Dataset Information

Identification through machine learning of potential immune- related gene biomarkers associated with immune cell infiltration in myocardial infarction.

ABSTRACT:

Background

To investigate the potential role of immune-related genes (IRGs) and immune cells in myocardial infarction (MI) and establish a nomogram model for diagnosing myocardial infarction.

Methods

Raw and processed gene expression profiling datasets were archived from the Gene Expression Omnibus (GEO) database. Differentially expressed immune-related genes (DIRGs), which were screened out by four machine learning algorithms-partial least squares (PLS), random forest model (RF), k-nearest neighbor (KNN), and support vector machine model (SVM) were used in the diagnosis of MI.

Results

The six key DIRGs (PTGER2, LGR6, IL17B, IL13RA1, CCL4, and ADM) were identified by the intersection of the minimal root mean square error (RMSE) of four machine learning algorithms, which were screened out to establish the nomogram model to predict the incidence of MI by using the rms package. The nomogram model exhibited the highest predictive accuracy and better potential clinical utility. The relative distribution of 22 types of immune cells was evaluated using cell type identification, which was done by estimating relative subsets of RNA transcripts (CIBERSORT) algorithm. The distribution of four types of immune cells, such as plasma cells, T cells follicular helper, Mast cells resting, and neutrophils, was significantly upregulated in MI, while five types of immune cell dispersion, T cells CD4 naive, macrophages M1, macrophages M2, dendritic cells resting, and mast cells activated in MI patients, were significantly downregulated in MI.

Conclusion

This study demonstrated that IRGs were correlated with MI, suggesting that immune cells may be potential therapeutic targets of immunotherapy in MI.

SUBMITTER: Dong H

PROVIDER: S-EPMC10052851 | biostudies-literature | 2023 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identification through machine learning of potential immune- related gene biomarkers associated with immune cell infiltration in myocardial infarction.

Dong Hao H Yan Shi-Bai SB Li Guo-Sheng GS Huang Zhi-Guang ZG Li Dong-Ming DM Tang Yu-Lu YL Le Jia-Qian JQ Pan Yan-Fang YF Yang Zhen Z Pan Hong-Bo HB Chen Gang G Li Ming-Jie MJ

BMC cardiovascular disorders 20230328 1

<h4>Background</h4>To investigate the potential role of immune-related genes (IRGs) and immune cells in myocardial infarction (MI) and establish a nomogram model for diagnosing myocardial infarction.<h4>Methods</h4>Raw and processed gene expression profiling datasets were archived from the Gene Expression Omnibus (GEO) database. Differentially expressed immune-related genes (DIRGs), which were screened out by four machine learning algorithms-partial least squares (PLS), random forest model (RF), ...[more]

PMID: 36978012

Similar Datasets

Project description:BackgroundPreeclampsia (PE) is a multisystem progressive disease that occurs during pregnancy. Previous studies have shown that the immune system is involved in the placental trophoblast function and the pathological process of uterine vascular remodeling in PE. However, its molecular mechanism is still unclear. This study aimed to identify critical genes and immune cells involved in the pathological process of PE.MethodsThe PE-related GSE74341 and GSE160888 datasets were downloaded from the Gene Expression Omnibus (GEO) database, and differential expression analysis, weighted gene co-expression network analysis (WGCNA), and least absolute shrinkage and selection operator (LASSO) analysis were combined to screen the PE-related DEGs. Receiver operating characteristic (ROC) analysis was used to evaluate the diagnostic specificity of obtained DEGs, and the GSE35574 dataset was used for preliminary validation. Furthermore, the single-sample Gene Set Enrichment Analysis (ssGSEA) was used to elucidate the correlation between the DEGs and the 28 types of infiltrating immune cells in PE. Real-time reverse transcription polymerase chain reaction (RT-PCR) was used to verify the differential expression of DEGs in the PE placental tissues.ResultsA total of 143 DEGs (DE-mRNAs) were screened using the PE datasets. The analysis of DEG modules and LASSO logistic regression were used to identify high-temperature requirement factor A4 (HtrA4), tumour suppressor candidate 3 (TUSC3), endothelial protein C receptor gene (PROCR), claudin 3 (CLDN3), and thioredoxin binding protein (TXNIP) as the hub DEGs in PE. Furthermore, validation with the GSE35574 dataset and ROC analysis was used to clarify that the HTRA4, PROCR, and TXNIP genes are potential markers of PE and are closely related to the infiltrating immune cells in PE, such as gamma delta T cells, mast cells, natural killer cells, and T follicular helper cells. Finally, differential HTRA4, PROCR, and TXNIP expression were confirmed in PE placental tissues (p < 0.001).ConclusionHTRA4, PROCR, and TXNIP can be used as potential PE biomarkers to provide a new strategy for early diagnosing and treating PE.

