Bioinformatics method combined with logistic regression analysis reveal potentially important miRNAs in ischemic stroke

Wei, Zhiqiang; Qi, Xingdi; Chen, Yan; Xia, Xiaoshuang; Zheng, Boyu; Sun, Xugang; Zhang, Guangming; Zhang, Qi; Xu, Can; Jiang, Shihe; Li, Xiulian; Xie, Bingxin; Liao, Xiao-Hui; Ai, Zhu

doi:10.1042/bsr20201154

Cited by 13 publications

(10 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LR classification has the benefits of small computational complexity, fast speed, little storage resources, and parallelism. It has been frequently utilized to address issues in the field of bioinformatics [ 43 – 45 ]. Using LR as a meta-classifier, the base learners from the first layer are integrated into the second layer in this study.…”

Section: Methodsmentioning

confidence: 99%

StackCirRNAPred: computational classification of long circRNA from other lncRNA based on stacking strategy

Wang

Liu

et al. 2022

BMC Bioinformatics

View full text Add to dashboard Cite

Background CircRNAs are essential for the regulation of post-transcriptional gene expression, including as miRNA sponges, and play an important role in disease development. Some computational tools have been proposed recently to predict circRNA, since only one classifier is used, there is still much that can be done to improve the performance. Results StackCirRNAPred was proposed, the computational classification of long circRNA from other lncRNA based on stacking strategy. In order to cope with the potential problem that a single feature might not be able to distinguish circRNA well from other lncRNA, we first extracted features from different sources, including nucleic acid composition, sequence spatial features and physicochemical properties, Alu and tandem repeats. We innovatively apply the stacking strategy to integrate the more advantageous classifiers of RF, LightGBM, XGBoost. This allows the model to incorporate these features more flexibly. StackCirRNAPred was found to be significantly better than other tools, with precision, accuracy, F1, recall and MCC of 0.843, 0.833, 0.831, 0.819 and 0.666 respectively. We tested it directly on the mouse dataset. StackCirRNAPred was still significantly better than other methods, with precision, accuracy, F1, recall and MCC of 0.837, 0.839, 0.839, 0.841, 0.677. Conclusions We proposed StackCirRNAPred based on stacking strategy to distinguish long circRNAs from other lncRNAs. With the test results demonstrating the validity and robustness of StackCirRNAPred, we hope StackCirRNAPred will complement existing circRNA prediction methods and is helpful in down-stream research.

show abstract

Section: Methodsmentioning

confidence: 99%

StackCirRNAPred: computational classification of long circRNA from other lncRNA based on stacking strategy

Wang

Liu

et al. 2022

BMC Bioinformatics

View full text Add to dashboard Cite

show abstract

“…Logistic regression is a common method in classification, referring to predicting the classifications basing on a group of variables [ 19 ]. In our present work, the β value of various CpG sites were used for the prediction of sample type (atherosclerosis or nonatherosclerotic).…”

Section: Methodsmentioning

confidence: 99%

Integrated Analysis of Gene Expression and Methylation Data to Identify Potential Biomarkers Related to Atherosclerosis Onset

Dong

Lü

et al. 2022

Oxidative Medicine and Cellular Longevity

View full text Add to dashboard Cite

Atherosclerosis is a kind of chronic inflammatory cardiovascular disease. Epigenetic regulation plays a crucial role in atherosclerosis. Our study was aimed at finding potential biomarkers associated with the occurrence of atherosclerosis. Two datasets were downloaded from the Gene Expression Omnibus (GEO) database. The epigenome-wide association study (EWAS) analysis was performed on methylation data using CpGassoc package. The differential expression analysis was conducted on mRNA data using limma package. The GO (Gene Ontology) and KEGG (Kyoto Encyclopedia of Genes and Genomes) functional enrichment was done in clusterProfiler package. Finally, the logistic regression model was constructed using generalized linear model (glm) function. Between atherosclerotic vs. nonatherosclerotic samples, totally 4980 cytosine-phosphate-guanine (CpG) sites (annotated to 2860 genes) and 132 differentially expressed genes (DEGs) related to atherosclerosis were identified. The annotated 2860 genes and 132 DEGs were significantly enriched in 9 and 4 KEGG pathways and 289 and 132 GO terms, respectively. After cross-analysis, 6 crucial CpG sites were screened to build the model, including cg01187920, cg03422911, cg08018825, cg10967350, cg14473924, and cg25313204. The diagnostic model could reliably separate the atherosclerosis samples from nonatherosclerotic samples. In conclusion, the 6 CpG sites are probably potential diagnostic biomarkers for atherosclerosis, including cg01187920, cg03422911, cg08018825, cg10967350, cg14473924, and cg25313204.

show abstract

“…It is an acute cerebrovascular disease, resulting in brain tissue damage due to the sudden rupture of blood vessels in the brain (hemorrhagic strokes) ( Saand et al, 2019 ) or vascular occlusion preventing blood from flowing into the brain (ischemic strokes) ( Patel et al, 2020 ). Ischemic stroke is the most common type of stroke ( Wei et al, 2020 ).…”

Section: Sirtuin 2 and Neuroinflammatory Disordersmentioning

confidence: 99%

Will Sirtuin 2 Be a Promising Target for Neuroinflammatory Disorders?

Zhang

2022

Front. Cell. Neurosci.

View full text Add to dashboard Cite

Neuroinflammatory disorder is a general term that is associated with the progressive loss of neuronal structure or function. At present, the widely studied diseases with neuroinflammatory components are mainly divided into neurodegenerative and neuropsychiatric diseases, namely, Alzheimer’s disease, Parkinson’s disease, depression, stroke, and so on. An appropriate neuroinflammatory response can promote brain homeostasis, while excessive neuroinflammation can inhibit neuronal regeneration and damage the central nervous system. Apart from the symptomatic treatment with cholinesterase inhibitors, antidepressants/anxiolytics, and neuroprotective drugs, the treatment of neuroinflammation is a promising therapeutic method. Sirtuins are a host of class III histone deacetylases, that require nicotinamide adenine dinucleotide for their lysine residue deacetylase activity. The role of sirtuin 2 (SIRT2), one of the sirtuins, in modulating senescence, myelin formation, autophagy, and inflammation has been widely studied. SIRT2 is associated with many neuroinflammatory disorders considering it has deacetylation properties, that regulate the entire immune homeostasis. The aim of this review was to summarize the latest progress in regulating the effects of SIRT2 on immune homeostasis in neuroinflammatory disorders. The overall structure and catalytic properties of SIRT2, the selective inhibitors of SIRT2, the relationship between immune homeostasis and SIRT2, and the multitasking role of SIRT2 in several diseases with neuroinflammatory components were discussed.

show abstract

Bioinformatics method combined with logistic regression analysis reveal potentially important miRNAs in ischemic stroke

Cited by 13 publications

References 28 publications

StackCirRNAPred: computational classification of long circRNA from other lncRNA based on stacking strategy

StackCirRNAPred: computational classification of long circRNA from other lncRNA based on stacking strategy

Integrated Analysis of Gene Expression and Methylation Data to Identify Potential Biomarkers Related to Atherosclerosis Onset

Will Sirtuin 2 Be a Promising Target for Neuroinflammatory Disorders?

Contact Info

Product

Resources

About