Dataset Information

Morphology-based prediction of osteogenic differentiation potential of human mesenchymal stem cells.

ABSTRACT: Human bone marrow mesenchymal stem cells (hBMSCs) are widely used cell source for clinical bone regeneration. Achieving the greatest therapeutic effect is dependent on the osteogenic differentiation potential of the stem cells to be implanted. However, there are still no practical methods to characterize such potential non-invasively or previously. Monitoring cellular morphology is a practical and non-invasive approach for evaluating osteogenic potential. Unfortunately, such image-based approaches had been historically qualitative and requiring experienced interpretation. By combining the non-invasive attributes of microscopy with the latest technology allowing higher throughput and quantitative imaging metrics, we studied the applicability of morphometric features to quantitatively predict cellular osteogenic potential. We applied computational machine learning, combining cell morphology features with their corresponding biochemical osteogenic assay results, to develop prediction model of osteogenic differentiation. Using a dataset of 9,990 images automatically acquired by BioStation CT during osteogenic differentiation culture of hBMSCs, 666 morphometric features were extracted as parameters. Two commonly used osteogenic markers, alkaline phosphatase (ALP) activity and calcium deposition were measured experimentally, and used as the true biological differentiation status to validate the prediction accuracy. Using time-course morphological features throughout differentiation culture, the prediction results highly correlated with the experimentally defined differentiation marker values (R>0.89 for both marker predictions). The clinical applicability of our morphology-based prediction was further examined with two scenarios: one using only historical cell images and the other using both historical images together with the patient's own cell images to predict a new patient's cellular potential. The prediction accuracy was found to be greatly enhanced by incorporation of patients' own cell features in the modeling, indicating the practical strategy for clinical usage. Consequently, our results provide strong evidence for the feasibility of using a quantitative time series of phase-contrast cellular morphology for non-invasive cell quality prediction in regenerative medicine.

SUBMITTER: Matsuoka F

PROVIDER: S-EPMC3578868 | biostudies-literature | 2013

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Morphology-based prediction of osteogenic differentiation potential of human mesenchymal stem cells.

Matsuoka Fumiko F Takeuchi Ichiro I Agata Hideki H Kagami Hideaki H Shiono Hirofumi H Kiyota Yasujiro Y Honda Hiroyuki H Kato Ryuji R

PloS one 20130221 2

Human bone marrow mesenchymal stem cells (hBMSCs) are widely used cell source for clinical bone regeneration. Achieving the greatest therapeutic effect is dependent on the osteogenic differentiation potential of the stem cells to be implanted. However, there are still no practical methods to characterize such potential non-invasively or previously. Monitoring cellular morphology is a practical and non-invasive approach for evaluating osteogenic potential. Unfortunately, such image-based approach ...[more]

PMID: 23437049

Similar Datasets

Project description:Human mesenchymal stem cells (hMSCs) are multipotent progenitor cells with the potential to differentiate into various cell types, including osteoblasts, chondrocytes, and adipocytes. These cells have been extensively employed in the field of cell-based therapies and regenerative medicine due to their inherent attributes of self-renewal and multipotency. Traditional approaches for assessing hMSCs differentiation capacity have relied heavily on labor-intensive techniques, such as RT-PCR, immunostaining, and Western blot, to identify specific biomarkers. However, these methods are not only time-consuming and economically demanding, but also require the fixation of cells, resulting in the loss of temporal data. Consequently, there is an emerging need for a more efficient and precise approach to predict hMSCs differentiation in live cells, particularly for osteogenic and adipogenic differentiation. In response to this need, we developed innovative approaches that combine live-cell imaging with cutting-edge deep learning techniques, specifically employing a convolutional neural network (CNN) to meticulously classify osteogenic and adipogenic differentiation. Specifically, four notable pre-trained CNN models, VGG 19, Inception V3, ResNet 18, and ResNet 50, were developed and tested for identifying adipogenic and osteogenic differentiated cells based on cell morphology changes. We rigorously evaluated the performance of these four models concerning binary and multi-class classification of differentiated cells at various time intervals, focusing on pivotal metrics such as accuracy, the area under the receiver operating characteristic curve (AUC), sensitivity, precision, and F1-score. Among these four different models, ResNet 50 has proven to be the most effective choice with the highest accuracy (0.9572 for binary, 0.9474 for multi-class) and AUC (0.9958 for binary, 0.9836 for multi-class) in both multi-class and binary classification tasks. Although VGG 19 matched the accuracy of ResNet 50 in both tasks, ResNet 50 consistently outperformed it in terms of AUC, underscoring its superior effectiveness in identifying differentiated cells. Overall, our study demonstrated the capability to use a CNN approach to predict stem cell fate based on morphology changes, which will potentially provide insights for the application of cell-based therapy and advance our understanding of regenerative medicine.