Project description:ObjectiveThis study was designed to identify potential biomarkers for ulcerative colitis (UC) and analyze the immune infiltration characteristics in UC.MethodsDatasets containing human UC and normal control tissues (GSE87466, GSE107597, and GSE13367) were downloaded from the GEO database. Then, the GSE87466 and GSE107597 datasets were merged, and the differentially expressed genes (DEGs) between UC and normal control tissues were screened out by the "limma R" package. The LASSO regression model and support vector machine recursive feature elimination (SVM-RFE) were performed to screen out the best biomarkers. The GSE13367 dataset was used as a validation cohort, and the receiver operating characteristic curve (ROC) was used to evaluate the diagnostic performance. Finally, the immune infiltration characteristics in UC were explored by CIBERSORT, and we further analyzed the correlation between potential biomarkers and different immune cells.ResultsA total of 76 DEGs were screened out, among which 56 genes were upregulated and 20 genes were downregulated. Functional enrichment analysis revealed that these DEGs were mainly involved in immune response, chemokine signaling, IL-17 signaling, cytokine receptor interactions, inflammatory bowel disease, etc. ABCG2, HSPB3, SLC6A14, and VNN1 were identified as potential biomarkers for UC and validated in the GSE13367 dataset (AUC = 0.889, 95% CI: 0.797~0.961). Immune infiltration analysis by CIBERSORT revealed that there were significant differences in immune infiltration characteristics between UC and normal control tissues. A high level of memory B cells, γδ T cells, activated mast cells, M1 macrophages, neutrophils, etc. were found in the UC group, while a high level of M2 type macrophages, resting mast cells, eosinophils, CD8+ T cells, etc. were found in the normal control group.ConclusionABCG2, HSPB3, SLC6A14, and VNN 1 were identified as potential biomarkers for UC. There was an obvious difference in immune infiltration between UC and normal control tissues, which may provide help to guide individualized treatment and develop new research directions.

Project description:BackgroundMyocardial infarction (MI) is one of the first cardiovascular diseases endangering human health. Inflammatory response plays a significant role in the pathophysiological process of MI. Messenger RNA (mRNA) has been proven to play a key role in cardiovascular diseases. Single-cell sequencing (SCS) technology is a new technology for high-throughput sequencing analysis of genome, transcriptome, and epigenome at the single-cell level, and it also plays an important role in the diagnosis and treatment of cardiovascular diseases. Machine learning algorithms have a wide scope of utilization in biomedicine and have demonstrated superior efficiency in clinical trials. However, few studies integrate these three methods to investigate the role of mRNA in MI. The aim of this study was to screen the expression of mRNA, investigate the function of mRNA, and provide an underlying scientific basis for the diagnosis of MI.MethodsIn total, four RNA microarray datasets of MI, namely, GSE66360, GSE97320, GSE60993, and GSE48060, were downloaded from the Gene Expression Omnibus database. The function analysis was carried out by Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and Disease Ontology (DO) enrichment analysis. At the same time, inflammation-related genes (IRGs) were acquired from the GeneCards database. Then, 52 co-DEGs were acquired from differentially expressed genes (DEGs) in differential analysis, IRGs, and genes from SCS, and they were used to construct a protein-protein interaction (PPI) network. Two machine learning algorithms, namely, (1) least absolute shrinkage and selection operator and (2) support vector machine recursive feature elimination, were used to filter the co-DEGs. Gene set enrichment analysis (GSEA) was performed to screen the hub-modulating signaling pathways associated with the hub genes. The results were validated in GSE97320, GSE60993, and GSE48060 datasets. The CIBERSORT algorithm was used to analyze 22 infiltrating immune cells in the MI and healthy control (CON) groups and to analyze the correlation between these immune cells. The Pymol software was used for molecular docking of hub DEGs and for potential treatment of MI drugs acquired from the COREMINE.ResultsA total of 126 DEGs were in the MI and CON groups. After screening two machine learning algorithms and key co-DEGs from a PPI network, two hub DEGs (i.e., IL1B and TLR2) were obtained. The diagnostic efficiency of IL1B, TLR2, and IL1B + TLR2 showed good discrimination in the four cohorts. GSEA showed that KEGG enriched by DEGs were mainly related to inflammation-mediated signaling pathways, and GO biological processes enriched by DEGs were linked to biological effects of various inflammatory cells. Immune analysis indicated that IL1B and TLR2 were correlated with various immune cells. Dan shen, san qi, feng mi, yuan can e, can sha, san qi ye, san qi hua, and cha shu gen were identified as the potential traditional Chinese medicine (TCM) for the treatment of MI. 7-hydroxyflavone (HF) had stable combinations with IL1B and TLR2, respectively.ConclusionThis study identified two hub DEGs (IL1B and TLR2) and illustrated its potential role in the diagnosis of MI to enhance our knowledge of the underlying molecular mechanism. Infiltrating immune cells played an important role in MI. TCM, especially HF, was a potential drug for the treatment of MI.

Dataset Information

Identification through machine learning of potential immune- related gene biomarkers associated with immune cell infiltration in myocardial infarction.

Background

Methods

Results

Conclusion

Publications

Identification through machine learning of potential immune- related gene biomarkers associated with immune cell infiltration in myocardial infarction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets