Dataset Information

Deep learning-based predictive classification of functional subpopulations of hematopoietic stem cells and multipotent progenitors.

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.

SUBMITTER: Wang S

PROVIDER: S-EPMC10935795 | biostudies-literature | 2024 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning-based predictive classification of functional subpopulations of hematopoietic stem cells and multipotent progenitors.

Wang Shen S Han Jianzhong J Huang Jingru J Islam Khayrul K Shi Yuheng Y Zhou Yuyuan Y Kim Dongwook D Zhou Jane J Lian Zhaorui Z Liu Yaling Y Huang Jian J

Stem cell research & therapy 20240313 1

<h4>Background</h4>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.<h4>Methods</h4>In this study, we explored the feasibility of employing deep learn ...[more]

PMID: 38475857

Similar Datasets

Project description:Adult mammalian testis is a source of pluripotent stem cells. However, the lack of specific surface markers has hampered identification and tracking of the unrecognized subset of germ cells that gives rise to multipotent cells. Although embryonic-like cells can be derived from adult testis cultures after only several weeks in vitro, it is not known whether adult self-renewing spermatogonia in long-term culture can generate such stem cells as well. Here, we show that highly proliferative adult spermatogonial progenitor cells (SPCs) can be efficiently obtained by cultivation on mitotically inactivated testicular feeders containing CD34+ stromal cells. SPCs exhibit testicular repopulating activity in vivo and maintain the ability in long-term culture to give rise to multipotent adult spermatogonial-derived stem cells (MASCs). Furthermore, both SPCs and MASCs express GPR125, an orphan adhesion-type G-protein-coupled receptor. In knock-in mice bearing a GPR125-beta-galactosidase (LacZ) fusion protein under control of the native Gpr125 promoter (GPR125-LacZ), expression in the testis was detected exclusively in spermatogonia and not in differentiated germ cells. Primary GPR125-LacZ SPC lines retained GPR125 expression, underwent clonal expansion, maintained the phenotype of germline stem cells, and reconstituted spermatogenesis in busulphan-treated mice. Long-term cultures of GPR125+ SPCs (GSPCs) also converted into GPR125+ MASC colonies. GPR125+ MASCs generated derivatives of the three germ layers and contributed to chimaeric embryos, with concomitant downregulation of GPR125 during differentiation into GPR125- cells. MASCs also differentiated into contractile cardiac tissue in vitro and formed functional blood vessels in vivo. Molecular bookmarking by GPR125 in the adult mouse and, ultimately, in the human testis could enrich for a population of SPCs for derivation of GPR125+ MASCs, which may be employed for genetic manipulation, tissue regeneration and revascularization of ischaemic organs.

Dataset Information

Deep learning-based predictive classification of functional subpopulations of hematopoietic stem cells and multipotent progenitors.

Background

Methods

Results

Conclusion

Publications

Deep learning-based predictive classification of functional subpopulations of hematopoietic stem cells and multipotent progenitors.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets