Integrating nonlinear analysis and machine learning for human induced pluripotent stem cell‐based drug cardiotoxicity testing

Abstract

Utilizing recent advances in human induced pluripotent stem cell (hiPSC) technology, nonlinear analysis and machine learning we can create novel tools to evaluate drug-induced cardiotoxicity on human cardiomyocytes. With cardiovascular disease remaining the leading cause of death globally it has become imperative to create effective and modern tools to test the efficacy and toxicity of drugs to combat heart disease. The calcium transient signals recorded from hiPSC-derived cardiomyocytes (hiPSC-CMs) are highly complex and dynamic with great degrees of response characteristics to various drug treatments. However, traditional linear methods often fail to capture the subtle variation in these signals generated by hiPSC-CMs.In this work, we integrated nonlinear analysis, dimensionality reduction techniques and machine learning algorithms for better classifying the contractile signals from hiPSC-CMs in response to different drug exposure. By utilizing extracted parameters from a commercially available high-throughput testing platform, we were able to distinguish the groups with drug treatment from baseline controls, determine the drug exposure relative to IC50 values, and classify the drugs by its unique cardiac responses. By incorporating nonlinear parameters computed by phase space reconstruction, we were able to improve our machine learning algorithm's ability to predict cardiotoxic levels and drug classifications. We also visualized the effects of drug treatment and dosages with dimensionality reduction techniques, t-distributed stochastic neighbor embedding (t-SNE). We have shown that integration of nonlinear analysis and artificial intelligence has proven to be a powerful tool for analyzing cardiotoxicity and classifying toxic compounds through their mechanistic action.

AI‐organoid integrated systems for biomedical studies and applications

“…Results showed that the neural network outperformed the other two models with an initial accuracy of 71.4% in drug classification, which was boosted to 80% accuracy with the addition of data preprocessing steps. In addition, t‐SNE, a dimensionality reduction technique, was used to visualize how data preprocessing can help the separation of drug effects and allow ML algorithms to detect subtle variations among different drugs 61 . In another study, the t‐SNE algorithm was used to investigate the structure–function relationships of cardiac organoids generated from different micropattern sizes.…”

“…In addition, t-SNE, a dimensionality reduction technique, was used to visualize how data preprocessing can help the separation of drug effects and allow ML algorithms to detect subtle variations among different drugs. 61 In another study, the t-SNE algorithm was used to investigate the structure-function relationships of cardiac organoids generated from different micropattern sizes. This data visualization technique allowed us to identify the correlation between pattern size and parametric functional parameters of cardiac organoids, revealing important associations.…”

A review on machine learning approaches in cardiac tissue engineering

“…In our literature review, we specifically targeted research articles that employ ML models to enhance the comprehension of hiPSC-CM behavior. We deliberately excluded studies that integrate ML into the use of hiPSC-CMs as models, like drug cardiotoxicity or disease progression (Heylman et al, 2015;Lee et al, 2017;Maddah et al, 2020;Grafton et al, 2021;Juhola et al, 2021;Kowalczewski et al, 2022;Yang et al, 2023). To assemble the cohort of research papers, a comprehensive literature search was conducted using the PubMed-NCBI database with the following search terms: Other searches with relevant key terms yielded no results; therefore, they were omitted from this list.…”

Machine learning discriminates P2X7-mediated intracellular calcium sparks in human-induced pluripotent stem cell-derived neural stem cells

“…However, its application to toxicological screening systems as a replacement for in vitro and in vivo tests remains challenging. Kowalczewski et al 15 reported that a machine-learning model can distinguish the responses of hiPSC-derived cardiomyocytes to representative arrhythmogenic agents, isoproterenol, verapamil, and cisapride, based on known calcium wave parameters. Monzel et al 16 developed a machine-learning model that can discriminate between dopaminergic neuron-specific toxin 6-hydroxydopamine-treated hiPSC-derived neuronal organoids.…”