Search

Hematopoietic stem and progenitor cells (HSPCs) develop in distinct waves at various anatomical sites during embryonic development. The in vitro differentiation of human pluripotent stem cells (hPSCs) recapitulates some of these processes; however, it has proven difficult to generate functional hematopoietic stem cells (HSCs). To define the dynamics and heterogeneity of HSPCs that can be generated in vitro from hPSCs, we explored single-cell RNA sequencing (scRNAseq) in combination with single-cell protein expression analysis. Bioinformatics analyses and functional validation defined the transcriptomes of naïve progenitors and erythroid-, megakaryocyte-, and leukocyte-committed progenitors, and we identified CD44, CD326, ICAM2/CD9, and CD18, respectively, as markers of these progenitors. Using an artificial neural network that we trained on scRNAseq derived from human fetal liver, we identified a wide range of hPSC-derived HSPCs phenotypes, including a small group classified as HSCs. This transient HSC-like population decreased as differentiation proceeded, and was completely missing in the data set that had been generated using cells selected on the basis of CD43 expression. By comparing the single-cell transcriptome of in vitro-generated HSC-like cells with those generated within the fetal liver, we identified transcription factors and molecular pathways that can be explored in the future to improve the in vitro production of HSCs., (© 2020 by The American Society of Hematology.)

Changes in stem cell activity may underpin aging. However, these changes are not completely understood. Here, we combined single-cell profiling with machine learning and in vivo functional studies to explore how hematopoietic stem cell (HSC) divisions patterns evolve with age. We first trained an artificial neural network (ANN) to accurately identify cell types in the hematopoietic hierarchy and predict their age from single-cell gene-expression patterns. We then used this ANN to compare identities of daughter cells immediately after HSC divisions and found that the self-renewal ability of individual HSCs declines with age. Furthermore, while HSC cell divisions are deterministic and intrinsically regulated in young and old age, they are variable and niche sensitive in mid-life. These results indicate that the balance between intrinsic and extrinsic regulation of stem cell activity alters substantially with age and help explain why stem cell numbers increase through life, yet regenerative potency declines., Competing Interests: Declaration of Interests The authors declare no competing interests., (Copyright © 2020 Elsevier Inc. All rights reserved.)

Biomedical research often involves conducting experiments on model organisms in the anticipation that the biology learnt will transfer to humans. Previous comparative studies of mouse and human tissues were limited by the use of bulk-cell material. Here we show that transfer learning-the branch of machine learning that concerns passing information from one domain to another-can be used to efficiently map bone marrow biology between species, using data obtained from single-cell RNA sequencing. We first trained a multiclass logistic regression model to recognize different cell types in mouse bone marrow achieving equivalent performance to more complex artificial neural networks. Furthermore, it was able to identify individual human bone marrow cells with 83% overall accuracy. However, some human cell types were not easily identified, indicating important differences in biology. When re-training the mouse classifier using data from human, less than 10 human cells of a given type were needed to accurately learn its representation. In some cases, human cell identities could be inferred directly from the mouse classifier via zero-shot learning. These results show how simple machine learning models can be used to reconstruct complex biology from limited data, with broad implications for biomedical research.