Project description:Precise quantification of cellular potential of stem cells, such as human bone marrow-derived mesenchymal stem cells (hBMSCs), is important for achieving stable and effective outcomes in clinical stem cell therapy. Here, we report a method for image-based prediction of the multiple differentiation potentials of hBMSCs. This method has four major advantages: (1) the cells used for potential prediction are fully intact, and therefore directly usable for clinical applications; (2) predictions of potentials are generated before differentiation cultures are initiated; (3) prediction of multiple potentials can be provided simultaneously for each sample; and (4) predictions of potentials yield quantitative values that correlate strongly with the experimental data. Our results show that the collapse of hBMSC differentiation potentials, triggered by in vitro expansion, can be quantitatively predicted far in advance by predicting multiple potentials, multi-lineage differentiation potentials (osteogenic, adipogenic, and chondrogenic) and population doubling potential using morphological features apparent during the first 4 days of expansion culture. In order to understand how such morphological features can be effective for advance predictions, we measured gene-expression profiles of the same early undifferentiated cells. Both senescence-related genes (p16 and p21) and cytoskeleton-related genes (PTK2, CD146, and CD49) already correlated to the decrease of potentials at this stage. To objectively compare the performance of morphology and gene expression for such early prediction, we tested a range of models using various combinations of features. Such comparison of predictive performances revealed that morphological features performed better overall than gene-expression profiles, balancing the predictive accuracy with the effort required for model construction. This benchmark list of various prediction models not only identifies the best morphological feature conversion method for objective potential prediction, but should also allow clinicians to choose the most practical morphology-based prediction method for their own purposes.

Project description:Mesenchymal stem cells (MSC) are multipotent stem cells that can differentiate into multiple cell types, including osteoblasts, chondrocytes, and adipocytes. Osteoblast differentiation is reduced during osteoporosis development, resulting in reduced bone formation. Further, MSC isolated from different donors possess distinct osteogenic capacity. In this study, we used single-cell multiomic analysis to profile the transcriptome and epigenome of MSC from four healthy donors. Data were obtained from ~1300 to 1600 cells for each donor. These cells were clustered into four groups, indicating that MSC from different donors have distinct chromatin accessible regulatory elements for regulating gene expression. To investigate the mechanism by which MSC undergo osteogenic differentiation, we used the chromatin accessibility data from the single-cell multiome data to identify individual-specific enhancer-promoter pairs and evaluated the expression levels and activities of the transcriptional regulators. The MSC from four donors showed distinct differentiation potential into osteoblasts. MSC of donor 1 showed the largest average motif activities, indicating that MSC from donor 1 was most likely to differentiate into osteoblasts. The results of our validation experiments were consistent with the bioinformatics prediction. We also tested the enrichment of genome-wide association study (GWAS) signals of several musculoskeletal disease traits in the patient-specific chromatin accessible regions identified in the single-cell multiome data, including osteoporosis, osteopenia, and osteoarthritis. We found that osteoarthritis-associated variants were only enriched in the regions identified from donor 4. In contrast, osteoporosis and osteopenia variants were enriched in regions from donor 1 and least enriched in donor 4. Since osteoporosis and osteopenia are related to the density of bone cells, the enrichment of variants from these traits should be correlated with the osteogenic potential of MSC. In summary, this study provides large-scale data to link regulatory elements with their target genes to study the regulatory relationships during the differentiation of mesenchymal stem cells and provide a deeper insight into the gene regulatory mechanism.

Dataset Information

Morphology-based prediction of osteogenic differentiation potential of human mesenchymal stem cells.

Publications

Morphology-based prediction of osteogenic differentiation potential of human mesenchymal stem cells.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets