Investigating heterogeneities of live mesenchymal stromal cells using AI-based label-free imaging

Machine learning aided single cell image analysis improves understanding of morphometric heterogeneity of human mesenchymal stem cells

The multipotent stem cells of our body have been largely harnessed in biotherapeutics. However, as they are derived from multiple anatomical sources, from different tissues, human mesenchymal stem cells (hMSCs) are a heterogeneous population showing ambiguity in their in vitro behavior. Intra-clonal population heterogeneity has also been identified and pre-clinical mechanistic studies suggest that these cumulatively depreciate the therapeutic effects of hMSC transplantation. Although various biomarkers identify these specific stem cell populations, recent artificial intelligence-based methods have capitalized on the cellular morphologies of hMSCs, opening a new approach to understand their attributes. A robust and rapid platform is required to accommodate and eliminate the heterogeneity observed in the cell population, to standardize the quality of hMSC therapeutics globally. Here, we report our primary findings of morphological heterogeneity observed within and across two sources of hMSCs namely, stem cells from human exfoliated deciduous teeth (SHEDs) and human Wharton jelly mesenchymal stem cells (hWJ MSCs), using real-time single-cell images generated on immunophenotyping by imaging flow cytometry (IFC). We used the ImageJ software for identification and comparison between the two types of hMSCs using statistically significant morphometric descriptors that are biologically relevant. To expand on these insights, we have further applied deep learning methods and successfully report the development of a Convolutional Neural Network-based image classifier. In our research, we introduced a machine learning methodology to streamline the entire procedure, utilizing convolutional neural networks and transfer learning for binary classification, achieving an accuracy rate of 97.54%. We have also critically discussed the challenges, comparisons between solutions and future directions of machine learning in hMSC classification in biotherapeutics.

The optimized priming effect of FGF-1 and FGF-2 enhances preadipocyte lineage commitment in human adipose-derived mesenchymal stem cells

The cell-assisted lipotransfer technique, integrating adipose-derived mesenchymal stem cells (ADMSCs), has transformed lipofilling, enhancing fat graft viability. However, the multipotent nature of ADMSCs poses challenges. To improve safety and graft vitality and to reduce unwanted lineage differentiation, this study refines the methodology by priming ADMSCs into preadipocytes-unipotent, self-renewing cells. We explored the impact of fibroblast growth factor-1 (FGF-1), fibroblast growth factor-2 (FGF-2), and epidermal growth factor (EGF), either alone or in combination, on primary human ADMSCs during the proliferative phase. FGF-2 emerged as a robust stimulator of cell proliferation, preserving stemness markers, especially when combined with EGF. Conversely, FGF-1, while not significantly affecting cell growth, influenced cell morphology, transitioning cells to a rounded shape with reduced CD34 expression. Furthermore, co-priming with FGF-1 and FGF-2 enhanced adipogenic potential, limiting osteogenic and chondrogenic tendencies, and possibly promoting preadipocyte commitment. These preadipocytes exhibited unique features: rounded morphology, reduced CD34, decreased preadipocyte factor 1 (Pref-1), and elevated C/EBPα and PPARγ, alongside sustained stemness markers (CD73, CD90, CD105). Mechanistically, FGF-1 and FGF-2 activated key adipogenic transcription factors-C/EBPα and PPARγ-while inhibiting GATA3 and Notch3, which are adipogenesis inhibitors. These findings hold the potential to advance innovative strategies for ADMSC-mediated lipofilling procedures.

Trustworthy in silico cell labeling via ensemble-based image translation

Artificial intelligence (AI) image translation has been a valuable tool for processing image data in biological and medical research. To apply such a tool in mission-critical applications, including drug screening, toxicity study, and clinical diagnostics, it is essential to ensure that the AI prediction is trustworthy. Here, we demonstrate that an ensemble learning method can quantify the uncertainty of AI image translation. We tested the uncertainty evaluation using experimentally acquired images of mesenchymal stromal cells. We find that the ensemble method reports a prediction standard deviation that correlates with the prediction error, estimating the prediction uncertainty. We show that this uncertainty is in agreement with the prediction error and Pearson correlation coefficient. We further show that the ensemble method can detect out-of-distribution input images by reporting increased uncertainty. Altogether, these results suggest that the ensemble-estimated uncertainty can be a useful indicator for identifying erroneous AI image translations.

