Advance in applications of artificial intelligence algorithms in cancer-related miRNA research.

Abstract

MiRNAs are a class of small non-coding RNAs, which regulate gene expression post-transcriptionally by partial complementary base pairing. Aberrant miRNA expressions have been reported in tumor tissues and peripheral blood of cancer patients. Bioinformatic tools could improve efficiency of miRNA research, while current bioinformatic tools are in lack of sufficient accuracy. In recent years, artificial intelligence algorithms such as machine learning and deep learning have been widely used in the bioinformatical tools. MiRNA target prediction tools based on artificial intelligence algorithms have higher accuracy than traditional target prediction tools. Bioinformatic tools based on artificial intelligence algorithms successfully predicted miRNA subcellular localization and redistribution, which advanced researchers' understanding of miRNAs. Additionally, the clinical application of artificial intelligence algorithms improved the development of miRNA biomarkers. In this article, we summarized recently developed miRNA bioinformatic tools based on artificial intelligence algorithms. And the potential of machine learning and deep learning in the miRNA research was also highlighted.