Machine learning-assisted high-content analysis of pluripotent stem cell-derived embryos in vitro

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.

Automated, High-Throughput Phenotypic Screening and Analysis Platform to Study Pre- and Post-Implantation Morphogenesis in Stem Cell-Derived Embryo-Like Structures

Combining high-throughput generation and high-content imaging of embryo models will enable large-scale screening assays in the fields of (embryo) toxicity, drug development, embryogenesis, and reproductive medicine. This study shows the continuous culture and in situ (i.e., in microwell) imaging-based readout of a 3D stem cell-based model of peri-implantation epiblast (Epi)/extraembryonic endoderm (XEn) development with an expanded pro-amniotic cavity (PAC) (E3.5 E5.5), namely XEn/EPiCs. Automated image analysis and supervised machine learning permit the identification of embryonic morphogenesis, tissue compartmentalization, cell differentiation, and consecutive classification. Screens with signaling pathway modulators at different time windows provide spatiotemporal information on their phenotypic effect on developmental processes leading to the formation of XEn/EPiCs. Exposure of the biological model in the microwell platform to pathway modulators at two time windows, namely 0-72 h and 48-120 h, show that Wnt and Fgf/MAPK pathway modulators affect Epi differentiation and its polarization, while modulation of BMP and Tgfβ/Nodal pathway affects XEn specification and epithelialization. Further, their collective role is identified in the timing of the formation and expansion of PAC. The newly developed, scalable culture and analysis platform, thereby, provides a unique opportunity to quantitatively and systematically study effects of pathway modulators on early embryonic development.

Spectroscopic techniques for monitoring stem cell and organoid proliferation in 3D environments for therapeutic development

Spectroscopic techniques for monitoring stem cell and organoid proliferation have gained significant attention in therapeutic development. Spectroscopic techniques such as fluorescence, Raman spectroscopy, and infrared spectroscopy offer noninvasive and real-time monitoring of biochemical and biophysical changes that occur during stem cell and organoid proliferation. These techniques provide valuable insight into the underlying mechanisms of action of potential therapeutic agents, allowing for improved drug discovery and screening. This review highlights the importance of spectroscopic monitoring of stem cell and organoid proliferation and its potential impact on therapeutic development. Furthermore, this review discusses recent advances in spectroscopic techniques and their applications in stem cell and organoid research. Overall, this review emphasizes the importance of spectroscopic techniques as valuable tools for studying stem cell and organoid proliferation and their potential to revolutionize therapeutic development in the future.

A comparison of machine learning approaches for the quantification of microglial cells in the brain of mice, rats and non-human primates

Microglial cells are brain-specific macrophages that swiftly react to disruptive events in the brain. Microglial activation leads to specific modifications, including proliferation, morphological changes, migration to the site of insult, and changes in gene expression profiles. A change in inflammatory status has been linked to many neurodegenerative diseases such as Parkinson's disease and Alzheimer's disease. For this reason, the investigation and quantification of microglial cells is essential for better understanding their role in disease progression as well as for evaluating the cytocompatibility of novel therapeutic approaches for such conditions. In the following study we implemented a machine learning-based approach for the fast and automatized quantification of microglial cells; this tool was compared with manual quantification (ground truth), and with alternative free-ware such as the threshold-based ImageJ and the machine learning-based Ilastik. We first trained the algorithms on brain tissue obtained from rats and non-human primate immunohistochemically labelled for microglia. Subsequently we validated the accuracy of the trained algorithms in a preclinical rodent model of Parkinson's disease and demonstrated the robustness of the algorithms on tissue obtained from mice, as well as from images provided by three collaborating laboratories. Our results indicate that machine learning algorithms can detect and quantify microglial cells in all the three mammalian species in a precise manner, equipotent to the one observed following manual counting. Using this tool, we were able to detect and quantify small changes between the hemispheres, suggesting the power and reliability of the algorithm. Such a tool will be very useful for investigation of microglial response in disease development, as well as in the investigation of compatible novel therapeutics targeting the brain. As all network weights and labelled training data are made available, together with our step-by-step user guide, we anticipate that many laboratories will implement machine learning-based quantification of microglial cells in their research.

Deep learning models will shape the future of stem cell research

Our ability to understand and control stem cell biology is being augmented by developments on two fronts, our ability to collect more data describing cell state and our capability to comprehend these data using deep learning models. Here we consider the impact deep learning will have in the future of stem cell research. We explore the importance of generating data suitable for these methods, the requirement for close collaboration between experimental and computational researchers, and the challenges we face to do this fairly and effectively. Achieving this will ensure that the resulting deep learning models are biologically meaningful and computationally tractable.