Morphology-Based Prediction of Proliferation and Differentiation Potencies of Porcine Muscle Stem Cells for Cultured Meat Production

Inconsistent efficiency of cell production caused by cellular quality variations has become a significant problem in the cultured meat industry. In our study, morphological information on passages 5-9 of porcine muscle stem cells (pMuSCs) from three lots was analyzed and used as input data in prediction models. Cell proliferation and differentiation potencies were measured by cell growth rate and average stained area of the myosin heavy chain. Analysis of PCA and heatmap showed that the morphological parameters could be used to discriminate the differences of passages and lots. Various morphological parameters were analyzed, which revealed that accumulating time-course information regarding morphological heterogeneity in cell populations is crucial to predicting the potencies. Based on the 36 and 60 h morphological profiles, the best proliferation potency prediction model (R2 = 0.95, RMSE = 1.1) and differentiation potency prediction model (R2 = 0.74, RMSE = 1.2) were explored. Correlation analysis demonstrated that morphological parameters selected in models are related to the quality of porcine muscle stem cells.

MSCProfiler: a single cell image processing workflow to investigate mesenchymal stem cell heterogeneity

Single cell cytometry has demonstrated plausible immuno-heterogeneity of mesenchymal stem cells (MSCs) owing to their multivariate stromal origin. To contribute successfully to next-generation stem cell therapeutics, a deeper understanding of their cellular morphology and immunophenotype is important. In this study, the authors describe MSCProfiler, an image analysis pipeline developed using CellProfiler software. This workflow can extract geometrical and texture features such as shape, size, eccentricity and entropy, along with intensity values of the surface markers from multiple single cell images obtained using imaging flow cytometry. This screening pipeline can be used to analyze geometrical and texture features of all types of MSCs across different passages hallmarked by enhanced feature extraction potential from brightfield and fluorescent images of the cells.

Stem cell-based therapy for COVID-19

While The World Health Organization (WHO) has announced that COVID-19 is no longer a public health emergency of international concern(PHEIC), the risk of reinfection and new emerging variants still makes it crucial to study and work towards the prevention of COVID-19. Stem cell and stem cell-like derivatives have shown some promising results in clinical trials and preclinical studies as an alternative treatment option for the pulmonary illnesses caused by the COVID-19 and can be used as a potential vaccine. In this review, we will systematically summarize the pathophysiological process and potential mechanisms underlying stem cell-based therapy in COVID-19, and the registered COVID-19 clinical trials, and engineered extracellular vesicle as a potential vaccine for preventing COVID-19.

Virtual Fluorescence Translation for Biological Tissue by Conditional Generative Adversarial Network

Fluorescence labeling and imaging provide an opportunity to observe the structure of biological tissues, playing a crucial role in the field of histopathology. However, when labeling and imaging biological tissues, there are still some challenges, e.g., time-consuming tissue preparation steps, expensive reagents, and signal bias due to photobleaching. To overcome these limitations, we present a deep-learning-based method for fluorescence translation of tissue sections, which is achieved by conditional generative adversarial network (cGAN). Experimental results from mouse kidney tissues demonstrate that the proposed method can predict the other types of fluorescence images from one raw fluorescence image, and implement the virtual multi-label fluorescent staining by merging the generated different fluorescence images as well. Moreover, this proposed method can also effectively reduce the time-consuming and laborious preparation in imaging processes, and further saves the cost and time.

Supplementary Information

The online version contains supplementary material available at 10.1007/s43657-023-00094-1.

