Modeling susceptibility to drug-induced long QT with a panel of subject-specific induced pluripotent stem cells

Abstract

A large number of drugs can induce prolongation of cardiac repolarization and life-threatening cardiac arrhythmias. The prediction of this side effect is however challenging as it usually develops in some genetically predisposed individuals with normal cardiac repolarization at baseline. Here, we describe a platform based on a genetically diverse panel of induced pluripotent stem cells (iPSCs) that reproduces susceptibility to develop a cardiotoxic drug response. We generated iPSC-derived cardiomyocytes from patients presenting in vivo with extremely low or high changes in cardiac repolarization in response to a pharmacological challenge with sotalol. In vitro, the responses to sotalol were highly variable but strongly correlated to the inter-individual differences observed in vivo. Transcriptomic profiling identified dysregulation of genes (DLG2, KCNE4, PTRF, HTR2C, CAMKV) involved in downstream regulation of cardiac repolarization machinery as underlying high sensitivity to sotalol. Our findings offer novel insights for the development of iPSC-based screening assays for testing individual drug reactions.

Trial registration: ClinicalTrials.gov NCT01338441.

Keywords: arrhythmia; cardiotoxicity; human; human biology; induced pluripotent stem cells; medicine.

Figure 1.. QTcf changes following Sotalol administration in healthy volunteers.

(A) Flow chart of the clinical study. (B) Distribution of QTcf duration before (blue) and 3 hr after sotalol intake (red). (C) Distribution of delta change in QTcf showing the wide inter-individual variability in response to the same pharmacological stimulation. Subjects with the most extreme responses were selected as low sensitive (low-S) or high- sensitive (high-S) as indicated in green and red respectively. (D) Average delta change in QTcf in the two groups of selected subjects. ***p<0.001. (E) Typical ECG recordings before and after sotalol intake in a high-S subject (upper panels) and in a low-S subject (lower panels). There is one figure supplement. DOI: http://dx.doi.org/10.7554/eLife.19406.003

Figure 1—figure supplement 1.. Overview of the clinical and experimental study and role of each partner.

This translational study started with a prospective clinical study performed in a clinical investigation center near Paris, France. The objective was to identify healthy subjects with extreme responses to Sotalol 80 mg. Skin punch biopsies were performed in a total of twenty subjects, 10 with low-sensitivity and 10 with high-sensitivity to Sotalol. The fresh skin biopsies were then transferred at the Ectycell company (Romainville, France) in close vicinity of the clinical investigation center. The objective was to culture and bank human dermal fibroblasts and to derive and characterize hiPSC. iPSC clones were then anonymized before any further cardiac experiments were performed. This procedure was agreed by all partners to avoid potential biases in interpreting the recording at the cellular level. iPSCs clones were successfully generated for 17 subjects using retroviral infection and were investigated in this study. For the remaining three subjects (Patients 4, 14 and 20), iPSCs clones were secondarily generated using episomal plasmids and were thus not investigated. The 17 iPSCs clones were then transferred to the Cardiovascular Research Center at Icahn School of Medicine, New York, USA. The objective was to differentiate iPSCs into cardiac myocytes and to perform MEA recordings and drug testing. All required authorizations were obtained. DOI: http://dx.doi.org/10.7554/eLife.19406.004

Figure 2.. Expression of sarcomeric proteins and ion channels in human iPSC-CMs.

(A) Confocal microscopy imaging of Troponin T (top), alpha-actinin and connexin 43 (bottom) in single generated iPSC-CMs (from line P11015). Nuclei are stained with DAPI (Blue). (B) Gene expression of cardiac ion channel KCNH2 (encoding hERG) by quantitative PCR; Adult LV tissue is used as a positive control and the level of expression in human ESC-derived cardiomyocytes as a comparator. (C) Example of monolayer of iPSC-CMs seeded and attached on a 6-well MEA chip, each well containing nine microelectrodes (black). See also Video 1. (D) Representative field potential duration (FPD) recorded before and after application of the hERG blocker E4031 (from line P11007). There are five figure supplements. DOI: http://dx.doi.org/10.7554/eLife.19406.007

Figure 2—figure supplement 1.. Expression of exogenous and endogenous pluripotency genes.

Representative gel showing silencing of the four exogenous reprogramming transgenes (OCT3/4; KLF4; SOX2 ; c-MYC) and quantitative PCR results for endogenous pluripotent stem cell genes (OCT3/4; NANOG; SOX2) in the generated hiPSCs. DOI: http://dx.doi.org/10.7554/eLife.19406.010

Figure 2—figure supplement 2.. MEA arrays.

