Prediction of Human Induced Pluripotent Stem Cell Cardiac Differentiation Outcome by Multifactorial Process Modeling

Recent advances in artificial intelligent strategies for tissue engineering and regenerative medicine

BACKGROUND

Tissue engineering and regenerative medicine (TERM) aim to repair or replace damaged or lost tissues or organs due to accidents, diseases, or aging, by applying different sciences. For this purpose, an essential part of TERM is the designing, manufacturing, and evaluating of scaffolds, cells, tissues, and organs. Artificial intelligence (AI) or the intelligence of machines or software can be effective in all areas where computers play a role.

METHODS

The "artificial intelligence," "machine learning," "tissue engineering," "clinical evaluation," and "scaffold" keywords used for searching in various databases and articles published from 2000 to 2024 were evaluated.

RESULTS

The combination of tissue engineering and AI has created a new generation of technological advancement in the biomedical industry. Experience in TERM has been refined using advanced design and manufacturing techniques. Advances in AI, particularly deep learning, offer an opportunity to improve scientific understanding and clinical outcomes in TERM.

CONCLUSION

The findings of this research show the high potential of AI, machine learning, and robots in the selection, design, and fabrication of scaffolds, cells, tissues, or organs, and their analysis, characterization, and evaluation after their implantation. AI can be a tool to accelerate the introduction of tissue engineering products to the bedside.

HIGHLIGHTS

The capabilities of artificial intelligence (AI) can be used in different ways in all the different stages of TERM and not only solve the existing limitations, but also accelerate the processes, increase efficiency and precision, reduce costs, and complications after transplantation. ML predicts which technologies have the most efficient and easiest path to enter the market and clinic. The use of AI along with these imaging techniques can lead to the improvement of diagnostic information, the reduction of operator errors when reading images, and the improvement of image analysis (such as classification, localization, regression, and segmentation).

Chemically defined production of engineered cardiac tissue microspheres from hydrogel-encapsulated pluripotent stem cells

Chemically defined, suspension culture conditions are a key requirement in realizing clinical translation of engineered cardiac tissues (ECTs). Building on our previous work producing functional ECT microspheres through differentiation of biomaterial encapsulated human induced pluripotent stem cells (hiPSCs), here we establish the ability to use chemically defined culture conditions, including stem cell media (E8) and cardiac differentiation media (chemically defined differentiation media with three components, CDM3). A custom microfluidic cell encapsulation system was used to encapsulate hiPSCs at a range of initial cell concentrations and diameters in the hybrid biomaterial, poly(ethylene glycol)-fibrinogen (PF), for the formation of highly spherical and uniform ECT microspheres for subsequent cardiac differentiation. Initial microsphere diameter could be tightly controlled, and microspheres could be produced with an initial diameter between 400 and 800 µm. Three days after encapsulation, cardiac differentiation was initiated through small molecule modulation of Wnt signaling in CDM3. Cardiac differentiation occurred resulting in in situ ECT formation; results showed that this differentiation protocol could be used to achieve cardiomyocyte (CM) contents greater than 90%, although there was relatively high variability in CM content and yield between differentiation batches. Spontaneous contraction of ECT microspheres initiated between Days 7 and 10 of differentiation and ECT microspheres responded to electrical pacing up to 1.5 Hz. Resulting CMs had well-defined sarcomeres and the gap junction protein, connexin 43, and had appropriate temporal changes in gene expression. In summary, this study demonstrated the proof-of-concept to produce functional ECT microspheres with chemically defined media in suspension culture in combination with biomaterial support of microsphere encapsulated hiPSCs.

Advances in induced pluripotent stem cell-derived cardiac myocytes: technological breakthroughs, key discoveries and new applications

A transformation is underway in precision and patient-specific medicine. Rapid progress has been enabled by multiple new technologies including induced pluripotent stem cell-derived cardiac myocytes (iPSC-CMs). Here, we delve into these advancements and their future promise, focusing on the efficiency of reprogramming techniques, the fidelity of differentiation into the cardiac lineage, the functional characterization of the resulting cardiac myocytes, and the many applications of in silico models to understand general and patient-specific mechanisms controlling excitation-contraction coupling in health and disease. Furthermore, we explore the current and potential applications of iPSC-CMs in both research and clinical settings, underscoring the far-reaching implications of this rapidly evolving field.

