In-process evaluation of culture errors using morphology-based image analysis

Prediction of antibody production performance change in Chinese hamster ovary cells using morphological profiling

Monoclonal antibodies (mAbs) represent a significant segment of biopharmaceuticals, with the market for mAb therapeutics expected to reach $200 billion in 2021. Chinese Hamster Ovary (CHO) cells are the industry standard for large-scale mAb production owing to their adaptability and genetic engineering capabilities. However, maintaining consistent product quality is challenging, primarily because of the inherent genetic instability of CHO cells. In this study, we address the need for advanced technologies for quality monitoring of host cells in biopharmaceuticals. We highlight the limitations of traditional cell assessment techniques such as flow cytometry and propose a noninvasive, label-free image-based analysis method. By utilizing advanced image processing and machine learning, this technique aims to non-invasively and quantitatively evaluate subtle quality changes in suspension cells. The research aims to investigate the use of morphological analysis for identifying subtle alterations in mAb productivity of CHO cells, employing cells stimulated by compounds as a model for this study. Our results show that the mAb productivity of CHO cells (day 8) can be predicted only from their early morphological profile (day 3). Our study also discusses the importance of strategic methods for forecasting host cell mAb productivity using morphological profiles, as inferred from our machine learning models specialized in predictive score prediction and anomaly prediction.

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.

Morphology-based noninvasive early prediction of serial-passage potency enhances the selection of clone-derived high-potency cell bank from mesenchymal stem cells

Background

Rapidly expanding clones (RECs) are one of the single-cell-derived mesenchymal stem cell clones sorted from human bone marrow mononuclear cells (BMMCs), which possess advantageous features. The RECs exhibit long-lasting proliferation potency that allows more than 10 repeated serial passages in vitro, considerably benefiting the manufacturing process of allogenic MSC-based therapeutic products. Although RECs aid the preparation of large-variation clone libraries for a greedy selection of better-quality clones, such a selection is only possible by establishing multiple-candidate cell banks for quality comparisons. Thus, there is a high demand for a novel method that can predict “low-risk and high-potency clones” early and in a feasible manner given the excessive cost and effort required to maintain such an establishment.

Methods

LNGFR and Thy-1 co-positive cells from BMMCs were single-cell-sorted into 96-well plates, and only fast-growing clones that reached confluency in 2 weeks were picked up and passaged as RECs. Fifteen RECs were prepared as passage 3 (P3) cryostock as the primary cell bank. From this cryostock, RECs were passaged until their proliferation limitation; their serial-passage limitation numbers were labeled as serial-passage potencies. At the P1 stage, phase-contrast microscopic images were obtained over 6–90 h to identify time-course changes of 24 morphological descriptors describing cell population information. Machine learning models were constructed using the morphological descriptors for predicting serial-passage potencies. The time window and field-of-view-number effects were evaluated to identify the most efficient image data usage condition for realizing high-performance serial-passage potency models.

Results

Serial-passage test results indicated variations of 7–13-repeated serial-passage potencies within RECs. Such potency values were predicted quantitatively with high performance (RMSE < 1.0) from P1 morphological profiles using a LASSO model. The earliest and minimum effort predictions require 6–30 h with 40 FOVs and 6–90 h with 15 FOVs, respectively.

Conclusion

We successfully developed a noninvasive morphology-based machine learning model to enhance the efficiency of establishing cell banks with single-cell-derived RECs for quantitatively predicting the future serial-passage potencies of clones. Conventional methods that can make noninvasive and quantitative predictions without wasting precious cells in the early stage are lacking; the proposed method will provide a more efficient and robust cell bank establishment process for allogenic therapeutic product manufacturing.

Supplementary Information

The online version contains supplementary material available at 10.1186/s41232-022-00214-w.

Implementing robotics and artificial intelligence

An automated platform for cell culture combines robotics and artificial intelligence to optimize cell culture protocols and reliably produce specific cell types that could be used for regenerative medicine treatments.

Label-free morphological sub-population cytometry for sensitive phenotypic screening of heterogenous neural disease model cells

Label-free image analysis has several advantages with respect to the development of drug screening platforms. However, the evaluation of drug-responsive cells based exclusively on morphological information is challenging, especially in cases of morphologically heterogeneous cells or a small subset of drug-responsive cells. We developed a novel label-free cell sub-population analysis method called “in silico FOCUS (in silico analysis of featured-objects concentrated by anomaly discrimination from unit space)” to enable robust phenotypic screening of morphologically heterogeneous spinal and bulbar muscular atrophy (SBMA) model cells. This method with the anomaly discrimination concept can sensitively evaluate drug-responsive cells as morphologically anomalous cells through in silico cytometric analysis. As this algorithm requires only morphological information of control cells for training, no labeling or drug administration experiments are needed. The responses of SBMA model cells to dihydrotestosterone revealed that in silico FOCUS can identify the characteristics of a small sub-population with drug-responsive phenotypes to facilitate robust drug response profiling. The phenotype classification model confirmed with high accuracy the SBMA-rescuing effect of pioglitazone using morphological information alone. In silico FOCUS enables the evaluation of delicate quality transitions in cells that are difficult to profile experimentally, including primary cells or cells with no known markers.

