Supervised Machine Learning for Classification of the Electrophysiological Effects of Chronotropic Drugs on Human Induced Pluripotent Stem Cell-Derived Cardiomyocytes

Using induced pluripotent stem cells for drug discovery in arrhythmias

INTRODUCTION

Arrhythmias are disturbances in the normal rhythm of the heart and account for significant cardiovascular morbidity and mortality worldwide. Historically, preclinical research has been anchored in animal models, though physiological differences between these models and humans have limited their clinical translation. The discovery of human induced pluripotent stem cells (iPSC) and subsequent differentiation into cardiomyocyte has led to the development of new in vitro models of arrhythmias with the hope of a new pathway for both exploration of pathogenic variants and novel therapeutic discovery.

AREAS COVERED

The authors describe the latest two-dimensional in vitro models of arrhythmias, several examples of the use of these models in drug development, and the role of gene editing when modeling diseases. They conclude by discussing the use of three-dimensional models in the study of arrythmias and the integration of computational technologies and machine learning with experimental technologies.

EXPERT OPINION

Human iPSC-derived cardiomyocytes models have significant potential to augment disease modeling, drug discovery, and toxicity studies in preclinical development. While there is initial success with modeling arrhythmias, the field is still in its nascency and requires advances in maturation, cellular diversity, and readouts to emulate arrhythmias more accurately.

Design optimization of geometrically confined cardiac organoids enabled by machine learning techniques

Stem cell organoids are powerful models for studying organ development, disease modeling, drug screening, and regenerative medicine applications. The convergence of organoid technology, tissue engineering, and artificial intelligence (AI) could potentially enhance our understanding of the design principles for organoid engineering. In this study, we utilized micropatterning techniques to create a designer library of 230 cardiac organoids with 7 geometric designs. We employed manifold learning techniques to analyze single organoid heterogeneity based on 10 physiological parameters. We clustered and refined the cardiac organoids based on their functional similarity using unsupervised machine learning approaches, thus elucidating unique functionalities associated with geometric designs. We also highlighted the critical role of calcium transient rising time in distinguishing organoids based on geometric patterns and clustering results. This integration of organoid engineering and machine learning enhances our understanding of structure-function relationships in cardiac organoids, paving the way for more controlled and optimized organoid design.

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.

BeatProfiler: Multimodal In Vitro Analysis of Cardiac Function Enables Machine Learning Classification of Diseases and Drugs

Goal: Contractile response and calcium handling are central to understanding cardiac function and physiology, yet existing methods of analysis to quantify these metrics are often time-consuming, prone to mistakes, or require specialized equipment/license. We developed BeatProfiler, a suite of cardiac analysis tools designed to quantify contractile function, calcium handling, and force generation for multiple in vitro cardiac models and apply downstream machine learning methods for deep phenotyping and classification. Methods: We first validate BeatProfiler's accuracy, robustness, and speed by benchmarking against existing tools with a fixed dataset. We further confirm its ability to robustly characterize disease and dose-dependent drug response. We then demonstrate that the data acquired by our automatic acquisition pipeline can be further harnessed for machine learning (ML) analysis to phenotype a disease model of restrictive cardiomyopathy and profile cardioactive drug functional response. To accurately classify between these biological signals, we apply feature-based ML and deep learning models (temporal convolutional-bidirectional long short-term memory model or TCN-BiLSTM). Results: Benchmarking against existing tools revealed that BeatProfiler detected and analyzed contraction and calcium signals better than existing tools through improved sensitivity in low signal data, reduction in false positives, and analysis speed increase by 7 to 50-fold. Of signals accurately detected by published methods (PMs), BeatProfiler's extracted features showed high correlations to PMs, confirming that it is reliable and consistent with PMs. The features extracted by BeatProfiler classified restrictive cardiomyopathy cardiomyocytes from isogenic healthy controls with 98% accuracy and identified relax90 as a top distinguishing feature in congruence with previous findings. We also show that our TCN-BiLSTM model was able to classify drug-free control and 4 cardiac drugs with different mechanisms of action at 96% accuracy. We further apply Grad-CAM on our convolution-based models to identify signature regions of perturbations by these drugs in calcium signals. Conclusions: We anticipate that the capabilities of BeatProfiler will help advance in vitro studies in cardiac biology through rapid phenotyping, revealing mechanisms underlying cardiac health and disease, and enabling objective classification of cardiac disease and responses to drugs.

