Search

Abstract Background Hematopoietic stem cells (HSCs) and multipotent progenitors (MPPs) play a pivotal role in maintaining lifelong hematopoiesis. The distinction between stem cells and other progenitors, as well as the assessment of their functions, has long been a central focus in stem cell research. In recent years, deep learning has emerged as a powerful tool for cell image analysis and classification/prediction. Methods In this study, we explored the feasibility of employing deep learning techniques to differentiate murine HSCs and MPPs based solely on their morphology, as observed through light microscopy (DIC) images. Results After rigorous training and validation using extensive image datasets, we successfully developed a three-class classifier, referred to as the LSM model, capable of reliably distinguishing long-term HSCs, short-term HSCs, and MPPs. The LSM model extracts intrinsic morphological features unique to different cell types, irrespective of the methods used for cell identification and isolation, such as surface markers or intracellular GFP markers. Furthermore, employing the same deep learning framework, we created a two-class classifier that effectively discriminates between aged HSCs and young HSCs. This discovery is particularly significant as both cell types share identical surface markers yet serve distinct functions. This classifier holds the potential to offer a novel, rapid, and efficient means of assessing the functional states of HSCs, thus obviating the need for time-consuming transplantation experiments. Conclusion Our study represents the pioneering use of deep learning to differentiate HSCs and MPPs under steady-state conditions. This novel and robust deep learning-based platform will provide a basis for the future development of a new generation stem cell identification and separation system. It may also provide new insight into the molecular mechanisms underlying stem cell self-renewal.

Abstract Background Deciphering molecular mechanisms underlying the division of hematopoietic stem cells (HSCs) and malignant precursors would improve our understanding of the basis of stem cell-fate decisions and oncogenic transformation. Methods Using a novel reporter of hematopoietic precursor, Evi1-GFP, we tracked the division of hematopoietic precursors in culture in real time. Results First, we confirmed that Evi1-GFP is a faithful reporter of HSC activity and identified three dividing patterns of HSCs: symmetric renewal, symmetric differentiation, and asymmetric division. Moreover, we found that the cytokine and growth factor combination (STIF) promotes symmetric renewal, whereas OP9 stromal cells balance symmetric renewal and differentiation of HSCs ex vivo. Interestingly, we found that Tet2 knockout HSCs underwent more symmetric differentiation in culture compared with the wild-type control. Intriguingly, OP9 stromal cells reverse the phenotype of Tet2 knockout HSCs ex vivo. Furthermore, we demonstrated that Tet2 –/– ;Flt3ITD acute myeloid leukemia (AML) precursors primarily underwent symmetric renewal divisions in culture. Mechanistically, we demonstrated that inhibiting DNA methylation can reverse the aberrant division phenotypes of Tet2 –/– and Tet2 –/– ;FLT3ITD precursors, suggesting that abnormal DNA methylation plays an important role in controlling (pre-)leukemic precursor fate decision ex vivo. Conclusions Our study exploited a new system to explore the molecular mechanisms of the regulation of benign and malignant hematopoietic precursor division ex vivo. The knowledge learned from these studies will provide new insights into the molecular mechanisms of HSC fate decision and leukemogenesis.