Rolling Circle cDNA Synthesis Uncovers Circular RNA Splice Variants

Abstract

High-throughput RNA sequencing and novel bioinformatic pipelines have identified thousands of circular (circ)RNAs containing backsplice junction sequences. However, circRNAs generated from multiple exons may contain different combinations of exons and/or introns arising from alternative splicing, while the backsplice junction sequence is the same. To be able to identify circRNA splice variants, we developed a method termed circRNA-Rolling Circle Amplification (circRNA-RCA). This method detects full-length circRNA sequences by performing reverse transcription (RT) in the absence of RNase H activity, followed by polymerase chain reaction (PCR) amplification of full-length circRNAs using a forward primer spanning the backsplice junction sequence and a reverse primer exactly upstream of the forward primer. By sequencing the PCR products, circRNA splice variants bearing the same backsplice junctions, which were otherwise only predicted computationally, could be experimentally validated. The splice variants were further predicted to associate with different subsets of target RNA-binding proteins and microRNAs, supporting the notion that different circRNA splice variants can have different biological impacts. In sum, the circRNA-RCA method allows the accurate identification of full-length circRNA sequences, offering unique insight into their individual function.

Keywords: RNase R; RT-PCR; alternative splicing; backsplice sequence; circRNAs; divergent primers; splice variants.

Figure 1

Validation of circRNA expression using divergent primers. (A) Schematic representation of the divergent primers used for detection and quantification of circRNAs. The red arrowhead represents the backsplice site. (B) PCR products amplified with divergent primers resolved on SYBR Gold-stained, 2% agarose gels. (C) Sanger sequencing of purified PCR products showing the backsplice junction sequences of mentioned circRNAs. The red arrowhead represents the backsplice site. (D) RT-qPCR (reverse transcription-qPCR) analysis of the resistance of circRNAs to RNase R digestion. Data represent the means ± S.E.M. from three experiments.

Figure 2

Schematic of the circRNA-Rolling Circle Amplification (circRNA-RCA) method. Step 1: total RNA is digested with RNase R to enrich the circRNA population. Step 2: the enriched circRNA pool is reverse-transcribed with RNase H-minus reverse transcriptase. Step 3: cDNA prepared in the above step is amplified by PCR, using full-length primers. Step 4: Sanger sequencing of the full-length circRNA PCR products identifies the mature spliced sequence of circRNAs and their splice variants. Black arrowheads represent the backsplice site.

Figure 3

circRNA-RCA for full-length circRNA amplification. RT-PCR products amplified with full-length PCR primers and resolved on SYBR Gold-stained, 2% agarose gels. Arrowheads represent the sequence reported by circBase, while asterisks represent the splice variants. Hashtags represent either the doublets of circRNA or other circRNA isoforms or nonspecific products.

Figure 4

Alternative splicing generates circRNA splice variants. (A) Schematic representation of the CNOT2 pre-mRNA and biogenesis of hsa_circ_0007127 splice variants by alternative splicing. Boxes and straight lines represent exons and introns, respectively. The black dotted lines represent splicing, while the blue dotted lines represent alternative splicing. (B) Spliced full-length sequences of circBase and splice variants of hsa_circ_0007127. The text color matches the color of the exon box in panel A.

Figure 5

Selected list of biological processes enriched in Gene Ontology (GO) annotation analysis for the target genes of miRNAs associated with the sequence of circBase and splice variants of hsa_circ_0007127.