Regulatory Genes Through Robust-SNR for Binary Classification Within Functional Genomics Experiments

The current study proposes a novel technique for feature selection by inculcating robustness in the conventional Signal to noise Ratio(SNR).The proposed method utilizes the robust measures of location i.e.,the“Median”as well as the measures of variation i.e.,“Median absolute deviation(MAD)and Interquartile range(IQR)”in the SNR.By this way,two independent robust signal-to-noise ratios have been proposed.The proposed method selects the most informative genes/features by combining the minimum subset of genes or features obtained via the greedy search approach with top-ranked genes selected through the robust signal-to-noise ratio(RSNR).The results obtained via the proposed method are compared with wellknown gene/feature selection methods on the basis of performance metric i.e.,classification error rate.A total of 5 gene expression datasets have been used in this study.Different subsets of informative genes are selected by the proposed and all the other methods included in the study,and their efficacy in terms of classification is investigated by using the classifier models such as support vector machine(SVM),Random forest(RF)and k-nearest neighbors(k-NN).The results of the analysis reveal that the proposed method(RSNR)produces minimum error rates than all the other competing feature selection methods in majority of the cases.For further assessment of the method,a detailed simulation study is also conducted.

Construction and Analysis of an LncRNA-miRNA-mRNA Network Based on Competitive Endogenous RNA Reveal miRNAs Potentially Involved in In-stent Restenosis after Percutaneous Coronary Intervention

Objective:Percutaneous coronary intervention is one of the most common procedures used for the invasive treatment of patients with coronary heart disease;the incidence of in-stent restenosis(ISR)after percutaneous coronary intervention is 5%to 15%.In this study,a competitive endogenous RNA(ceRNA)network was constructed to investigate potential mechanisms involved in ISR.Methods:The expression data for differentially expressed microRNAs(DEmiRNAs)and messenger RNAs(mRNAs)between patients with and without ISR were obtained using limma package.Long noncoding RNAs(lncRNAs)were predicted based on the DEmiRNAs using the miRDB,miRTarBase,and TargetScan databases.An ISR-specific ceRNA network was subsequently constructed and investigated.To verify the key miRNAs of ceRNA,patients with and without ISR were enrolled from Guangdong Provincial Hospital of Chinese Medicine between January 2017 and December 2018(n=8,respectively);plasma was collected from all enrolled patients.Results:Based on the raw data obtained from the Gene Expression Omnibus database,472 DEmiRNAs and 304 differentilly expressed messenger RNAs between patients with and without ISR were identified.A ceRNA network was constructed by combining 270 IncRNAs,3 miRNAs(miR-125,miR-140,and miR-206),and 4 mRNAs(STRADB,TKT,PCTP,and BTG2).The hub genes of the ceRNA network of ISR included the following:miR-125,miR-206,miR-140,PCDHB9,CASC2,BAK1P1,CSPG4P3Y,CSPG4P4Y,STRCP1,and GRIP2.Verification of miRNAs of ceRNA also showed that the expression of miR-206 was upregulated in patients with ISR vs.those without ISR(P<0.05).In contrast,the expression of miR-140 and miR-125 was downregulated in patients with ISR vs.those without ISR(P<0.05).Conclusions:This study constructed noncoding RNA-related ceRNA networks for ISR.The results indicated that miR-206,miR-125,and miR-140 may be biomarkers of ISR.