Popular Vote (popV) model for automated cell type annotation of single-cell RNA-seq data. We provide here pretrained models for plug-in use in your own analysis. Follow our tutorial to learn how to use the model for cell type annotation.
Model description
Tabula Sapiens is a benchmark, first-draft human cell atlas of over 1.1M cells from 28 organs of 24 normal human subjects. This work is the product of the Tabula Sapiens Consortium. Taking the organs from the same individual controls for genetic background, age, environment, and epigenetic effects, and allows detailed analysis and comparison of cell types that are shared between tissues.
Link to CELLxGENE: Link to the data in the CELLxGENE browser for interactive exploration of the data and download of the source data.
Training Code URL: Not provided by uploader.
Metrics
We provide here accuracies for each of the experts and the ensemble model. The validation set accuracies are computed on a 10% random subset of the data that was not used for training.
| