基于miRNA-gene调控网络的miRNA重要性评估

Evaluation of the importance of miRNAs based on miRNA-gene regulatory networks

MicroRNAs(miRNAs)是一类非编码短序列RNAs分子,它能够与靶基因特异性结合,进而影响靶基因对应的蛋白质产量。单个miRNA可能调节多个基因的表达,同时,单个基因的表达也可能被多个miRNAs所调控。已有研究表明,miRNA可以作为潜在的肿瘤标志物用于癌症的早期诊断和治疗。评价不同miRNAs的重要性对于探究miRNA在各种疾病中的作用具有重要的意义。因此,文章基于miRNA与基因之间的调控网络,提出了一种miRNA重要性评价指标。通过对该指标对miRNAs进行打分排序,排名靠前的miRNAs与疾病相关可能性越大,GO富集分析结果表明,排名靠前的miRNAs具有重要的生物学功能。基于排名靠前的100个miRNAs表达特征,训练SVM分类模型对各种癌症进行分类,实验证明其平均精度达到90%以上。总之,文章提出的miRNA重要性指标对于疾病相关miRNAs的识别以及应用具有重要的指导意义。

MicroRNAs(miRNAs) are a class of non-coding short sequence RNA molecules that can specifically bind to target genes, thereby influencing the production of proteins corresponding to the target genes. A single miRNA may regulate the expression of multiple genes, and conversely, the expression of a single gene may be regulated by multiple miRNAs. Existing research has shown that miRNAs can serve as potential tumor markers for early diagnosis and treatment of cancer. Evaluating the importance of different miRNAs is crucial for exploring the role of miRNAs in various diseases. Therefore, based on the regulatory network between miRNAs and genes, this study proposes an evaluation index for miRNA importance. By scoring and ranking miRNAs based on this index, miRNAs ranked higher are more likely to be associated with diseases. GO enrichment analysis results indicate that these top-ranked miRNAs have significant biological functions. Based on the expression characteristics of the top 100 ranked miRNAs, an SVM classification model is trained to classify various cancers, with an average accuracy of over 90%. The model also performs well in cancer classification problems. In conclusion, the proposed miRNA importance index in this study has important guiding significance for the identification of disease-related miRNAs and the application of miRNAs.