AI-organoid integrated systems for biomedical studies and applications

In this review, we explore the growing role of artificial intelligence (AI) in advancing the biomedical applications of human pluripotent stem cell (hPSC)-derived organoids. Stem cell-derived organoids, these miniature organ replicas, have become essential tools for disease modeling, drug discovery, and regenerative medicine. However, analyzing the vast and intricate datasets generated from these organoids can be inefficient and error-prone. AI techniques offer a promising solution to efficiently extract insights and make predictions from diverse data types generated from microscopy images, transcriptomics, metabolomics, and proteomics. This review offers a brief overview of organoid characterization and fundamental concepts in AI while focusing on a comprehensive exploration of AI applications in organoid-based disease modeling and drug evaluation. It provides insights into the future possibilities of AI in enhancing the quality control of organoid fabrication, label-free organoid recognition, and three-dimensional image reconstruction of complex organoid structures. This review presents the challenges and potential solutions in AI-organoid integration, focusing on the establishment of reliable AI model decision-making processes and the standardization of organoid research.

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.

Intersection of stem cell biology and engineering towards next generation in vitro models of human fibrosis

Human fibrotic diseases constitute a major health problem worldwide. Fibrosis involves significant etiological heterogeneity and encompasses a wide spectrum of diseases affecting various organs. To date, many fibrosis targeted therapeutic agents failed due to inadequate efficacy and poor prognosis. In order to dissect disease mechanisms and develop therapeutic solutions for fibrosis patients, in vitro disease models have gone a long way in terms of platform development. The introduction of engineered organ-on-a-chip platforms has brought a revolutionary dimension to the current fibrosis studies and discovery of anti-fibrotic therapeutics. Advances in human induced pluripotent stem cells and tissue engineering technologies are enabling significant progress in this field. Some of the most recent breakthroughs and emerging challenges are discussed, with an emphasis on engineering strategies for platform design, development, and application of machine learning on these models for anti-fibrotic drug discovery. In this review, we discuss engineered designs to model fibrosis and how biosensor and machine learning technologies combine to facilitate mechanistic studies of fibrosis and pre-clinical drug testing.

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

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.

Induced Pluripotent Stem Cell-Based Drug Screening by Use of Artificial Intelligence

Induced pluripotent stem cells (iPSCs) are terminally differentiated somatic cells that differentiate into various cell types. iPSCs are expected to be used for disease modeling and for developing novel treatments because differentiated cells from iPSCs can recapitulate the cellular pathology of patients with genetic mutations. However, a barrier to using iPSCs for comprehensive drug screening is the difficulty of evaluating their pathophysiology. Recently, the accuracy of image analysis has dramatically improved with the development of artificial intelligence (AI) technology. In the field of cell biology, it has become possible to estimate cell types and states by examining cellular morphology obtained from simple microscopic images. AI can evaluate disease-specific phenotypes of iPS-derived cells from label-free microscopic images; thus, AI can be utilized for disease-specific drug screening using iPSCs. In addition to image analysis, various AI-based methods can be applied to drug development, including phenotype prediction by analyzing genomic data and virtual screening by analyzing structural formulas and protein-protein interactions of compounds. In the future, combining AI methods may rapidly accelerate drug discovery using iPSCs. In this review, we explain the details of AI technology and the application of AI for iPSC-based drug screening.

