Instability of circular RNAs in clinical tissue samples impairs their reliable expression analysis using RT-qPCR: from the myth of their advantage as biomarkers to reality

Abstract

Background: Circular RNAs (circRNAs) are a new class of RNAs with medical significance. Compared to that of linear mRNA transcripts, the stability of circRNAs against degradation owing to their circular structure is considered advantageous for their use as biomarkers. As systematic studies on the stability of circRNAs depending on the RNA integrity, determined as RNA integrity number (RIN), in clinical tissue samples are lacking, we have investigated this aspect in the present study under model and clinical conditions. Methods: Total RNA isolated from kidney cancer tissue and cell lines (A-498 and HEK-293) with different RIN after thermal degradation was used in model experiments. Further, RNA isolated from kidney cancer and prostate cancer tissue collected under routine surgical conditions, representing clinical samples with RIN ranging from 2 to 9, were examined. Quantitative real-time reverse-transcription polymerase chain reaction (RT-qPCR) analysis of several circRNAs (circEGLN3, circRHOBTB3, circCSNK1G3, circRNA4, and circRNA9), their corresponding linear counterparts, tissue-specific reference genes, and three microRNAs (as controls) was performed. The quantification cycles were converted into relative quantities and normalized to the expression of specific reference genes for the corresponding tissue. The effect of RIN on the expression of different RNA entities was determined using linear regression analysis, and clinical samples were classified into two groups based on RIN greater or lesser than 6. Results: The results of model experiments and clinical sample analyses showed that all relative circRNA expression gradually decreased with reduction in RIN values. The adverse effect of RIN was partially compensated after normalizing the data and limiting the samples to only those with RIN values > 6. Conclusions: Our results suggested that circRNAs are not stable in clinical tissue samples, but are subjected to degradative processes similar to mRNAs. This has not been investigated extensively in circRNA expression studies, and hence must be considered in future for obtaining reliable circRNA expression data. This can be achieved by applying the principles commonly used in mRNA expression studies.

Keywords: RNA degradation; RNA integrity; RT-qPCR; circRNA stability; circular RNAs; normalization.

Figure 1

Decrease in RNA integrity after time-dependent thermal degradation of total RNA isolated from renal cell lines A-498 and HEK-293, and the kidney cancer tissue pool. The RNA samples were incubated at 80 °C in Eppendorf tubes for different time points and subsequently transferred to an ice-bath to stop the degradation and stored at -80 °C until analysis. The RIN values at the time points were for the A-498 cells: 10.0, 9.0, 8.2, 7.1, 6.1, 4.4, 3.3, and 2.7; for the HEK-293 cells: 9.7, 8.3, 7.1, 5.8, 4.9, 3.7, 2.8, and 1.9 (the last sample was excluded in further analysis); and for the tissue pool: 8.2, 7.9, 7.0, 6.6, 5.8, 4.6, 3.6, and 3.0. The gel like view of total RNA samples after heat degradation analyzed with the total Agilent RNA 6000 Nano Chip Kit on the Agilent 2100 bioanalyzer is shown in Figure S1.

Figure 2

Expression of circRNAs, mRNAs, and miRNAs depending on RNA degradation in renal cell lines A-498 and HEK-293, and the kidney cancer tissue pool. In the RNA samples shown in Figure 1 with their RNA integrity number (RIN) listed in its legend, all RNA variables (including the conventional reference genes PPIA and TBP for mRNA expression studies in kidney cancer) were analyzed using RT-qPCR and converted to relative values, which are depicted as percentage mean values of triplicates with respect to the starting RIN (RIN 10 for A-498, 9.7 for HEK-293, and 8.2 for kidney cancer tissue pool). In order not to impair the clarity of the figure with the various curves, no error bars were drawn in. The analytical variations of the intra-plate measurements for the RNA variables in the degradation experiments correspond to the %RSD values of the repeatability data in Table S11 (<9%). Linear regression lines were calculated for miRNAs with slopes that did not differ significantly from zero (P-values between 0.157 and 0.877) and with intercepts between 94% and 107% with 95% confidence intervals, while always including the starting point of 100%. CircRNA4 and circRNA9 were included in this study as controls to confirm the effect of RNA integrity on established circRNAs used in other studies . Abbreviations: PPIA: peptidylprolyl isomerase A; TBP: tata-box binding protein.

Figure 3

Expression of circRNAs and their linear counterparts depending on RNA degradation in renal cell lines A-498 and HEK-293, and the kidney cancer tissue pool after normalization to the reference genes PPIA and TBP. The percentage results refer to the expression data used in Figure 2, but normalized to the reference genes PPIA and TBP using the qbase⁺ software. Abbreviations: PPIA: peptidylprolyl isomerase A; TBP: tata-box binding protein.

Figure 4

Differential expression of circRNAs and their linear counterparts in kidney and prostate cancer tissue samples with RIN values of < 6 and > 6 and calculated as relative quantities and normalized relative quantities. The expression data of RNA samples isolated from (A) clear cell renal cell carcinoma with RIN < 6 (n = 28; median 4.3, range 2.3-6.0) and > 6 (n = 33; median 7.7, range 6.1-9.4) and from (B) prostate cancer with RIN < 6 (n = 26; median 3.5, range 2.2-5.5) and > 6 (n = 31; median 7.4, range 6.3-8.2). Data are shown as box- and whisker plots with the individual values of samples. Boxes represent the lower and upper quartiles with medians; whiskers illustrate the range from the minimum to the maximum value. Expression levels are presented as relative quantities (RQs) and normalized quantities (NRQs) using the software qbase⁺ as described in Materials and Methods. Statistical significance was tested using the Mann-Whitney U-test.

Figure 5

Regression analysis of the expression of circRNAs and their linear counterparts in (A) kidney and (B) prostate cancer tissue samples depending on RIN and their quantification as relative quantities and normalized relative quantities. Linear regression line analyses of the expression levels presented as relative quantities (RQs) and normalized relative quantities (NRQs) in Figure 4 were performed. Data were calculated both for samples over the whole range of RIN and only for samples with RIN > 6. Statistical differences between the slopes of RQs and NRQs, and their deviation from zero were assessed. The results have been summarized in the Tables S13 and S14 and have been described in Results.