Subcellular spatially resolved gene neighborhood networks in single cells

Image-based spatial omics methods such as fluorescence in situ hybridization (FISH) generate molecular profiles of single cells at single-molecule resolution. Current spatial transcriptomics methods focus on the distribution of single genes. However, the spatial proximity of RNA transcripts can play an important role in cellular function. We demonstrate a spatially resolved gene neighborhood network (spaGNN) pipeline for the analysis of subcellular gene proximity relationships. In spaGNN, machine-learning-based clustering of subcellular spatial transcriptomics data yields subcellular density classes of multiplexed transcript features. The nearest-neighbor analysis produces heterogeneous gene proximity maps in distinct subcellular regions. We illustrate the cell-type-distinguishing capability of spaGNN using multiplexed error-robust FISH data of fibroblast and U2-OS cells and sequential FISH data of mesenchymal stem cells (MSCs), revealing tissue-source-specific MSC transcriptomics and spatial distribution characteristics. Overall, the spaGNN approach expands the spatial features that can be used for cell-type classification tasks.

Phenotyping senescent mesenchymal stromal cells using AI image translation

Mesenchymal stromal cells (MSCs) offer promising potential in biomedical research, clinical therapeutics, and immunomodulatory therapies due to their ease of isolation and multipotent, immunoprivileged, and immunosuppersive properties. Extensive efforts have focused on optimizing the cell isolation and culture methods to generate scalable, therapeutically-relevant MSCs for clinical applications. However, MSC-based therapies are often hindered by cell heterogeneity and inconsistency of therapeutic function caused, in part, by MSC senescence. As such, noninvasive and molecular-based MSC characterizations play an essential role in assuring the consistency of MSC functions. Here, we demonstrated that AI image translation algorithms can effectively predict immunofluorescence images of MSC senescence markers from phase contrast images. We showed that the expression level of senescence markers including senescence-associated beta-galactosidase (SABG), p16, p21, and p38 are accurately predicted by deep-learning models for Doxorubicin-induced MSC senescence, irradiation-induced MSC senescence, and replicative MSC senescence. Our AI model distinguished the non-senescent and senescent MSC populations and simultaneously captured the cell-to-cell variability within a population. Our microscopy-based phenotyping platform can be integrated with cell culture routines making it an easily accessible tool for MSC engineering and manufacturing.

High throughput screening of mesenchymal stem cell lines using deep learning

Mesenchymal stem cells (MSCs) are increasingly used as regenerative therapies for patients in the preclinical and clinical phases of various diseases. However, the main limitations of such therapies include functional heterogeneity and the lack of appropriate quality control (QC) methods for functional screening of MSC lines; thus, clinical outcomes are inconsistent. Recently, machine learning (ML)-based methods, in conjunction with single-cell morphological profiling, have been proposed as alternatives to conventional in vitro/vivo assays that evaluate MSC functions. Such methods perform in silico analyses of MSC functions by training ML algorithms to find highly nonlinear connections between MSC functions and morphology. Although such approaches are promising, they are limited in that extensive, high-content single-cell imaging is required; moreover, manually identified morphological features cannot be generalized to other experimental settings. To address these limitations, we propose an end-to-end deep learning (DL) framework for functional screening of MSC lines using live-cell microscopic images of MSC populations. We quantitatively evaluate various convolutional neural network (CNN) models and demonstrate that our method accurately classifies in vitro MSC lines to high/low multilineage differentiating stress-enduring (MUSE) cells markers from multiple donors. A total of 6,120 cell images were obtained from 8 MSC lines, and they were classified into two groups according to MUSE cell markers analyzed by immunofluorescence staining and FACS. The optimized DenseNet121 model showed area under the curve (AUC) 0.975, accuracy 0.922, F1 0.922, sensitivity 0.905, specificity 0.942, positive predictive value 0.940, and negative predictive value 0.908. Therefore, our DL-based framework is a convenient high-throughput method that could serve as an effective QC strategy in future clinical biomanufacturing processes.

