Prediction of inotropic effect based on calcium transients in human iPSC-derived cardiomyocytes and machine learning.

Functional changes to cardiomyocytes are undesirable during drug discovery and identifying the inotropic effects of compounds is hence necessary to decrease the risk of cardiovascular adverse effects in the clinic. Recently, approaches leveraging calcium transients in human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) have been developed to detect contractility changes, induced by a variety of mechanisms early during drug discovery projects. Although these approaches have been able to provide some predictive ability, we hypothesised that using additional waveform parameters could offer improved insights, as well as predictivity. In this study, we derived 25 parameters from each calcium transient waveform and developed a modified Random Forest method to predict the inotropic effects of the compounds. In total annotated data for 48 compounds were available for modelling, out of which 31 were inotropes. The results show that the Random Forest model with a modified purity criterion performed slightly better than an unmodified algorithm in terms of the Area Under the Curve, giving values of 0.84 vs 0.81 in a cross-validation, and outperformed the ToxCast Pipeline model, for which the highest value was 0.76 when using the best-performing parameter, PW10. Our study hence demonstrates that more advanced parameters derived from waveforms, in combination with additional machine learning methods, provide improved predictivity of cardiovascular risk associated with inotropic effects.

Strengthening cardiac therapy pipelines using human pluripotent stem cell-derived cardiomyocytes.

Advances in hiPSC isolation and reprogramming and hPSC-CM differentiation have prompted their therapeutic application and utilization for evaluating potential cardiovascular safety liabilities. In this perspective, we showcase key efforts toward the large-scale production of hiPSC-CMs, implementation of hiPSC-CMs in industry settings, and recent clinical applications of this technology. The key observations are a need for traceable gender and ethnically diverse hiPSC lines, approaches to reduce cost of scale-up, accessible clinical trial datasets, and transparent guidelines surrounding the safety and efficacy of hiPSC-based therapies.

Discovery and SAR Study of Boronic Acid-Based Selective PDE3B Inhibitors from a Novel DNA-Encoded Library.

Human genetic evidence shows that PDE3B is associated with metabolic and dyslipidemia phenotypes. A number of PDE3 family selective inhibitors have been approved by the FDA for various indications; however, given the undesirable proarrhythmic effects in the heart, selectivity for PDE3B inhibition over closely related family members (such as PDE3A; 48% identity) is a critical consideration for development of PDE3B therapeutics. Selectivity for PDE3B over PDE3A may be achieved in a variety of ways, including properties intrinsic to the compound or tissue-selective targeting. The high (>95%) active site homology between PDE3A and B represents a massive obstacle for obtaining selectivity at the active site; however, utilization of libraries with high molecular diversity in high throughput screens may uncover selective chemical matter. Herein, we employed a DNA-encoded library screen to identify PDE3B-selective inhibitors and identified potent and selective boronic acid compounds bound at the active site.

Deriving waveform parameters from calcium transients in human iPSC-derived cardiomyocytes to predict cardiac activity with machine learning.

Human induced pluripotent stem cell-derived cardiomyocytes have been established to detect dynamic calcium transients by fast kinetic fluorescence assays that provide insights into specific aspects of clinical cardiac activity. However, the precise derivation and use of waveform parameters to predict cardiac activity merit deeper investigation. In this study, we derived, evaluated, and applied 38 waveform parameters in a novel Python framework, including (among others) peak frequency, peak amplitude, peak widths, and a novel parameter, shoulder-tail ratio. We then trained a random forest model to predict cardiac activity based on the 25 parameters selected by correlation analysis. The area under the curve (AUC) obtained for leave-one-compound-out cross-validation was 0.86, thereby replicating the predictions of conventional methods and outperforming fingerprint-based methods by a large margin. This work demonstrates that machine learning is able to automate the assessment of cardiovascular liability from waveform data, reducing any risk of user-to-user variability and bias.