基于自编码器的疾病相关miRNAs的预测方法

Predictive method for disease-associated miRNAs based on autoencoders

MicroRNAs(miRNAs)是一类由内源基因编码的长度约为22个核苷酸的非编码单链RNA分子,它们在动植物中参与转录后基因表达调控。大量研究表明,miRNAs在包括肿瘤在内的多种复杂疾病发生、发展过程中扮演着重要的角色。因此,识别疾病相关的miRNAs对研究疾病的机理及治疗具有重要意义。鉴于湿实验验证方法存在耗时长、成本高的缺点,当前许多研究工作聚焦于开发高效计算模型,识别新的miRNA-disease关联关系。该研究提出一种基于自编码器数据驱动的模型,预测miRNA-disease关联关系。结果表明,作者预测的疾病相关miRNAs在HMDD数据库中对应的疾病相关miRNAs列表上显著富集。此外,通过对排名靠前的miRNAs分析,发现这些miRNAs具有重要的生物学功能,同时对于疾病的分类表现出较高的精度。总之,文章提出的模型,对于疾病相关miRNAs的发现具有重要的辅助作用。

MicroRNAs(miRNAs) are a class of non-coding single-stranded RNA molecules encoded by endogenous genes, with a length of about 22 nucleotides. They participate in post-transcriptional gene expression regulation in animals and plants. Numerous studies have shown that miRNAs play crucial roles in the occurrence and development of various complex diseases, including tumors. Therefore, identifying disease-related miRNAs is of significant importance for studying disease mechanisms and developing appropriate treatment strategies. Given the time-consuming and costly nature of wet-lab validation methods, many researchers focus on developing efficient computational models to identify novel miRNA-disease associations. This study proposes a data-driven model based on autoencoders to predict miRNA-disease associations. The results indicate that the disease-related miRNAs predicted are significantly enriched in the list of disease-related miRNAs from the HMDD database. Furthermore, by analyzing the top-ranked miRNAs, it was found that these miRNAs perform crucial biological functions and accurately exhibit disease classification. In conclusion, the model proposed in this paper serves as a valuable auxiliary tool for the discovery of disease-related miRNAs.