Data analytics for cardiac diseases

In the present research we tackled the classification of seven genetic cardiac diseases and control subjects by using an extensive set of machine learning algorithms with their variations from simple K-nearest neighbor searching method to support vector machines. The research was based on calcium transient signals measured from induced pluripotent stem cell-derived cardiomyocytes. All in all, 55 different machine learning alternatives were used to model eight classes by applying the principle of 10-fold crossvalidation with the peak data of 1626 signals. The best classification accuracy of approximately 69% was given by random forests, which can be seen high enough here to show machine learning to be potential for the differentiation of the eight disease classes.

Moving Towards Induced Pluripotent Stem Cell-based Therapies with Artificial Intelligence and Machine Learning

The advent of induced pluripotent stem cell (iPSC) technology, which allows to transform one cell type into another, holds the promise to produce therapeutic cells and organs on demand. Realization of this objective is contingent on the ability to demonstrate quality and safety of the cellular product for its intended use. Bottlenecks and backlogs to the clinical use of iPSCs have been fully outlined and a need has emerged for safer and standardized protocols to trigger cell reprogramming and functional differentiation. Amidst great challenges, in particular associated with lengthy culture time and laborious cell characterization, a demand for faster and more accurate methods for the validation of cell identity and function at different stages of the iPSC manufacturing process has risen. Artificial intelligence-based methods are proving helpful for these complex tasks and might revolutionize the way iPSCs are managed to create surrogate cells and organs. Here, we briefly review recent progress in artificial intelligence approaches for evaluation of iPSCs and their derivatives in experimental studies.

On computational classification of genetic cardiac diseases applying iPSC cardiomyocytes

BACKGROUND

Cardiomyocytes differentiated from human induced pluripotent stem cells (iPSC-CMs) can be used to study genetic cardiac diseases. In patients these diseases are manifested e.g. with impaired contractility and fatal cardiac arrhythmias, and both of these can be due to abnormal calcium transients in cardiomyocytes. Here we classify different genetic cardiac diseases using Ca²⁺ transient data and different machine learning algorithms.

METHODS

By studying calcium cycling of disease-specific iPSC-CMs and by using calcium transients measured from these cells it is possible to classify diseases from each other and also from healthy controls by applying machine learning computation on the basis of peak attributes detected from calcium transient signals.

RESULTS

In the current research we extend our previous study having Ca-transient data from four different genetic diseases by adding data from two additional diseases (dilated cardiomyopathy and long QT Syndrome 2). We also study, in the light of the current data, possible differences and relations when machine learning modelling and classification accuracies were computed by using either leave-one-out test or 10-fold cross-validation.

CONCLUSIONS

Despite more complex classification tasks compared to our earlier research and having more different genetic cardiac diseases in the analysis, it is still possible to attain good disease classification results. As excepted, leave-one-out test and 10-fold cross-validation achieved virtually equal results.

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.

How to Apply Supervised Machine Learning Tools to MS Imaging Files: Case Study with Cancer Spheroids Undergoing Treatment with the Monoclonal Antibody Cetuximab

As the field of mass spectrometry imaging continues to grow, so too do its needs for optimal methods of data analysis. One general need in image analysis is the ability to classify the underlying regions within an image, as healthy or diseased, for example. Classification, as a general problem, is often best accomplished by supervised machine learning strategies; unfortunately, conducting supervised machine learning on MS imaging files is not typically done by mass spectrometrists because a high degree of specialized knowledge is needed. To address this problem, we developed a fully open-source approach that facilitates supervised machine learning on MS imaging files, and we demonstrated its implementation on sets of cancer spheroids that either had or had not undergone chemotherapy treatment. These supervised machine learning studies demonstrated that metabolic changes induced by the monoclonal antibody, Cetuximab, are detectable but modest at 24 h, and by 72 h, the drug induces a larger and more diverse metabolic response.