Standardized production of hPSC-derived cardiomyocyte aggregates in stirred spinner flasks

A promising cell-therapy approach for heart failure aims at differentiating human pluripotent stem cells (hPSCs) into functional cardiomyocytes (CMs) in vitro to replace the disease-induced loss of patients' heart muscle cells in vivo. But many challenges remain for the routine clinical application of hPSC-derived CMs (hPSC-CMs), including good manufacturing practice (GMP)-compliant production strategies. This protocol describes the efficient generation of hPSC-CM aggregates in suspension culture, emphasizing process simplicity, robustness and GMP compliance. The strategy promotes clinical translation and other applications that require large numbers of CMs. Using a simple spinner-flask platform, this protocol is applicable to a broad range of users with general experience in handling hPSCs without extensive know-how in biotechnology. hPSCs are expanded in monolayer to generate the required cell numbers for process inoculation in suspension culture, followed by stirring-controlled formation of cell-only aggregates at a 300-ml scale. After 48 h at checkpoint (CP) 0, chemically defined cardiac differentiation is induced by WNT-pathway modulation through use of the glycogen-synthase kinase-3 inhibitor CHIR99021 (WNT agonist), which is replaced 24 h later by the chemical WNT-pathway inhibitor IWP-2. The exact application of the described process parameters is important to ensure process efficiency and robustness. After 10 d of differentiation (CP I), the production of ≥100 × 106 CMs is expected. Moreover, to 'uncouple' cell production from downstream applications, continuous maintenance of CM aggregates for up to 35 d in culture (CP II) is demonstrated without a reduction in CM content, supporting downstream logistics while potentially overcoming the requirement for cryopreservation.

The use of artificial intelligence in induced pluripotent stem cell-based technology over 10-year period: A systematic scoping review

BACKGROUND

Stem cell research, particularly in the domain of induced pluripotent stem cell (iPSC) technology, has shown significant progress. The integration of artificial intelligence (AI), especially machine learning (ML) and deep learning (DL), has played a pivotal role in refining iPSC classification, monitoring cell functionality, and conducting genetic analysis. These enhancements are broadening the applications of iPSC technology in disease modelling, drug screening, and regenerative medicine. This review aims to explore the role of AI in the advancement of iPSC research.

METHODS

In December 2023, data were collected from three electronic databases (PubMed, Web of Science, and Science Direct) to investigate the application of AI technology in iPSC processing.

RESULTS

This systematic scoping review encompassed 79 studies that met the inclusion criteria. The number of research studies in this area has increased over time, with the United States emerging as a leading contributor in this field. AI technologies have been diversely applied in iPSC technology, encompassing the classification of cell types, assessment of disease-specific phenotypes in iPSC-derived cells, and the facilitation of drug screening using iPSC. The precision of AI methodologies has improved significantly in recent years, creating a foundation for future advancements in iPSC-based technologies.

CONCLUSIONS

Our review offers insights into the role of AI in regenerative and personalized medicine, highlighting both challenges and opportunities. Although still in its early stages, AI technologies show significant promise in advancing our understanding of disease progression and development, paving the way for future clinical applications.

Wnt dose escalation during the exit from pluripotency identifies tranilast as a regulator of cardiac mesoderm

Wnt signaling is a critical determinant of cell lineage development. This study used Wnt dose-dependent induction programs to gain insights into molecular regulation of stem cell differentiation. We performed single-cell RNA sequencing of hiPSCs responding to a dose escalation protocol with Wnt agonist CHIR-99021 during the exit from pluripotency to identify cell types and genetic activity driven by Wnt stimulation. Results of activated gene sets and cell types were used to build a multiple regression model that predicts the efficiency of cardiomyocyte differentiation. Cross-referencing Wnt-associated gene expression profiles to the Connectivity Map database, we identified the small-molecule drug, tranilast. We found that tranilast synergistically activates Wnt signaling to promote cardiac lineage differentiation, which we validate by in vitro analysis of hiPSC differentiation and in vivo analysis of developing quail embryos. Our study provides an integrated workflow that links experimental datasets, prediction models, and small-molecule databases to identify drug-like compounds that control cell differentiation.

