Lentiviral vector mediated thymidine kinase expression in pluripotent stem cells enables removal of tumorigenic cells

Abstract

Embryonic stem cells (ES) and induced pluripotent stem (iPS) cells represent promising tools for cell-based therapies and regenerative medicine. Nevertheless, implantation of ES cell derived differentiated cells holds the risk of teratoma formation due to residual undifferentiated cells. In order to tackle this problem, we used pluripotent stem cells consisting of ES and iPS cells of mouse genetically modified by lentiviral vectors (LVs) carrying herpes simplex virus thymidine kinase (HSV-TK) under the control of different promoters of pluripotency genes. Cells expressing TK in turn are eliminated upon administration of the prodrug ganciclovir (GCV). Our aim was to study the conditions required for a safe mechanism to clear residual undifferentiated cells but using low MOIs of lentiviruses to reduce the risk of insertional mutagenesis. Our in vitro data demonstrated that TK expression in pluripotent stem cells upon treatment with GCV led to elimination of undifferentiated cells. However, introduction of hygromycin resistance in the LV transduced ES cells followed by pre-selection with hygromycin and GCV treatment was required to abolish undifferentiated cells. Most importantly, transplantation of pre-selected ES cells that had been transduced with low MOI LV in mice resulted in no teratoma development after GCV treatment in vivo. Taken together, our data show that pre-selection of ES cells prior to in vivo application is necessary if vector integration events are minimized. The study presented here gives rise to safer use of pluripotent stem cells as promising cell sources in regenerative medicine in the future.

Figure 1. Constructs of LVs carrying TK expression cassette and analysis of NT- or OT-transduced ES and iPS cells in vitro.

(A) Constructs of LVs carrying thymidine kinase (TK) cDNA from herpes simplex virus driven by promoters of pluripotency genes Nanog (NT) or Oct-3/4 (OT). (B) ES cells were transduced with LVs (NT or OT, 300 ng of reverse transcriptase) or not transduced (WT) and further treated with 0, 10, 20, 40, 60, 80 or 100 µM GCV for 72 hours. Representative brightfield images are shown (n=3). (C) and (D) iPS cells (C) or iPS-Oct-GFP cells (D) were transduced with LVs (NT or OT, 300 ng of reverse transcriptase) or not transduced (WT) and further treated with (+) or without (-) 20 µM GCV for 72 hours. Representative brightfield images (C, D) and fluorescence images (D) are shown (n=3).

Figure 2. Analysis of mixed ES cell populations transduced with lentiviral NT or OT with low copy number.

(A) ES cells were transduced with different amounts of lentiviral NT or OT or were not transduced (WT). The copy number of LVs in mixed ES cell populations was analyzed by qPCR. Shown are the results of mixed ES cell populations carrying ^≈1.5 copy numbers per genome in average (n=3, Mean±SEM; N.S., not significant, ANOVA). As control, two transgenic mice previously analyzed by Southern Blot to have one or two integrants (data not shown), were also analyzed by qPCR. (B) ES cells were transduced with NT or OT (1.5 copy numbers per genome in average) or not transduced (WT) and treated with (+) or without (-) 20 µM GCV. Representative brightfield images are shown (n=3). (C) The untreated ES cell populations shown in (B) were differentiated as EBs with (+) or without (-) 20 µM GCV treatment. After 14 days of differentiation dissociated EBs were immunostained with Oct-3/4 (red) and Hoechst (blue) indicating Oct-3/4-positive cells (ES cells) and nucleus, respectively. Representative images are shown (n=3). (D) Percentage of Oct-3/4-positive cells on day 14 of differentiation with and without GCV treatment analyzed by manual counting of Oct-3/4-positive cells on images representatively shown in (C) using three different fields of view that were counted five times (Mean±SEM, **P<0.01, ANOVA).

Figure 3. Analysis of ES cells transduced with LVs using different promoters of pluripotency genes.

(A) In addition to NT and OT (Figure 1A) LVs carrying TK cDNA under the control of the EOS-C3 (CT) and EOS-S4 (ST) promoters were constructed. (B) The copy number of LVs in mixed ES cell populations transduced with NT, OT, CT and ST or not transduced (WT) was analyzed by qPCR (n=3, Mean±SEM, N.S., not significant, ANOVA). As control, DNAs of two transgenic mice were used, that were previously analyzed by Southern Blot to have one or two integrants. (C) TK expression on mRNA level of NT, OT, CT and ST transduced ES cells (1.5 copy numbers per genome in average) or not transduced (WT) was analyzed by qPCR and normalized to GAPDH (n=3, Mean±SEM, *P<0.05, **P<0.01, ***P<0.001 compared to ST, ANOVA). (D) Brightfield images of NT, OT, CT, ST (1.5 copy numbers per genome in average) or not transduced (WT) ES cells after treatment with (+) or without (-) 20 µM GCV for 72 hours. Representative images are shown (n=4). (E) ES cells from (D) with GCV treatment were analyzed with LDH assay as described in experimental methods section. Shown are the relative numbers of NT, OT, CT or ST transduced ES cells that survived GCV treatment as compared to untransduced (WT) ES cells (n=3, Mean±SEM; ***P<0.001, compared to WT; N.S., not significant, ANOVA).

