A deep learning algorithm to translate and classify cardiac electrophysiology.

The development of induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) has been a critical in vitro advance in the study of patient-specific physiology, pathophysiology, and pharmacology. We designed a new deep learning multitask network approach intended to address the low throughput, high variability, and immature phenotype of the iPSC-CM platform. The rationale for combining translation and classification tasks is because the most likely application of the deep learning technology we describe here is to translate iPSC-CMs following application of a perturbation. The deep learning network was trained using simulated action potential (AP) data and applied to classify cells into the drug-free and drugged categories and to predict the impact of electrophysiological perturbation across the continuum of aging from the immature iPSC-CMs to the adult ventricular myocytes. The phase of the AP extremely sensitive to perturbation due to a steep rise of the membrane resistance was found to contain the key information required for successful network multitasking. We also demonstrated successful translation of both experimental and simulated iPSC-CM AP data validating our network by prediction of experimental drug-induced effects on adult cardiomyocyte APs by the latter.

The inhibitory effect of shakuyakukanzoto on K+ current in H9c2 cells.

Shakuyakukanzoto (shao-yao-gan-cao-tang) is a commonly used Chinese traditional herbal medicine for the treatment of acute pain with muscle cramp. However, its mechanism of action is unclear. We previously reported that a low concentration of Kanzo (licorice) and isoliquiritigenin, a component of licorice, inhibited the potassium (K(+)) current in H9c2 cells. Therefore, in the present study, we examined the effects of Shakuyakukanzoto, Shakuyaku or Kanzo on the K(+) current (IKur) in H9c2 cells. Shakuyakukanzoto inhibited IKur in a concentration-dependent manner. The half-maximal concentration of Shakuyakukanzoto was approximately 1.3 mg/mL and the Hill coefficient was 1.2. The order of potency of inhibiting IKur was Kanzo>Shakuyakukanzoto>Shakuyaku. Glycyrrhizin, a major component of licorice, had no inhibitory effect on IKur. A small interfering RNA experiment indicated that IKur was most likely to be Kv2.1 in H9c2 cells. Our results suggest that Shakuyakukanzoto may normalize intracellular and extracellular K(+) balance by inhibiting IKur and reducing K(+) efflux, while the Na(+)-K(+) pump promotes K(+) influx into myofibers. Consequently, excess K(+) may be reduced from external space of myofibers. This may be a part of the Shakuyakukanzoto mechanism for improving muscle pain.

Inhibitory effects of isoliquiritigenin and licorice extract on voltage-dependent K(+) currents in H9c2 cells.

The effect of isoliquiritigenin (ISL), a component of licorice, on the voltage-dependent, ultra-rapidly activating delayed-rectifier K(+) current (IKur) was examined in H9c2 cells, a cell-line derived from rat cardiac myoblasts. IKur was recorded using the whole-cell patch clamp method with a pipette solution containing 140 mM K(+). Depolarizing voltage pulses of 200-ms duration were given with 10-mV steps every 10 s from -40 mV holding potential. ISL inhibited IKur in a concentration-dependent manner. The median inhibitory concentration (IC(50)) of ISL was approximately 0.11 microM and the Hill coefficient was 0.71. Using CHO cells expressing Kv1.5 IKur channels, ISL also inhibited Kv1.5 IKur, but less potently than the IKur current in H9c2 cells. Furthermore, in H9c2 cells, the licorice extract itself inhibited IKur in a manner similar to ISL. We conclude that ISL, one component of licorice, is a potent inhibitor of K(+) channels, which specifically in H9c2 cells could be Kv2.1, and that this inhibition may be involved in various pharmacological effects of licorice.