Artificial-Intelligence-Based Imaging Analysis of Stem Cells: A Systematic Scoping Review

Simple Summary

Lately, investigations of artificial intelligence as an assisting tool for analyzing and identifying stem cells have increased. In this systematic scoping review, we aimed to identify and map the available artificial-intelligence-based techniques for imaging analysis, the characterization of stem cell differentiation, and trans-differentiation pathways. After an extensive search for the literature following a structured methodology, we included 27 studies in our systematic scoping review that we extracted the relevant data from. Based on the results of the included studies, artificial intelligence has the potential to serve as an assisting tool in stem cell imaging. However, it is still considered relatively new and under maturation. The goal of our review is to guide and help researchers while planning for future investigations.

Abstract

This systematic scoping review aims to map and identify the available artificial-intelligence-based techniques for imaging analysis, the characterization of stem cell differentiation, and trans-differentiation pathways. On the ninth of March 2022, data were collected from five electronic databases (PubMed, Medline, Web of Science, Cochrane, and Scopus) and manual citation searching; all data were gathered in Zotero 5.0. A total of 4422 articles were collected after deduplication; only twenty-seven studies were included in this systematic scoping review after a two-phase screening against inclusion criteria by two independent reviewers. The amount of research in this field is significantly increasing over the years. While the current state of artificial intelligence (AI) can tackle a multitude of medical problems, the consensus amongst researchers remains that AI still falls short in multiple ways that investigators should examine, ranging from the quality of images used in training sets and appropriate sample size, as well as the unexpected events that may occur which the algorithm cannot predict.

The role of BMP4 signaling in trophoblast emergence from pluripotency

The Bone Morphogenetic Protein (BMP) signaling pathway has established roles in early embryonic morphogenesis, particularly in the epiblast. More recently, however, it has also been implicated in development of extraembryonic lineages, including trophectoderm (TE), in both mouse and human. In this review, we will provide an overview of this signaling pathway, with a focus on BMP4, and its role in emergence and development of TE in both early mouse and human embryogenesis. Subsequently, we will build on these in vivo data and discuss the utility of BMP4-based protocols for in vitro conversion of primed vs. naïve pluripotent stem cells (PSC) into trophoblast, and specifically into trophoblast stem cells (TSC). PSC-derived TSC could provide an abundant, reproducible, and ethically acceptable source of cells for modeling placental development.

Archetypal Architecture Construction, Patterning, and Scaling Invariance in a 3D Embryoid Body Differentiation Model

Self-organized patterning and architecture construction studying is a priority goal for fundamental developmental and stem cell biology. To study the spatiotemporal patterning of pluripotent stem cells of different origins, we developed a three-dimensional embryoid body (EB) differentiation model quantifying volumetric parameters and investigated how the EB architecture formation, patterning, and scaling depend on the proliferation, cavitation, and differentiation dynamics, external environmental factors, and cell numbers. We identified three similar spatiotemporal patterns in the EB architectures, regardless of cell origin, which constitute the EB archetype and mimick the pre-gastrulation embryonic patterns. We found that the EB patterning depends strongly on cellular positional information, culture media factor/morphogen content, and free diffusion from the external environment and between EB cell layers. However, the EB archetype formation is independent of the EB size and initial cell numbers forming EBs; therefore, it is capable of scaling invariance and patterning regulation. Our findings indicate that the underlying principles of reaction-diffusion and positional information concepts can serve as the basis for EB architecture construction, patterning, and scaling. Thus, the 3D EB differentiation model represents a highly reproducible and reliable platform for experimental and theoretical research on developmental and stem cell biology issues.

YY1 safeguard multidimensional epigenetic landscape associated with extended pluripotency

Although extended pluripotent stem cells (EPSCs) have the potential to form both embryonic and extraembryonic lineages, how their transcriptional regulatory mechanism differs from that of embryonic stem cells (ESCs) remains unclear. Here, we discovered that YY1 binds to specific open chromatin regions in EPSCs. Yy1 depletion in EPSCs leads to a gene expression pattern more similar to that of ESCs than control EPSCs. Moreover, Yy1 depletion triggers a series of epigenetic crosstalk activities, including changes in DNA methylation, histone modifications and high-order chromatin structures. Yy1 depletion in EPSCs disrupts the enhancer-promoter (EP) interactions of EPSC-specific genes, including Dnmt3l. Yy1 loss results in DNA hypomethylation and dramatically reduces the enrichment of H3K4me3 and H3K27ac on the promoters of EPSC-specific genes by upregulating the expression of Kdm5c and Hdac6 through facilitating the formation of CCCTC-binding factor (CTCF)-mediated EP interactions surrounding their loci. Furthermore, single-cell RNA sequencing (scRNA-seq) experiments revealed that YY1 is required for the derivation of extraembryonic endoderm (XEN)-like cells from EPSCs in vitro. Together, this study reveals that YY1 functions as a key regulator of multidimensional epigenetic crosstalk associated with extended pluripotency.

