a-live-cell-image-based-machine-learning-strategy-to-monitor

A Live-cell Image-Based Machine Learning Strategy to Monitor Pluripotent Stem Cell Differentiation

Pluripotent stem cell (PSC) technologies have been widely used in drug discovery, disease modeling, and regenerative medicine.&#160;However, available ...

Peking University

Vascular aging predisposes the elderly to the progression of many aging-related vascular disorders and leads to deterioration of cardiovascular diseases (CVD). However, the underlying mechanisms have not been clearly elucidated. Agonistic autoantibodies against angiotensin II type 1 (AT1) receptor (AT1-AAs) have been demonstrated to be pro-inflammatory and contribute to the progression of atherosclerosis. However, the association between AT1-AAs and vascular aging has not been defined. Peripheral arterial disease (PAD) is an acknowledged vascular aging-related disease. In this study, AT1-AAs were detected in the sera of patients with PAD and the positive rate was 44.44% (n=63)  17.46% in non-PAD volunteers (n=63). In addition, case-control analysis showed that AT1-AAs level was positively correlated with PAD. To reveal the causal relationship between AT1-AAs and vascular aging, an AT1-AAs-positive rat model was established by active immunization. The carotid pulse wave velocity was higher, and the aortic endothelium-dependent vasodilatation was attenuated significantly in the immunized rats. Morphological staining showed thickening of the aortic wall. Histological examination showed that levels of the senescent markers were increased in the aortic tissue, mostly located at the endothelium. In addition, purified AT1-AAs-IgGs from both the immunized rats and PAD patients induced premature senescence in cultured human umbilical vein endothelial cells. These effects were significantly blocked by the AT1 receptor blocker. Taken together, our study demonstrates that AT1-AAs contribute to the progression of vascular aging and induce EC senescence through AT1 receptor. AT1-AA is a novel biomarker of vascular aging and aging-related CVD that acts to accelerate EC senescence.

Autoantibodies against AT1 Receptor Contribute to Vascular Aging and Endothelial Cell Senescence.

Direct conversion of fibroblasts into induced cardiomyocytes (iCMs) holds promising potential to generate functional cardiomyocytes for drug development and clinical applications, especially for direct  heart regeneration by delivery of reprogramming genes into adult cardiac fibroblasts in injured hearts. For a decade, many cocktails of transcription factors have been developed to generate iCMs from fibroblasts of different tissues  and some were applied . Here, we aimed to develop genetic cocktails that induce cardiac reprogramming directly in cultured cardiac fibroblasts isolated from adult mice with myocardial infarction (MICFs), which could be more relevant to heart diseases. We found that the widely used genetic cocktail, Gata4, Mef2c, and Tbx5 (GMT) were inefficient in reprogramming cardiomyocytes from MICFs. In a whole well of a 12-well plate, less than 10 mCherry cells (<0.1%) were observed after 2 weeks of GMT infection with -reporter transgenic MICFs. By screening 22 candidate transcription factors predicted through analyzing the gene regulatory network of cardiac development, we found that five factors, GMTMS (GMT plus Myocd and Sall4), induced more iCMs expressing the cardiac structural proteins cTnT and cTnI at a frequency of about 22.5 ± 2.7% of the transduced MICFs at day 21 post infection. What is more, GMTMS induced abundant beating cardiomyocytes at day 28 post infection. Specifically, Myocd contributed mainly to inducing the expression of cardiac proteins, while Sall4 accounted for the induction of functional properties, such as contractility. RNA-seq analysis of the iCMs at day 28 post infection revealed that they were reprogrammed to adopt a cardiomyocyte-like gene expression profile. Overall, we show here that Sall4 and Myocd play important roles in cardiac reprogramming from MICFs, providing a cocktail of genetic factors that have potential for further applications in  cardiac reprogramming.

Sall4 and Myocd Empower Direct Cardiac Reprogramming From Adult Cardiac Fibroblasts After Injury.

Long-term live-cell imaging technology has emerged in the study of cell culture and development, and it is expected to elucidate the differentiation or reprogramming morphology of cells and the dynamic process of interaction between cells. There are some advantages to this technique: it is noninvasive, high-throughput, low-cost, and it can help researchers explore phenomena that are otherwise difficult to observe. Many challenges arise in the real-time process, for example, low-quality micrographs are often obtained due to unavoidable human factors or technical factors in the long-term experimental period. Moreover, some core dynamics in the developmental process are rare and fleeting in imaging observation and difficult to recapture again. Therefore, this study proposes a deep learning method for microscope cell image enhancement to reconstruct sharp images. We combine generative adversarial nets and various loss functions to make blurry images sharp again, which is much more convenient for researchers to carry out further analysis. This technology can not only make up the blurry images of critical moments of the development process through image enhancement but also allows long-term live-cell imaging to find a balance between imaging speed and image quality. Furthermore, the scalability of this technology makes the methods perform well in fluorescence image enhancement. Finally, the method is tested in long-term live-cell imaging of human-induced pluripotent stem cell-derived cardiomyocyte differentiation experiments, and it can greatly improve the image space resolution ratio.

CIEGAN: A Deep Learning Tool for Cell Image Enhancement.

The differentiation of pluripotent stem cells (PSCs) into diverse functional cell types provides a promising solution to support drug discovery, disease modeling, and regenerative medicine. However, functional cell differentiation is currently limited by the substantial line-to-line and batch-to-batch variabilities, which severely impede the progress of scientific research and the manufacturing of cell products. For instance, PSC-to-cardiomyocyte (CM) differentiation is vulnerable to inappropriate doses of CHIR99021 (CHIR) that are applied in the initial stage of mesoderm differentiation. Here, by harnessing live-cell bright-field imaging and machine learning (ML), we realize real-time cell recognition in the entire differentiation process, e.g., CMs, cardiac progenitor cells (CPCs), PSC clones, and even misdifferentiated cells. This enables non-invasive prediction of differentiation efficiency, purification of ML-recognized CMs and CPCs for reducing cell contamination, early assessment of the CHIR dose for correcting the misdifferentiation trajectory, and evaluation of initial PSC colonies for controlling the start point of differentiation, all of which provide a more invulnerable differentiation method with resistance to variability. Moreover, with the established ML models as a readout for the chemical screen, we identify a CDK8 inhibitor that can further improve the cell resistance to the overdose of CHIR. Together, this study indicates that artificial intelligence is able to guide and iteratively optimize PSC differentiation to achieve consistently high efficiency across cell lines and batches, providing a better understanding and rational modulation of the differentiation process for functional cell manufacturing in biomedical applications.

Xiaochun Yang

Peking University

A Live-cell Image-Based Machine Learning Strategy to Monitor Pluripotent Stem Cell Differentiation