Revealing Epigenetic Factors of circRNA Expression by Machine Learning in Various Cellular Contexts.

Haozhe Zou,Qi Wang,Kang Xu,Limei Fu,Yongsheng Li,Zhenghong Chang,Mengying Zhang,Yan Zhang

doi:10.1016/j.isci.2020.101842

Haozhe Zou, Qi Wang + Show 6 more

Open Access

https://doi.org/10.1016/j.isci.2020.101842

Copy DOI

Abstract

SummaryCircular RNAs (circRNAs) have been identified as naturally occurring RNAs that are highly represented in the eukaryotic transcriptome. Although a large number of circRNAs have been reported, the underlying regulatory mechanism of circRNAs biogenesis remains largely unknown. Here, we integrated in-depth multi-omics data including epigenome, transcriptome, and non-coding RNA and identified candidate circRNAs in six cellular contexts. Next, circRNAs were divided into two classes (high versus low) with different expression levels. Machine learning models were constructed that predicted circRNA expression levels based on 11 different histone modifications and host gene expression. We found that the models achieve great accuracy in predicting high versus low expressed circRNAs. Furthermore, the expression levels of host genes of circRNAs, H3k36me3, H3k79me2, and H4k20me1 contributed greatly to the classification models in six cellular contexts. In summary, all these results suggest that epigenetic modifications, particularly histone modifications, can effectively predict expression levels of circRNAs.

Highlights

Circular RNA is a novel endogenous non-coding RNA that is common in the eukaryotic transcriptome (Glazar et al, 2014; Memczak et al, 2013; Salzman et al, 2013) and characterized by the presence of covalent bonds connecting the 30 and 50 ends (Jeck et al, 2013)
Machine learning models were constructed that predicted circRNA expression levels based on 11 different histone modifications and host gene expression
We found that the models achieve great accuracy in predicting high versus low expressed circRNAs

Summary

Introduction

Circular RNA (circRNA) is a novel endogenous non-coding RNA that is common in the eukaryotic transcriptome (Glazar et al, 2014; Memczak et al, 2013; Salzman et al, 2013) and characterized by the presence of covalent bonds connecting the 30 and 50 ends (Jeck et al, 2013). The cyclization of circRNAs is promoted by surrounding complementary sequences and regulated by specific RNA-binding proteins (Ashwal-Fluss et al, 2014; Conn et al, 2015; Ivanov et al, 2015; Liang and Wilusz, 2014; Zhang et al, 2014). Both alternative splicing events within the same back-splice junction and alternative back-splice site selection can produce various circRNAs from the same gene locus (Gao et al, 2016). CircASAP1, a circRNA derived from exons 2 and 3 of the ASAP1 gene, was overexpressed in hepatocellular carcinoma (HCC) cell lines with high metastatic potential and in metastatic HCCs (Hu et al, 2019)

Methods

Results

Discussion

Conclusion