High content drug screening of primary cardiomyocytes based on microfluidics and real-time ultra-large-scale high-resolution imaging

High content screening (HCS) plays an important role in biological applications and drug development. Existing techniques fail to simultaneously meet multiple needs of throughput, efficiency in sample and chemical consumption, and real-time imaging of a large view at high resolution. Leveraging advances in microfluidics and imaging technology, we setup a new paradigm of large-scale, high-content drug screening solutions for rapid biological processes, like cardiotoxicity. The designed microfluidic chips enable 10 types of drugs each with 5 concentrations to be assayed simultaneously. The imaging system has 30 Hz video rate for a centimeter filed-of-view at 0.8 μm resolution. Using the HCS system, we assayed 12 small molecules through their effects on the Ca²⁺ ion signal of cardiomyocytes. Experimental results demonstrated the unparalleled capability of the system in revealing the spatiotemporal patterns of Ca²⁺ imaging of cardiomyocytes, and validated the cardiotoxicity of certain molecules. We envision that this new HCS paradigm and cutting-edge platform offer the most advanced alternative to well-plate based methods.

Machine learning-assisted imaging analysis of a human epiblast model

The human embryo is a complex structure that emerges and develops as a result of cell-level decisions guided by both intrinsic genetic programs and cell-cell interactions. Given limited accessibility and associated ethical constraints of human embryonic tissue samples, researchers have turned to the use of human stem cells to generate embryo models to study specific embryogenic developmental steps. However, to study complex self-organizing developmental events using embryo models, there is a need for computational and imaging tools for detailed characterization of cell-level dynamics at the single cell level. In this work, we obtained live cell imaging data from a human pluripotent stem cell (hPSC)-based epiblast model that can recapitulate the lumenal epiblast cyst formation soon after implantation of the human blastocyst. By processing imaging data with a Python pipeline that incorporates both cell tracking and event recognition with the use of a CNN-LSTM machine learning model, we obtained detailed temporal information of changes in cell state and neighborhood during the dynamic growth and morphogenesis of lumenal hPSC cysts. The use of this tool combined with reporter lines for cell types of interest will drive future mechanistic studies of hPSC fate specification in embryo models and will advance our understanding of how cell-level decisions lead to global organization and emergent phenomena. Insight, innovation, integration: Human pluripotent stem cells (hPSCs) have been successfully used to model and understand cellular events that take place during human embryogenesis. Understanding how cell-cell and cell-environment interactions guide cell actions within a hPSC-based embryo model is a key step in elucidating the mechanisms driving system-level embryonic patterning and growth. In this work, we present a robust video analysis pipeline that incorporates the use of machine learning methods to fully characterize the process of hPSC self-organization into lumenal cysts to mimic the lumenal epiblast cyst formation soon after implantation of the human blastocyst. This pipeline will be a useful tool for understanding cellular mechanisms underlying key embryogenic events in embryo models.

Complex Organ Construction from Human Pluripotent Stem Cells for Biological Research and Disease Modeling with New Emerging Techniques

Human pluripotent stem cells (hPSCs) are grouped into two cell types; embryonic stem cells (hESCs) and induced pluripotent stem cells (hiPSCs). hESCs have provided multiple powerful platforms to study human biology, including human development and diseases; however, there were difficulties in the establishment of hESCs from human embryo and concerns over its ethical issues. The discovery of hiPSCs has expanded to various applications in no time because hiPSCs had already overcome these problems. Many hPSC-based studies have been performed using two-dimensional monocellular culture methods at the cellular level. However, in many physiological and pathophysiological conditions, intra- and inter-organ interactions play an essential role, which has hampered the establishment of an appropriate study model. Therefore, the application of recently developed technologies, such as three-dimensional organoids, bioengineering, and organ-on-a-chip technology, has great potential for constructing multicellular tissues, generating the functional organs from hPSCs, and recapitulating complex tissue functions for better biological research and disease modeling. Moreover, emerging techniques, such as single-cell transcriptomics, spatial transcriptomics, and artificial intelligence (AI) allowed for a denser and more precise analysis of such heterogeneous and complex tissues. Here, we review the applications of hPSCs to construct complex organs and discuss further prospects of disease modeling and drug discovery based on these PSC-derived organs.

Autonomy in the Development of Stem Cell-Derived Embryoids: Sprouting Blastocyst-Like Cysts, and Ethical Implications

The experimental production of complex structures resembling mammalian embryos (e.g., blastoids, gastruloids) from pluripotent stem cells in vitro has become a booming research field. Since some of these embryoid models appear to reach a degree of complexity that may come close to viability, a broad discussion has set in with the aim to arrive at a consensus on the ethical implications with regard to acceptability of the use of this technology with human cells. The present text focuses on aspects of the gain of organismic wholeness of such stem cell-derived constructs, and of autonomy of self-organization, raised by recent reports on blastocyst-like cysts spontaneously budding in mouse stem cell cultures, and by previous reports on likewise spontaneous formation of gastrulating embryonic disc-like structures in primate models. Mechanisms of pattern (axis) formation in early embryogenesis are discussed in the context of self-organization of stem cell clusters. It is concluded that ethical aspects of development of organismic wholeness in the formation of embryoids need to receive more attention in the present discussions about new legal regulations in this field.