(A) Picture of a 6-well MEA array as used in the study. Each well contains nine micro-electrodes and a limited volume capacity allowing easier contact between cells and micro-electrodes after re-seeding and rapid response to drugs after application in a limited volume of medium. (B) Typical micro-electrodes map of the six well array. (C) Dose-curve responses to the hERG blocker E4031. Increasing concentrations of E4031 were applied as described in Materials and methods section. Individual data were plotted and a hill equation was fitted allowing estimates of EC50 for each cell lines. Results were obtained in 15 cell lines as two cell lines display no changes in FPD in response to E4031, suggesting expression of a non-functional hERG in these iPSC-CMs. For graphical purposes, cell lines from the low-S group are shown in green and from the high-S group in red. DOI: http://dx.doi.org/10.7554/eLife.19406.011

Figure 2—figure supplement 3.. Quality of FPD adjustment.

(A) Plot of adjusted FPD using the Bazett’s formula against the individual inter-beat interval. This plot shows the miss-correction achieved using the Bazett’s formula with a significant dependence of FPD to beating rate even after adjustment. (B) Plot of adjusted FPD against the individual inter-beat interval after re-estimation of the correction factor to the data set. The plot shows perfect correction with linear regression indicating the lack of influence of the beating rate on the adjusted FPD. DOI: http://dx.doi.org/10.7554/eLife.19406.012

Figure 3.. Differences in iPSC-CMs responses to Sotalol stimulation according to clinical sensitivity to Sotalol.

(A) Adjusted FPD (aFPD) measured in iPSC-CMs derived from subjects with low-sensitivity (green) vs. high-sensitivity (red) in response to increasing concentrations of sotalol. aFPD are normalized to baseline values to account for inter-lines variability in aFPD values. Two-way analysis of variance demonstrates a significant influence of sotalol concentrations (p<0.0005) and of the sensitivity group (p<0.02). *p<0.05 for post-hoc comparison between groups; high-S vs. low-S. N = 2–5 recordings per cell lines per concentrations. (B) Maximal change in aFPD observed during sotalol stimulation. (C) Proportion of observed arrhythmias after sotalol application. (D) Data plot graph showing the correlation between aFPD observed in iPSC-CMs and the DeltaQTcf observed in donors. The aFPD data are reported for sotalol 30 μM concentration. Data points are clustered in two distinct groups. Except for two lines (one line in each group), a threshold a 25% in aFPD change (dashed line) correctly discriminates cells from both groups. DOI: http://dx.doi.org/10.7554/eLife.19406.015

Figure 4.. Patch-clamp analysis of action potential (AP) in representative iPSC-CMs.

(A) Representative AP tracings of the iPSC-CMs generated from the low-S (P11009) and high-S (P11029) lines in control and sotalol-treated conditions. (B) bar chart summarizing the APD₉₀ in control and sotalol-treated conditions for the hiPSC-CMs generated from both low-S (P11009) and high-S (P11029) hiPSC cell lines (n = 5 for each condition). *p<0.05; **p<0.01, ANOVA, followed by Tukey's, sotalol-treated versus respective control without sotalol application. DOI: http://dx.doi.org/10.7554/eLife.19406.016

Figure 5.. Identification of dysregulated genes as direct neighbors of QT-associated network in high-S iPSC-CMs.

(A) Known LQTS genes were used as seed nodes (green squares) in the human interactome and five differentially expressed direct neighbors were identified (circles) (path length 1). Up-regulated genes are colored orange, down-regulated genes are in blue. (B) Relative expression of identified genes in each group. Males are represented in blue and females in red. Individual samples are represented by the same symbols in all diagrams. (C) Comparison of the log2-fold changes between the high-S and the low-S groups with the normalized counts of how often a gene (blue or orange dots) was found to be up- or down-regulated between the male and female groups. As there are more females in the high-S group and more males in the low-S groups, report of genes in the lower left or upper right quadrants indicate a gender-specific effect while the lower right and upper left quadrants argue for the lack of gender-specific effect. Except for HTR2C, dysregulation of all other candidate genes was suspected to occur independently of gender. There is one figure supplement. DOI: http://dx.doi.org/10.7554/eLife.19406.018

Figure 5—figure supplement 1.. Prediction of sex hormones-related transcription factors.

Predicted regulatory transcription factors of the identified DEGs (DLG2, KCNE4, CAMKV, PTRF, HTR2C) based on two transcription factor target databases (Chea background and Transfac) and ranked by significance. The sex-hormone related transcription factors (in orange) were ranked 16 (AR), 20 (ESR1) and 24 (ESR2) or 27 (PGR) and 180 (ESR1) while the top 10 candidates were independent of sex hormones influence (in blue). DOI: http://dx.doi.org/10.7554/eLife.19406.019

Author response image 1.

DOI: http://dx.doi.org/10.7554/eLife.19406.021