Morphological heterogeneity description enabled early and parallel non-invasive prediction of T-cell proliferation inhibitory potency and growth rate for facilitating donor selection of human mesenchymal stem cells

Background

Within the extensively developed therapeutic application of mesenchymal stem cells (MSCs), allogenic immunomodulatory therapy is among the promising categories. Although donor selection is a critical early process that can maximize the production yield, determining the promising candidate is challenging owing to the lack of effective biomarkers and variations of cell sources. In this study, we developed the morphology-based non-invasive prediction models for two quality attributes, the T-cell proliferation inhibitory potency and growth rate.

Methods

Eleven lots of mixing bone marrow-derived and adipose-derived MSCs were analyzed. Their morphological profiles and growth rates were quantified by image processing by acquiring 6 h interval time-course phase-contrast microscopic image acquisition. T-cell proliferation inhibitory potency was measured by employing flow cytometry for counting the proliferation rate of peripheral blood mononuclear cells (PBMCs) co-cultured with MSCs. Subsequently, the morphological profile comprising 32 parameters describing the time-course transition of cell population distribution was used for explanatory parameters to construct T-cell proliferation inhibitory potency classification and growth rate prediction models. For constructing prediction models, the effect of machine learning methods, parameter types, and time-course window size of morphological profiles were examined to identify those providing the best performance.

Results

Unsupervised morphology-based visualization enabled the identification of anomaly lots lacking T-cell proliferation inhibitory potencies. The best performing machine learning models exhibited high performances of predictions (accuracy > 0.95 for classifying risky lots, and RMSE < 1.50 for predicting growth rate) using only the first 4 days of morphological profiles. A comparison of morphological parameter types showed that the accumulated time-course information of morphological heterogeneity in cell populations is important for predicting the potencies.

Conclusions

To enable more consistent cell manufacturing of allogenic MSC-based therapeutic products, this study indicated that early non-invasive morphology-based prediction can facilitate the lot selection process for effective cell bank establishment. It was also found that morphological heterogeneity description is important for such potency prediction. Furthermore, performances of the morphology-based prediction models trained with data consisting of origin-different MSCs demonstrated the effectiveness of sharing morphological data between different types of MSCs, thereby complementing the data limitation issue in the morphology-based quality prediction concept.

Supplementary Information

The online version contains supplementary material available at 10.1186/s41232-021-00192-5.

Rapid and sensitive mycoplasma detection system using image-based deep learning

A major concern in the clinical application of cell therapy is the manufacturing cost of cell products, which mainly depends on quality control. The mycoplasma test, an important biological test in cell therapy, takes several weeks to detect a microorganism and is extremely expensive. Furthermore, the manual detection of mycoplasma from images requires high-level expertise. We hypothesized that a mycoplasma identification program using a convolutional neural network could reduce the test time and improve sensitivity. To this end, we developed a program comprising three parts (mycoplasma detection, prediction, and cell counting) that allows users to evaluate the sample and verify infected/non-infected cells identified by the program. In experiments conducted, stained DNA images of positive and negative control using mycoplasma-infected and non-infected Vero cells, respectively, were used as training data, and the program results were compared with those of conventional methods, such as manual counting based on visual observation. The minimum detectable mycoplasma contaminations for manual counting and the proposed program were 10 and 5 CFU (colony-forming unit), respectively, and the test time for manual counting was 20 times that for the proposed program. These results suggest that the proposed system can realize a low-cost and streamlined manufacturing process for cellular products in cell-based research and clinical applications.

