Identification of hub biomarkers of myocardial infarction by single-cell sequencing, bioinformatics, and machine learning

Zhang, Qunhui; Guo, Yang; Zhang, Benyin; Liu, Hairui; Peng, Yanfeng; Wang, Di; Zhang, Dejun

doi:10.3389/fcvm.2022.939972

Cited by 10 publications

(8 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also found that Nobiletin, which targets PLA2G4, may indicate a third pathway for the treatment of acute myeloid leukemia. Zhang [ 90 ] utilized SVM and LASSO to screen the underlying feature biomarkers in four RNA microarray datasets of myocardial infarction. These two machine learning methods yielded 10 and 14 genes, respectively.…”

Section: Applications Of Machine Learning In Tcm Researchmentioning

confidence: 99%

Machine learning in TCM with natural products and molecules: current status and future perspectives

Liu

et al. 2023

Chin Med

View full text Add to dashboard Cite

Traditional Chinese medicine (TCM) has been practiced for thousands of years with clinical efficacy. Natural products and their effective agents such as artemisinin and paclitaxel have saved millions of lives worldwide. Artificial intelligence is being increasingly deployed in TCM. By summarizing the principles and processes of deep learning and traditional machine learning algorithms, analyzing the application of machine learning in TCM, reviewing the results of previous studies, this study proposed a promising future perspective based on the combination of machine learning, TCM theory, chemical compositions of natural products, and computational simulations based on molecules and chemical compositions. In the first place, machine learning will be utilized in the effective chemical components of natural products to target the pathological molecules of the disease which could achieve the purpose of screening the natural products on the basis of the pathological mechanisms they target. In this approach, computational simulations will be used for processing the data for effective chemical components, generating datasets for analyzing features. In the next step, machine learning will be used to analyze the datasets on the basis of TCM theories such as the superposition of syndrome elements. Finally, interdisciplinary natural product-syndrome research will be established by unifying the results of the two steps outlined above, potentially realizing an intelligent artificial intelligence diagnosis and treatment model based on the effective chemical components of natural products under the guidance of TCM theory. This perspective outlines an innovative application of machine learning in the clinical practice of TCM based on the investigation of chemical molecules under the guidance of TCM theory.

show abstract

Section: Applications Of Machine Learning In Tcm Researchmentioning

confidence: 99%

Machine learning in TCM with natural products and molecules: current status and future perspectives

Liu

et al. 2023

Chin Med

View full text Add to dashboard Cite

show abstract

“…By examining individual cells, particularly their gene expression patterns within different cell subpopulations, researchers have successfully identified a range of potential biomarkers associated with MI. For example, Zhang et al ( 280 ) used scRNA-seq technology to reveal the potential roles that IL1B and TLR2 may play in the diagnosis of MI, which are closely related to various infiltrating immune cells. Another study also identified a series of immune cell-related genes, including FOS , DUSP1 , CXCL8 , and NFKBIA , which can not only differentiate between AMI and coronary heart disease (CHD) but also predict the risk of HF in AMI patients ( 281 ).…”

Section: Single-omics Approachesmentioning

confidence: 99%

From multi-omics approaches to personalized medicine in myocardial infarction

Zhan,

Tang,

et al. 2023

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

Myocardial infarction (MI) is a prevalent cardiovascular disease characterized by myocardial necrosis resulting from coronary artery ischemia and hypoxia, which can lead to severe complications such as arrhythmia, cardiac rupture, heart failure, and sudden death. Despite being a research hotspot, the etiological mechanism of MI remains unclear. The emergence and widespread use of omics technologies, including genomics, transcriptomics, proteomics, metabolomics, and other omics, have provided new opportunities for exploring the molecular mechanism of MI and identifying a large number of disease biomarkers. However, a single-omics approach has limitations in understanding the complex biological pathways of diseases. The multi-omics approach can reveal the interaction network among molecules at various levels and overcome the limitations of the single-omics approaches. This review focuses on the omics studies of MI, including genomics, epigenomics, transcriptomics, proteomics, metabolomics, and other omics. The exploration extended into the domain of multi-omics integrative analysis, accompanied by a compilation of diverse online resources, databases, and tools conducive to these investigations. Additionally, we discussed the role and prospects of multi-omics approaches in personalized medicine, highlighting the potential for improving diagnosis, treatment, and prognosis of MI.

show abstract

“…However, AMI patients need to complete continuous follow-ups to evaluate and improve their prognosis. Recently, the Gensini score and the SYNTAX score were used to predict the prognosis of AMI in clinics, but they could not be widely applied due to their complexity [ 3 – 5 ]. It was estimated that more than 50% of malnourished critically ill AMI patients admitted to the intensive care unit (ICU) could have more comorbidities and the risk of organ dysfunction [ 6 , 7 ].…”

Section: Introductionmentioning

confidence: 99%

The prognostic nutritional index predicts all-cause mortality in critically ill patients with acute myocardial infarction

Huang

Zhang

et al. 2023

BMC Cardiovasc Disord

Self Cite

View full text Add to dashboard Cite

Background Malnutrition is common in patients with acute myocardial infarction (AMI) and is associated with a poor prognosis. The prognostic value of the prognostic nutritional index (PNI) in patients with AMI remains controversial. We aimed to explore the relationship between PNI and all-cause mortality in critically ill patients with AMI and evaluate the incremental prognostic value of PNI to commonly used prognostic assessment tools. Methods The Medical Information Mart for Intensive Care-IV (MIMIC-IV) database was used to conduct a retrospective cohort analysis on 1180 critically ill patients with AMI. The primary endpoints were defined as 6-month and 1-year all-cause mortality. Cox regression analysis was used to investigate the relationship between admission PNI and all-cause mortality. The effect of adding PNI to sequential organ failure assessment (SOFA) score, or charlson comorbidity index (CCI) on its discriminative ability was assessed using C-statistic, net reclassification improvement (NRI), and integrated discrimination improvement (IDI). Results Multivariate cox regression analysis demonstrated that the low PNI was regarded as an independent predictor of 1-year all-cause mortality in AMI patients admitted to ICU (adjusted Hazard Ratio: 95% CI = 1.75 (1.22–2.49)). The ROC test showed that admission PNI had a moderate predictive ability to predict all-cause mortality of critically ill patients with AMI. Furthermore, the net reclassification and integrated discrimination of the CCI alone model improved significantly with PNI. [C-statistic increased from 0.669 to 0.752, p < 0.001; NRI = 0.698, p < 0.001; IDI = 0.073, p < 0.001]. When PNI was added to the SOFA score, the C-statistic significantly improved from 0.770 to 0.805 (p < 0.001), and the NRI and IDI were estimated at 0.573 (p < 0.001) and 0.041 (p < 0.001), respectively. Conclusion PNI could be a novel predictor for identifying patients at high risk of 1-year all-cause mortality in critically ill patients with AMI. The addition of PNI to the SOFA score or CCI may be useful for very early risk stratification.

show abstract

Identification of hub biomarkers of myocardial infarction by single-cell sequencing, bioinformatics, and machine learning

Cited by 10 publications

References 42 publications

Machine learning in TCM with natural products and molecules: current status and future perspectives

Machine learning in TCM with natural products and molecules: current status and future perspectives

From multi-omics approaches to personalized medicine in myocardial infarction

The prognostic nutritional index predicts all-cause mortality in critically ill patients with acute myocardial infarction

Contact Info

Product

Resources

About