Careful selection of reference genes is required for reliable performance of RT-qPCR in human normal and cancer cell lines

Abstract

Reverse Transcription - quantitative Polymerase Chain Reaction (RT-qPCR) is a standard technique in most laboratories. The selection of reference genes is essential for data normalization and the selection of suitable reference genes remains critical. Our aim was to 1) review the literature since implementation of the MIQE guidelines in order to identify the degree of acceptance; 2) compare various algorithms in their expression stability; 3) identify a set of suitable and most reliable reference genes for a variety of human cancer cell lines. A PubMed database review was performed and publications since 2009 were selected. Twelve putative reference genes were profiled in normal and various cancer cell lines (n = 25) using 2-step RT-qPCR. Investigated reference genes were ranked according to their expression stability by five algorithms (geNorm, Normfinder, BestKeeper, comparative ΔCt, and RefFinder). Our review revealed 37 publications, with two thirds patient samples and one third cell lines. qPCR efficiency was given in 68.4% of all publications, but only 28.9% of all studies provided RNA/cDNA amount and standard curves. GeNorm and Normfinder algorithms were used in 60.5% in combination. In our selection of 25 cancer cell lines, we identified HSPCB, RRN18S, and RPS13 as the most stable expressed reference genes. In the subset of ovarian cancer cell lines, the reference genes were PPIA, RPS13 and SDHA, clearly demonstrating the necessity to select genes depending on the research focus. Moreover, a cohort of at least three suitable reference genes needs to be established in advance to the experiments, according to the guidelines. For establishing a set of reference genes for gene normalization we recommend the use of ideally three reference genes selected by at least three stability algorithms. The unfortunate lack of compliance to the MIQE guidelines reflects that these need to be further established in the research community.

Figure 1. Number of RT-qPCR publications from 2009 to April 2012.

(A). Line chart of all publications (n = 37) investigating the most stably expressed reference genes. (B) Percentage of algorithms used to identify reliable reference genes among all publications.

Figure 2. Different reverse transcription setups provided by three suppliers.

(A) Random 6 mer were used in 2 and 5, oligo dT primer in 3 and 6, and both together in 1, 4 and 7 (abscissa); Cq on ordinate shows differences among the tested reverse transcriptase conditions. (B) Coefficient of variation (CV). RT suppliers indicated by roman numerals: I) BioRad, II) Takara, and III) Bioline. X-axis with different RT primers: oligo dT (oligo), random 6 mers (random), and both (both).

Figure 3. Bar graphs showing the most stably expressed genes calculated by rank sum of the 5 algorithms applied.

(A) All investigated cell lines (n = 25), (B) colon cancer cell lines (n = 9), and (C) normal and ovarian cancer cell lines (n = 11). Numbers highlight the first three most stable reference genes in each experimental set up.

Figure 4. Correlation matrix visualizing reference genes ranked by five different stability tests (geNorm, Normfinder, BestKeeper, deltaCt and RefFinder).

Absolute value of Pearson correlation and p-value indicated by asterisks (0***, 0.01**). Bottom of the scatter plots visualizes bivariate correlation among investigated stability tests including a fitted line.