Machine learning-based classification of cardiac relaxation impairment using sarcomere length and intracellular calcium transients

Impaired relaxation of cardiomyocytes leads to diastolic dysfunction in the left ventricle. Relaxation velocity is regulated in part by intracellular calcium (Ca2+) cycling, and slower outflux of Ca2+ during diastole translates to reduced relaxation velocity of sarcomeres. Sarcomere length transient and intracellular calcium kinetics are integral parts of characterizing the relaxation behavior of the myocardium. However, a classifier tool that can separate normal cells from cells with impaired relaxation using sarcomere length transient and/or calcium kinetics remains to be developed. In this work, we employed nine different classifiers to classify normal and impaired cells, using ex-vivo measurements of sarcomere kinematics and intracellular calcium kinetics data. The cells were isolated from wild-type mice (referred to as normal) and transgenic mice expressing impaired left ventricular relaxation (referred to as impaired). We utilized sarcomere length transient data with a total of n = 126 cells (n = 60 normal cells and n = 66 impaired cells) and intracellular calcium cycling measurements with a total of n = 116 cells (n = 57 normal cells and n = 59 impaired cells) from normal and impaired cardiomyocytes as inputs to machine learning (ML) models for classification. We trained all ML classifiers with cross-validation method separately using both sets of input features, and compared their performance metrics. The performance of classifiers on test data showed that our soft voting classifier outperformed all other individual classifiers on both sets of input features, with 0.94 and 0.95 area under the receiver operating characteristic curves for sarcomere length transient and calcium transient, respectively, while multilayer perceptron achieved comparable scores of 0.93 and 0.95, respectively. However, the performance of decision tree, and extreme gradient boosting was found to be dependent on the set of input features used for training. Our findings highlight the importance of selecting appropriate input features and classifiers for the accurate classification of normal and impaired cells. Layer-wise relevance propagation (LRP) analysis demonstrated that the time to 50% contraction of the sarcomere had the highest relevance score for sarcomere length transient, whereas time to 50% decay of calcium had the highest relevance score for calcium transient input features. Despite the limited dataset, our study demonstrated satisfactory accuracy, suggesting that the algorithm can be used to classify relaxation behavior in cardiomyocytes when the potential relaxation impairment of the cells is unknown.

Recent Advances in Generation of In Vitro Cardiac Organoids

Cardiac organoids are in vitro self-organizing and three-dimensional structures composed of multiple cardiac cells (i.e., cardiomyocytes, endothelial cells, cardiac fibroblasts, etc.) with or without biological scaffolds. Since cardiac organoids recapitulate structural and functional characteristics of the native heart to a higher degree compared to the conventional two-dimensional culture systems, their applications, in combination with pluripotent stem cell technologies, are being widely expanded for the investigation of cardiogenesis, cardiac disease modeling, drug screening and development, and regenerative medicine. In this mini-review, recent advances in cardiac organoid technologies are summarized in chronological order, with a focus on the methodological points for each organoid formation. Further, the current limitations and the future perspectives in these promising systems are also discussed.

Cellular and Engineered Organoids for Cardiovascular Models

An ensemble of in vitro cardiac tissue models has been developed over the past several decades to aid our understanding of complex cardiovascular disorders using a reductionist approach. These approaches often rely on recapitulating single or multiple clinically relevant end points in a dish indicative of the cardiac pathophysiology. The possibility to generate disease-relevant and patient-specific human induced pluripotent stem cells has further leveraged the utility of the cardiac models as screening tools at a large scale. To elucidate biological mechanisms in the cardiac models, it is critical to integrate physiological cues in form of biochemical, biophysical, and electromechanical stimuli to achieve desired tissue-like maturity for a robust phenotyping. Here, we review the latest advances in the directed stem cell differentiation approaches to derive a wide gamut of cardiovascular cell types, to allow customization in cardiac model systems, and to study diseased states in multiple cell types. We also highlight the recent progress in the development of several cardiovascular models, such as cardiac organoids, microtissues, engineered heart tissues, and microphysiological systems. We further expand our discussion on defining the context of use for the selection of currently available cardiac tissue models. Last, we discuss the limitations and challenges with the current state-of-the-art cardiac models and highlight future directions.

