi) Network Construction and H...mentioning

confidence: 99%

Identification of key proteins as potential biomarkers associated with post-infarction complications in diabetics

Wu,

Yan,

Yuan

et al. 2023

Int J Immunopathol Pharmacol

View full text Add to dashboard Cite

show abstract

“…Consequently, it serves as a valuable foundation for training machine learning models [10,11]. Moreover, with the wide application of machine learning algorithms, in-depth mining technology for network graph information is constantly being developed [12][13][14].…”

Section: Introductionmentioning

confidence: 99%

The biomedical knowledge graph of symptom phenotype in coronary artery plaque: machine learning-based analysis of real-world clinical data

Huan,

Wang,

et al. 2024

BioData Mining

View full text Add to dashboard Cite

A knowledge graph can effectively showcase the essential characteristics of data and is increasingly emerging as a significant means of integrating information in the field of artificial intelligence. Coronary artery plaque represents a significant etiology of cardiovascular events, posing a diagnostic challenge for clinicians who are confronted with a multitude of nonspecific symptoms. To visualize the hierarchical relationship network graph of the molecular mechanisms underlying plaque properties and symptom phenotypes, patient symptomatology was extracted from electronic health record data from real-world clinical settings. Phenotypic networks were constructed utilizing clinical data and protein‒protein interaction networks. Machine learning techniques, including convolutional neural networks, Dijkstra's algorithm, and gene ontology semantic similarity, were employed to quantify clinical and biological features within the network. The resulting features were then utilized to train a K-nearest neighbor model, yielding 23 symptoms, 41 association rules, and 61 hub genes across the three types of plaques studied, achieving an area under the curve of 92.5%. Weighted correlation network analysis and pathway enrichment were subsequently utilized to identify lipid status-related genes and inflammation-associated pathways that could help explain the differences in plaque properties. To confirm the validity of the network graph model, we conducted coexpression analysis of the hub genes to evaluate their potential diagnostic value. Additionally, we investigated immune cell infiltration, examined the correlations between hub genes and immune cells, and validated the reliability of the identified biological pathways. By integrating clinical data and molecular network information, this biomedical knowledge graph model effectively elucidated the potential molecular mechanisms that collude symptoms, diseases, and molecules.

show abstract

“…HN involves a number of complex pathological changes and is associated with a large number of combinations of symptoms and signs. Using a complex network based on real-world data (RWD), it is possible to collect relevant information about diseases from electronic medical records (EMRs) and biological databases and to analyze the prescription network of botanical drugs in RWD, thereby decreasing the difficulties caused by the diversity of the clinical manifestations of diseases ( Wang et al, 2019 ; Yang et al, 2021 ). Existing studies ( Wang et al, 2021 ) show that small molecules present in botanical drugs can not only act on disease-related genes but also play a role in interfering with the disease process through biological networks.…”

Section: Introductionmentioning

confidence: 99%

Effect of botanical drugs in improving symptoms of hypertensive nephropathy: Analysis of real-world data, retrospective cohort, network, and experimental assessment

Huan

et al. 2023

Front. Pharmacol.

View full text Add to dashboard Cite

Background/aim: Hypertensive nephropathy (HN) is a common complication of hypertension. Traditional Chinese medicine has long been used in the clinical treatment of Hypertensive nephropathy. However, botanical drug prescriptions have not been summarized. The purpose of this study is to develop a prescription for improving hypertensive nephropathy, explore the evidence related to clinical application of the prescription, and verify its molecular mechanism of action.Methods: In this study, based on the electronic medical record data on Hypertensive nephropathy, the core botanical drugs and patients’ symptoms were mined using the hierarchical network extraction and fast unfolding algorithm, and the protein interaction network between botanical drugs and Hypertensive nephropathy was established. The K-nearest neighbors (KNN) model was used to analyze the clinical and biological characteristics of botanical drug compounds to determine the effective compounds. Hierarchical clustering was used to screen for effective botanical drugs. The clinical efficacy of botanical drugs was verified by a retrospective cohort. Animal experiments were performed at the target and pathway levels to analyze the mechanism.Results: A total of 14 botanical drugs and five symptom communities were obtained from real-world clinical data. In total, 76 effective compounds were obtained using the K-nearest neighbors model, and seven botanical drugs were identified as Gao Shen Formula by hierarchical clustering. Compared with the classical model, the Area under the curve (AUC) value of the K-nearest neighbors model was the best; retrospective cohort verification showed that Gao Shen Formula reduced serum creatinine levels and Chronic kidney disease (CKD) stage [OR = 2.561, 95% CI (1.025–6.406), p < 0.05]. With respect to target and pathway enrichment, Gao Shen Formula acts on inflammatory factors such as TNF-α, IL-1β, and IL-6 and regulates the NF-κB signaling pathway and downstream glucose and lipid metabolic pathways.Conclusion: In the retrospective cohort, we observed that the clinical application of Gao Shen Formula alleviates the decrease in renal function in patients with hypertensive nephropathy. It is speculated that Gao Shen Formula acts by reducing inflammatory reactions, inhibiting renal damage caused by excessive activation of the renin-angiotensin-aldosterone system, and regulating energy metabolism.

show abstract

A network-based machine-learning framework to identify both functional modules and disease genes

Cited by 11 publications

References 64 publications

Identification of key proteins as potential biomarkers associated with post-infarction complications in diabetics

Identification of key proteins as potential biomarkers associated with post-infarction complications in diabetics

The biomedical knowledge graph of symptom phenotype in coronary artery plaque: machine learning-based analysis of real-world clinical data

Effect of botanical drugs in improving symptoms of hypertensive nephropathy: Analysis of real-world data, retrospective cohort, network, and experimental assessment

Contact Info

Product

Resources

About