Multiple Parallel Fusion Network for Predicting Protein Subcellular Localization from Stimulated Raman Scattering (SRS) Microscopy Images in Living Cells

Stimulated Raman Scattering Microscopy (SRS) is a powerful tool for label-free detailed recognition and investigation of the cellular and subcellular structures of living cells. Determining subcellular protein localization from the cell level of SRS images is one of the basic goals of cell biology, which can not only provide useful clues for their functions and biological processes but also help to determine the priority and select the appropriate target for drug development. However, the bottleneck in predicting subcellular protein locations of SRS cell imaging lies in modeling complicated relationships concealed beneath the original cell imaging data owing to the spectral overlap information from different protein molecules. In this work, a multiple parallel fusion network, MPFnetwork, is proposed to study the subcellular locations from SRS images. This model used a multiple parallel fusion model to construct feature representations and combined multiple nonlinear decomposing algorithms as the automated subcellular detection method. Our experimental results showed that the MPFnetwork could achieve over 0.93 dice correlation between estimated and true fractions on SRS lung cancer cell datasets. In addition, we applied the MPFnetwork method to cell images for label-free prediction of several different subcellular components simultaneously, rather than using several fluorescent labels. These results open up a new method for the time-resolved study of subcellular components in different cells, especially cancer cells.

An Appearance Data-Driven Model Visualizes Cell State and Predicts Mesenchymal Stem Cell Regenerative Capacity

Mesenchymal stem cells (MSCs) are widely used in treating various diseases. However, lack of a reliable evaluation approach to characterize the potency of MSCs has dampened their clinical applications. Here, a function-oriented mathematical model is established to evaluate and predict the regenerative capacity (RC) of MSCs. Processed by exhaustive testing, the model excavates four optimal fitted indices, including nucleus roundness, nucleus/cytoplasm ratio, side-scatter height, and ERK1/2 from the given index combinations. Notably, three of them except ERK1/2 are cell appearance-associated features. The predictive power of the model is validated via screening experiments of these indices by predicting the RC of newly enrolled and chemical inhibitor-treated MSCs. Further RNA-sequencing analysis reveals that cell appearance-based indices may serve as major indicators to visualize the results of integration-weighted signals in and out of cells and reflect MSC stemness. In general, this study proposes an appearance data-driven predictive model for the RC and stemness of MSCs.

Label-free prediction of cell painting from brightfield images

Cell Painting is a high-content image-based assay applied in drug discovery to predict bioactivity, assess toxicity and understand mechanisms of action of chemical and genetic perturbations. We investigate label-free Cell Painting by predicting the five fluorescent Cell Painting channels from brightfield input. We train and validate two deep learning models with a dataset representing 17 batches, and we evaluate on batches treated with compounds from a phenotypic set. The mean Pearson correlation coefficient of the predicted images across all channels is 0.84. Without incorporating features into the model training, we achieved a mean correlation of 0.45 with ground truth features extracted using a segmentation-based feature extraction pipeline. Additionally, we identified 30 features which correlated greater than 0.8 to the ground truth. Toxicity analysis on the label-free Cell Painting resulted a sensitivity of 62.5% and specificity of 99.3% on images from unseen batches. We provide a breakdown of the feature profiles by channel and feature type to understand the potential and limitations of label-free morphological profiling. We demonstrate that label-free Cell Painting has the potential to be used for downstream analyses and could allow for repurposing imaging channels for other non-generic fluorescent stains of more targeted biological interest.

Recapitulating human myogenesis ex vivo using human pluripotent stem cells

Human pluripotent stem cells (hPSCs) provide a human model for developmental myogenesis, disease modeling and development of therapeutics. Differentiation of hPSCs into muscle stem cells has the potential to provide a cell-based therapy for many skeletal muscle wasting diseases. This review describes the current state of hPSCs towards recapitulating human myogenesis ex vivo, considerations of stem cell and progenitor cell state as well as function for future use of hPSC-derived muscle cells in regenerative medicine.