Induced pluripotency in the context of stem cell expansion bioprocess development, optimization, and manufacturing: a roadmap to the clinic

The translation of laboratory-scale bioprocess protocols and technologies to industrial scales and the application of human induced pluripotent stem cell (hiPSC) derivatives in clinical trials globally presents optimism for the future of stem-cell products to impact healthcare. However, while many promising therapeutic approaches are being tested in pre-clinical studies, hiPSC-derived products currently account for a small fraction of active clinical trials. The complexity and volatility of hiPSCs present several bioprocessing challenges, where the goal is to generate a sufficiently large, high-quality, homogeneous population for downstream differentiation-the derivatives of which must retain functional efficacy and meet regulatory safety criteria in application. It is argued herein that one of the major challenges currently faced in improving the robustness of routine stem-cell biomanufacturing is in utilizing continuous, meaningful assessments of molecular and cellular characteristics from process to application. This includes integrating process data with biological characteristic and functional assessment data to model the interplay between variables in the search for global optimization strategies. Coupling complete datasets with relevant computational methods will contribute significantly to model development and automation in achieving process robustness. This overarching approach is thus crucially important in realizing the potential of hiPSC biomanufacturing for transformation of regenerative medicine and the healthcare industry.

The future of bone regeneration: integrating AI into tissue engineering

Tissue engineering is a branch of regenerative medicine that harnesses biomaterial and stem cell research to utilise the body's natural healing responses to regenerate tissue and organs. There remain many unanswered questions in tissue engineering, with optimal biomaterial designs still to be developed and a lack of adequate stem cell knowledge limiting successful application. Advances in artificial intelligence (AI), and deep learning specifically, offer the potential to improve both scientific understanding and clinical outcomes in regenerative medicine. With enhanced perception of how to integrate artificial intelligence into current research and clinical practice, AI offers an invaluable tool to improve patient outcome.

Machine Learning Techniques to Classify Healthy and Diseased Cardiomyocytes by Contractility Profile

Cardiomyocytes derived from human induced pluripotent stem (iPS) cells enable the study of cardiac physiology and the developmental testing of new therapeutic drugs in a human setting. In parallel, machine learning methods are being applied to biomedical science in unprecedented ways. Machine learning has been used to distinguish healthy from diseased cardiomyocytes using calcium (Ca²⁺) transient signals. Most Ca²⁺ transient signals are obtained via terminal assays that do not permit longitudinal studies, although some recently developed options can circumvent these concerns. Here, we describe the use of machine learning to identify healthy and diseased cardiomyocytes according to their contractility profiles, which are derived from brightfield videos. This noncontact, label-free approach allows for the continued cultivation of cells after they have been evaluated for use in other assays and can be readily extended to organs-on-chip. To demonstrate utility, we assessed contractility profiles of cardiomyocytes obtained from patients with Timothy Syndrome (TS), a long QT disease which can lead to fatal arrhythmias, and from healthy individuals. The videos were processed and classified using machine learning methods and their performance was evaluated according to several parameters. The trained algorithms were able to distinguish the TS cardiomyocytes from healthy controls and classify two different healthy controls. The proposed computational machine learning evaluation of human iPS cell-derived cardiomyocytes' contractility profiles has the potential to identify other genetic proarrhythmic events, screen therapeutic agents for inducing or suppressing long QT events, and predict drug-target interactions. The same approach could be readily extended to the evaluation of engineered cardiac tissues within single-tissue and multi-tissue organs-on-chip.

Cell surface markers for immunophenotyping human pluripotent stem cell-derived cardiomyocytes

Human pluripotent stem cells (hPSC) self-renew and represent a potentially unlimited source for the production of cardiomyocytes (CMs) suitable for studies of human cardiac development, drug discovery, cardiotoxicity testing, and disease modelling and for cell-based therapies. However, most cardiac differentiation protocols yield mixed cultures of atrial-, ventricular-, and pacemaker-like cells at various stages of development, as well as non-CMs. The proportions and maturation states of these cell types result from disparities among differentiation protocols and time of cultivation, as well as hPSC reprogramming inconsistencies and genetic background variations. The reproducible use of hPSC-CMs for research and therapy is therefore limited by issues of cell population heterogeneity and functional states of maturation. A validated method that overcomes issues of cell heterogeneity is immunophenotyping coupled with live cell sorting, an approach that relies on accessible surface markers restricted to the desired cell type(s). Here we review current progress in unravelling heterogeneity in hPSC-cardiac cultures and in the identification of surface markers suitable for defining cardiac identity, subtype specificity, and maturation states.