Machine learning predicts putative hematopoietic stem cells within large single-cell transcriptomics data sets.
MetadataShow full item record
Hamey, F., & Gottgens, B. (2019). Machine learning predicts putative hematopoietic stem cells within large single-cell transcriptomics data sets.. Experimental hematology, 78 11-20. https://doi.org/10.1016/j.exphem.2019.08.009
Haematopoietic stem cells (HSCs) are an essential source and reservoir for normal haematopoiesis, and their function is compromised in many blood disorders. HSC research has bene tted from the recent development of single-cell molecular pro ling technologies, where single-cell RNA-sequencing (scRNA-seq) in particular has rapidly become an established method to profi le HSCs and related haematopoietic populations. The classical de nition of HSCs relies on transplantation assays, which have been used to validate HSC function for cell populations de ned by flow cytometry. Flow cytometry information for single cells however is not available for many new high-throughput scRNA-seq methods, thus highlighting an urgent need for the establishment of alternative ways to pinpoint the likely HSCs within large scRNA-seq datasets. To address this, we tested a range of machine learning approaches and developed a tool, hscScore, to score single-cell transcriptomes from murine bone marrow based on their similarity to gene expression pro files of validated HSCs. We evaluated hscScore across scRNA-seq data from di erent laboratories, which allowed us to establish a robust method that functions across di fferent technologies. To facilitate broad adoption of hscScore by the wider haematopoiesis community, we have made the trained model and example code freely available online. In summary, our method hscScore provides fast identi cation of mouse bone marrow HSCs from scRNA-seq measurements and represents a broadly useful tool for analysis of single-cell gene expression data.
Hematopoietic Stem Cells, Animals, Mice, Knockout, Mice, Gene Expression Profiling, Sequence Analysis, RNA, Transcriptome, Machine Learning
MRC, Wellcome Trust, Bloodwise, CRUK
WELLCOME TRUST (105031/D/14/Z)
Cancer Research UK (21762)
Leukaemia & Lymphoma Research (12029)
Wellcome Trust (203151/Z/16/Z)
External DOI: https://doi.org/10.1016/j.exphem.2019.08.009
This record's URL: https://www.repository.cam.ac.uk/handle/1810/296436
Attribution-NonCommercial-NoDerivatives 4.0 International
Licence URL: https://creativecommons.org/licenses/by-nc-nd/4.0/