Analysis of Drug Effects on iPSC Cardiomyocytes with Machine Learning

Patient-specific induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) offer an attractive experimental platform to investigate cardiac diseases and therapeutic outcome. In this study, iPSC-CMs were utilized to study their calcium transient signals and drug effects by means of machine learning, a central part of artificial intelligence. Drug effects were assessed in six iPSC-lines carrying different mutations causing catecholaminergic polymorphic ventricular tachycardia (CPVT), a highly malignant inherited arrhythmogenic disorder. The antiarrhythmic effect of dantrolene, an inhibitor of sarcoplasmic calcium release, was studied in iPSC-CMs after adrenaline, an adrenergic agonist, stimulation by machine learning analysis of calcium transient signals. First, beats of transient signals were identified with our peak recognition algorithm previously developed. Then 12 peak variables were computed for every identified peak of a signal and by means of this data signals were classified into different classes corresponding to those affected by adrenaline or, thereafter, affected by a drug, dantrolene. The best classification accuracy was approximately 79% indicating that machine learning methods can be utilized in analysis of iPSC-CM drug effects. In the future, data analysis of iPSC-CM drug effects together with machine learning methods can create a very valuable and efficient platform to individualize medication in addition to drug screening and cardiotoxicity studies.

Development of a Human iPSC Cardiomyocyte-Based Scoring System for Cardiac Hazard Identification in Early Drug Safety De-risking

Human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) have emerged as a promising cardiac safety platform, demonstrated by numerous validation studies using drugs with known cardiac adverse effects in humans. However, the challenge remains to implement hiPSC-CMs into cardiac de-risking of new chemical entities (NCEs) during preclinical drug development. Here, we used the calcium transient screening assay in hiPSC-CMs to develop a hazard score system for cardiac electrical liabilities. Tolerance interval calculations and evaluation of different classes of cardio-active drugs enabled us to develop a weighted scoring matrix. This approach allowed the translation of various pharmacological effects in hiPSC-CMs into a single hazard label (no, low, high, or very high hazard). Evaluation of 587 internal NCEs and good translation to ex vivo and in vivo models for a subset of these NCEs highlight the value of the cardiac hazard scoring in facilitating the selection of compounds during early drug safety screening.

•

Scoring system identifies different degrees of cardiac hazard

•

Can be applied within R&D to cardiac safety screening of NCEs

•

Controls and reference drugs are essential for development of scoring matrix

•

Analysis can be applied to other in vitro drug safety assays

Imaging, Visualization, and Computation in Developmental Biology

Embryonic development is highly complex and dynamic, requiring the coordination of numerous molecular and cellular events at precise times and places. Advances in imaging technology have made it possible to follow developmental processes at cellular, tissue, and organ levels over time as they take place in the intact embryo. Parallel innovations of in vivo probes permit imaging to report on molecular, physiological, and anatomical events of embryogenesis, but the resulting multidimensional data sets pose significant challenges for extracting knowledge. In this review, we discuss recent and emerging advances in imaging technologies, in vivo labeling, and data processing that offer the greatest potential for jointly deciphering the intricate cellular dynamics and the underlying molecular mechanisms. Our discussion of the emerging area of “image-omics” highlights both the challenges of data analysis and the promise of more fully embracing computation and data science for rapidly advancing our understanding of biology.

The application of convolutional neural network to stem cell biology

Induced pluripotent stem cells (iPSC) are one the most prominent innovations of medical research in the last few decades. iPSCs can be easily generated from human somatic cells and have several potential uses in regenerative medicine, disease modeling, drug screening, and precision medicine. However, further innovation is still required to realize their full potential. Machine learning is an algorithm that learns from large datasets for pattern formation and classification. Deep learning, a form of machine learning, uses a multilayered neural network that mimics human neural circuit structure. Deep neural networks can automatically extract features from an image, although classical machine learning methods still require feature extraction by a human expert. Deep learning technology has developed recently; in particular, the accuracy of an image classification task by using a convolutional neural network (CNN) has exceeded that of humans since 2015. CNN is now used to address several tasks including medical issues. We believe that CNN would also have a great impact on the research of stem cell biology. iPSCs are utilized after their differentiation to specific cells, which are characterized by molecular techniques such as immunostaining or lineage tracing. Each cell shows a characteristic morphology; thus, a morphology-based identification system of cell type by CNN would be an alternative technique. The development of CNN enables the automation of identifying cell types from phase contrast microscope images without molecular labeling, which will be applied to several researches and medical science. Image classification is a strong field among deep learning tasks, and several medical tasks will be solved by deep learning-based programs in the future.