Figure 4. Analysis of single LV-integrant NT- or OT-transduced ES cell clones in vitro.

(A) ES cells were transduced with NT or OT and picked ES cell clones carrying one integrant (NT #8, NT #11, OT #4, OT#11) or not transduced ES cells (WT) were treated with (+) or without (-) 20 µM GCV for 72 hours. Representative brightfield images are shown (n=3). (B) The untreated ES cell clones shown in (A) were differentiated as EBs with (+) or without (-) 20µM GCV. After 14 days of differentiation dissociated EBs were immunostained with Oct-3/4 (red) and Hoechst (blue) indicating Oct-3/4-positive cells (ES cells) and nuclei, respectively. Representative images are shown (n=3). (C) Percentage of Oct-3/4-positive cells of dissociated EBs on day 14 after differentiation with and without GCV treatment analyzed by manual cell counting of images shown in (B) by using one field of view that was counted five times (Mean±SEM; ***P<0.001 compared to without GCV, respectively, ANOVA)..

Figure 5. Analysis of ES cells transduced with LVs carrying a hygromycin resistance gene.

(A) Construct of LV carrying additional hygromycin resistance gene driven by PGK promoter and cDNA of TK under control of EOS-S4-promoter (STPH). (B) ES cells were transduced with STPH (1.5 copy numbers per genome in average) or not transduced (WT) and treated with (+) or without (-) 20 µM GCV for 72 hours after pre-selection with (+Hygro) or without hygromycin (-Hygro). Representative brightfield images are shown (n=3). (C) (D) and (E) Relative cell survival of untransduced ES cells (WT) (C), STPH-transduced ES cells (1.5 copy numbers per genome in average) without pre-selection (D) and STPH-transduced ES cells (1.5 copy numbers per genome in average) with pre-selection (E) with (+) or without (-) 20 µM GCV treatment (n=3, Mean±SEM; ***P<0.001 compared to without GCV treatment, respectively, Student’s t-test). Data is based on images representatively shown in (B); undifferentiated cells were manually counted using three different fields of view that were counted twice. (F) The untreated ES cell populations shown in (B) were differentiated as EBs with (+) or without (-) 20 µM GCV. After 14 days of differentiation dissociated EBs were immunostained with Oct-3/4 (red) and Hoechst (blue) indicating Oct-3/4-positive cells (ES cells) and nuclei, respectively. Representative images are shown (n=3).

Figure 6. In vivo application of STPH-transduced ES cells.

(A) Schematic illustration of in vivo procedure: 1 x 10⁶ ES cells (STPH-transduced or not transduced (WT)) were injected s.c. into hind limbs of SCID/beige mice. Saline solution (0.9% (w/v) NaCl) or GCV (20 mg/kg/day) were administrated i.p. for 12 days. (B) Relative weight of teratoma from in vivo application of hygromycin pre-selected STPH-transduced ES cells with low copy number (L (1.5 copy numbers per genome in average)) or untransduced ES cells (WT) with (+) or without (-) GCV treatment. Note, that only one out of six mice showed formation of tissue when applying STPH pre-selected cells and GCV administration (n≥4, Mean±SEM; ***P<0.001 compared to WT +GCV, ANOVA). (C) H&E stained sections of explanted teratoma emerging from injection of pre-selected (+Hygro) STPH-transduced ES cells (1.5 copy numbers per genome in average) without GCV (-GCV, upper) or with GCV treatment (+GCV, lower), demonstrating muscle, cartilage, glandular epithelium and neural tissue as indicated. Note, that only muscle tissue was detected in the single mouse that showed tissue development when applying STPH-transduced pre-selected cells and GCV treatment. (D) Relative weight of teratoma from in vivo application of STPH-transduced ES cells with high number (H (3.8 copy numbers per genome in average)) or untransduced ES cells (WT) without hygromycin pre-selection and with (+) or without (-) GCV treatment (n=5, Mean±SEM; ***P<0.001, compared to WT +GCV, ANOVA).