Cells/colony motion of oral keratinocytes determined by non-invasive and quantitative measurement using optical flow predicts epithelial regenerative capacity

Cells/colony motion determined by non-invasive, quantitative measurements using the optical flow (OF) algorithm can indicate the oral keratinocyte proliferative capacity in early-phase primary cultures. This study aimed to determine a threshold for the cells/colony motion index to detect substandard cell populations in a subsequent subculture before manufacturing a tissue-engineered oral mucosa graft and to investigate the correlation with the epithelial regenerative capacity. The distinctive proliferating pattern of first-passage [passage 1 (p1)] cells reveals the motion of p1 cells/colonies, which can be measured in a non-invasive, quantitative manner using OF with fewer full-screen imaging analyses and cell segmentations. Our results demonstrate that the motion index lower than 40 μm/h reflects cellular damages by experimental metabolic challenges although this value shall only apply in case of our culture system. Nonetheless, the motion index can be used as the threshold to determine the quality of cultured cells while it may be affected by any different culture conditions. Because the p1 cells/colony motion index is correlated with epithelial regenerative capacity, it is a reliable index for quality control of oral keratinocytes.

Bioprinting 3D human cardiac tissue chips using the pin type printer 'microscopic painting device' and analysis for cardiotoxicity

In this study, three-dimensional (3D) cardiac tissue constructed using the pin type bioprinter 'microscopic painting device' and layer-by-layer cell coating technique was confirmed to have drug responsiveness by three different analytical methods for cardiotoxicity assay. Recently, increasing attention has been focused on biofabrication to create biomimetic 3D tissue. Although various tissues can be produced in vitro, there are many issues surrounding the stability and reproducibility of the preparation of 3D tissues. Thus, although many bioprinters have been developed, none can efficiently, reproducibly and precisely produce small 3D tissues (μm-mm order) such as spheroids, which are most commonly used in drug development. The 3D cardiac tissue chips were successfully constructed with a similar number of cells as conventional 2D tissue using a pin type bioprinter, and corresponding drug-induced cardiotoxicities were obtained with known compounds that induce cardiotoxicity. The 3D cardiac tissue chips displayed uniform cell density and completely synchronized electrophysiological properties as compared to 2D tissue. The 3D tissues constructed using a pin type bioprinter as a biofabrication device would be promising tools for cardiotoxicity assay as they are capable of obtaining stable and reproducible data, which cannot be obtained by 2D tissue.

Predicting quality decay in continuously passaged mesenchymal stem cells by detecting morphological anomalies

With rapid advances in cell therapy, technologies enabling both consistency and efficiency in cell manufacturing are becoming necessary. Morphological monitoring allows practical quality maintenance in cell manufacturing facilities, but relies heavily on human skill. For more reproducible and data-driven quality evaluation, image-based morphological analysis provides multiple advantages over manual observation. Our group has investigated the performance of multiple morphological parameters obtained from time-course images to non-invasively and quantitatively predict cellular quality using machine learning algorithms. Although such morphology-based computational models succeeded in early cell quality predictions, it was difficult to introduce our approach in cell manufacturing facilities owing to data variation issues. Since manufacturing facilities have fixed their protocol to minimize anomalies as much as possible, most accumulated data are normal, and anomalies are scarce. Thus, our morphological analysis had to adapt to such practical situation where it was difficult to observe a wide range of data variations, including both normal samples and anomalies, which is typically essential to improve most machine learning models' performance. In the present study, we introduce a practical morphological analysis concept by investigating the performance of anomalous quality decay discrimination during the continuous passaging of human mesenchymal stem cells (hMSCs). Combining the visualization method and asymmetric statistic discrimination, we describe an effective morphology-based, in-process quality monitoring concept to detect quality anomalies throughout cell culture process. Our results showed that the use of morphological parameters to reflect cellular population heterogeneity can predict hMSC quality decay within 6 h after seeding.

Characterization of heterogeneous primary human cartilage-derived cell population using non-invasive live-cell phase-contrast time-lapse imaging

Reliable and reproducible cell therapy strategies to treat osteoarthritis demand an improved characterization of the cell and heterogeneous cell population resident in native cartilage tissue. Using live-cell phase-contrast time-lapse imaging (PC-TLI), this study investigates the morphological attributes and biological performance of the three primary biological objects enzymatically isolated from primary human cartilage: connective tissue progenitors (CTPs), non-progenitors (NPs) and multi-cellular structures (MCSs). The authors' results demonstrated that CTPs were smaller in size in comparison to NPs (P < 0.001). NPs remained part of the adhered cell population throughout the cell culture period. Both NPs and CTP progeny on day 8 increased in size and decreased in circularity in comparison to their counterparts on day 1, although the percent change was considerably less in CTP progeny (P < 0.001). PC-TLI analyses indicated three colony types: single-CTP-derived (29%), multiple-CTP-derived (26%) and MCS-derived (45%), with large heterogeneity with respect to cell morphology, proliferation rate and cell density. On average, clonal (CL) (P = 0.009) and MCS (P = 0.001) colonies exhibited higher cell density (cells per colony area) than multi-clonal (MC) colonies; however, it is interesting to note that the behavior of CL (less cells per colony and less colony area) and MCS (high cells per colony and high colony area) colonies was quite different. Overall effective proliferation rate (EPR) of the CTPs that formed CL colonies was higher than the EPR of CTPs that formed MC colonies (P = 0.02), most likely due to CTPs with varying EPR that formed the MC colonies. Finally, the authors demonstrated that lag time before first cell division of a CTP (early attribute) could potentially help predict its proliferation rate long-term. Quantitative morphological characterization using non-invasive PC-TLI serves as a reliable and reproducible technique to understand cell heterogeneity. Size and circularity parameters can be used to distinguish CTP from NP populations. Morphological cell and colony features can also be used to reliably and reproducibly identify CTP subpopulations with preferred proliferation and differentiation potentials in an effort to improve cell manufacturing and therapeutic outcomes.