Anticancer Drug Affects Metabolomic Profiles in Multicellular Spheroids: Studies Using Mass Spectrometry Imaging Combined with Machine Learning

Multicellular spheroids (hereinafter referred to as spheroids) are 3D biological models. The metabolomic profiles inside spheroids provide crucial information reflecting the molecular phenotypes and microenvironment of cells. To study the influence of an anticancer drug on the spatially resolved metabolites, spheroids were cultured using HCT-116 colorectal cancer cells, treated with the anticancer drug Irinotecan under a series of time- and concentration-dependent conditions. The Single-probe mass spectrometry imaging (MSI) technique was utilized to conduct the experiments. The MSI data were analyzed using advanced data analysis methods to efficiently extract metabolomic information. Multivariate curve resolution alternating least square (MCR-ALS) was used to decompose each MS image into different components with grouped species. To improve the efficiency of data analysis, both supervised (Random Forest) and unsupervised (cluster large applications (CLARA)) machine learning (ML) methods were employed to cluster MS images according to their metabolomic features. Our results indicate that anticancer drug significantly affected the abundances of a variety of metabolites in different regions of spheroids. This integrated experiment and data analysis approach can facilitate the studies of metabolites in different types of 3D tumor models and tissues and potentially benefit the drug discovery, therapeutic resistance, and other biological research fields.

Detection of genetic cardiac diseases by Ca2+ transient profiles using machine learning methods

Human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) have revolutionized cardiovascular research. Abnormalities in Ca2+ transients have been evident in many cardiac disease models. We have shown earlier that, by exploiting computational machine learning methods, normal Ca2+ transients corresponding to healthy CMs can be distinguished from diseased CMs with abnormal transients. Here our aim was to study whether it is possible to separate different genetic cardiac diseases (CPVT, LQT, HCM) on the basis of Ca2+ transients using machine learning methods. Classification accuracies of up to 87% were obtained for these three diseases, indicating that Ca2+ transients are disease-specific. By including healthy controls in the classifications, the best classification accuracy obtained was still high: approximately 79%. In conclusion, we demonstrate as the proof of principle that the computational machine learning methodology appears to be a powerful means to accurately categorize iPSC-CMs and could provide effective methods for diagnostic purposes in the future.

Uninterrupted monitoring of drug effects in human-induced pluripotent stem cell-derived cardiomyocytes with bioluminescence Ca2+ microscopy

Objective

Cardiomyocytes derived from human-induced pluripotent stem cells are a powerful platform for high-throughput drug screening in vitro. However, current modalities for drug testing, such as electrophysiology and fluorescence imaging have inherent drawbacks. To circumvent these problems, we report the development of a bioluminescent Ca²⁺ indicator GmNL(Ca²⁺), and its application in a customized microscope for high-throughput drug screening.

Results

GmNL(Ca²⁺) gives a 140% signal change with Ca²⁺, and can image drug-induced changes of Ca²⁺ dynamics in cultured cells. Since bioluminescence requires application of a chemical substrate, which is consumed over ~ 30 min we made a dedicated microscope with automated drug dispensing inside a light-tight box, to control drug addition. To overcome thermal instability of the luminescent substrate, or small molecule, dual climate control enables distinct temperature settings in the drug reservoir and the biological sample. By combining GmNL(Ca²⁺) with this adaptation, we could image spontaneous Ca²⁺ transients in cultured cardiomyocytes and phenotype their response to well-known drugs without accessing the sample directly. In addition, the bioluminescent strategy demonstrates minimal perturbation of contractile parameters and long-term observation attributable to lack of phototoxicity and photobleaching. Overall, bioluminescence may enable more accurate drug screening in a high-throughput manner.

Electronic supplementary material

The online version of this article (10.1186/s13104-018-3421-7) contains supplementary material, which is available to authorized users.

Automated Deep Learning-Based System to Identify Endothelial Cells Derived from Induced Pluripotent Stem Cells

Deep learning technology is rapidly advancing and is now used to solve complex problems. Here, we used deep learning in convolutional neural networks to establish an automated method to identify endothelial cells derived from induced pluripotent stem cells (iPSCs), without the need for immunostaining or lineage tracing. Networks were trained to predict whether phase-contrast images contain endothelial cells based on morphology only. Predictions were validated by comparison to immunofluorescence staining for CD31, a marker of endothelial cells. Method parameters were then automatically and iteratively optimized to increase prediction accuracy. We found that prediction accuracy was correlated with network depth and pixel size of images to be analyzed. Finally, K-fold cross-validation confirmed that optimized convolutional neural networks can identify endothelial cells with high performance, based only on morphology.

•

Neural networks were trained to spot endothelial cells on phase-contrast images

•

Performance was correlated with network depth and pixel size of training images

•

Optimized networks identify endothelial cells with high accuracy

Towards enhanced metabolomic data analysis of mass spectrometry image: Multivariate Curve Resolution and Machine Learning

Large amounts of data are generally produced from mass spectrometry imaging (MSI) experiments in obtaining the molecular and spatial information of biological samples. Traditionally, MS images are constructed using manually selected ions, and it is very challenging to comprehensively analyze MSI results due to their large data sizes and highly complex data structures. To overcome these barriers, it is obligatory to develop advanced data analysis approaches to handle the increasingly large MSI data. In the current study, we focused on the method development of using Multivariate Curve Resolution (MCR) and Machine Learning (ML) approaches. We aimed to effectively extract the essential information present in the large and complex MSI data and enhance the metabolomic data analysis of biological tissues. Multivariate Curve Resolution-Alternating Least Squares (MCR-ALS) algorithm was used to obtain major patterns of spatial distribution and grouped metabolites with the same spatial distribution patterns. In addition, both supervised and unsupervised ML methods were established to analyze the MSI data. In the supervised ML approach, Random Forest method was selected, and the model was trained using the selected datasets based on the distribution pattern obtained from MCR-ALS analyses. In the unsupervised ML approach, both DBSCAN (Density-based Spatial Clustering of Applications with Noise) and CLARA (Clustering Large Applications) were applied to cluster the MSI datasets. It is worth noting that similar patterns of spatial distribution were discovered through MSI data analysis using MCR-ALS, supervised ML, and unsupervised ML. Our protocols of data analysis can be applied to process the data acquired using many other types of MSI techniques, and to extract the overall features present in MSI results that are intractable using traditional data analysis approaches.

Automated detection and analysis of depolarization events in human cardiomyocytes using MaDEC

Optical imaging-based methods for assessing the membrane electrophysiology of in vitro human cardiac cells allow for non-invasive temporal assessment of the effect of drugs and other stimuli. Automated methods for detecting and analyzing the depolarization events (DEs) in image-based data allow quantitative assessment of these different treatments. In this study, we use 2-photon microscopy of fluorescent voltage-sensitive dyes (VSDs) to capture the membrane voltage of actively beating human induced pluripotent stem cell-derived cardiomyocytes (hiPS-CMs). We built a custom and freely available Matlab software, called MaDEC, to detect, quantify, and compare DEs of hiPS-CMs treated with the β-adrenergic drugs, propranolol and isoproterenol. The efficacy of our software is quantified by comparing detection results against manual DE detection by expert analysts, and comparing DE analysis results to known drug-induced electrophysiological effects. The software accurately detected DEs with true positive rates of 98-100% and false positive rates of 1-2%, at signal-to-noise ratios (SNRs) of 5 and above. The MaDEC software was also able to distinguish control DEs from drug-treated DEs both immediately as well as 10min after drug administration.