Noninvasive measurement of cell/colony motion using image analysis methods to evaluate the proliferative capacity of oral keratinocytes as a tool for quality control in regenerative medicine

Image-based cell/colony analyses offer promising solutions to compensate for the lack of quality control (QC) tools for noninvasive monitoring of cultured cells, a regulatory challenge in regenerative medicine. Here, the feasibility of two image analysis algorithms, optical flow and normalised cross-correlation, to noninvasively measure cell/colony motion in human primary oral keratinocytes for screening the proliferative capacity of cells in the early phases of cell culture were examined. We applied our software to movies converted from 96 consecutive time-lapse phase-contrast images of an oral keratinocyte culture. After segmenting the growing colonies, two indices were calculated based on each algorithm. The correlation between each index of the colonies and their proliferative capacity was evaluated. The software was able to assess cell/colony motion noninvasively, and each index reflected the observed cell kinetics. A positive linear correlation was found between cell/colony motion and proliferative capacity, indicating that both algorithms are potential tools for QC.

Quantitative analysis of operators' flow line in the cell culture for controlled manual operation

Introduction

Although cell culture has been widely used in the life sciences, there are still many aspects of this technique that are unclear. In this study, we have focused on the manual operations in the cell culture process and try to analyze the operators’ flow line.

Methods

During a course of approximately 6 years, we obtained the operators’ flow line data from two places (three layouts) and 38 operators (93 subcultures) using two network cameras and a motion detection software (Vitracom SiteView).

Results

Our investigation succeeded in quantifying the flow line of the subculture process and analyzed the time taken to carry out the process, to travel around the workplace. For the subculture process, the total time of the process being rerated the time of the operation in the place where the main operation is performed; the total distance of travel and the counts of travel not being related to the total time of the process. Based on these results, we propose a new way of evaluating the efficiency of cell culture process in terms of time and traveling. We believe that the results of this study can guide cell culture operators in handling cells more efficiently in cell manufacturing processes.

Conclusions

The flow line analysis method suggested by us can record the operators involved and improve the efficiency and consistency of the process; it can, therefore, be introduced in cell manufacturing processes. In addition, this method only requires network cameras and motion detection software, which are inexpensive and can be set up easily.

•

The subculture process was quantified successfully irrespective of location.

•

The time of some operation correlated with the total time of subculture process.

•

The distance and the counts of travel did not correlate with total time of subculture process.

•

Establishment of a new method of evaluation of operation efficiency, based on time and travel.

•

The results of flow line analysis can be used effectively to guide operators.

Time-course colony tracking analysis for evaluating induced pluripotent stem cell culture processes

Increasing the yield and maintaining a high quality of induced pluripotent stem cells (iPSCs) is necessary for manufacturing iPSCs at the industrial scale. However, because iPSCs are delicate, it is important to evaluate their quality during processing. To examine the status of cultured iPSCs non-invasively, morphology-based iPSC colony evaluation may be an efficient technology for cellular status monitoring and analysis. In this study, we examined the effectiveness of time-course colony tracking analysis for evaluating the iPSC culture process. Particularly, we obtained detailed time-course data to evaluate the effect of the pipetting technique on cell dissociation before seeding. Although the pipetting process causes severe shear stress to cells, which affects their quality, these effects have not been quantitatively analyzed because of their complex and uncontrollable parameters. By analyzing the heterogeneity and time-course responses of individual colonies, our colony tracking analysis revealed a critically damaged population caused by pipetting stress which could not be detected in conventional bulk analysis. Moreover, by comprehensively analyzing colony tracking data, which links the time-course morphology and marker staining results with each colony, we found that colony morphology is only highly correlated with the undifferentiated marker in the final stage, with a lower correlation in the early stages. Thus, colony tracking analysis provides a way to quantify cellular morphological information when evaluating complex iPSC manufacturing processes.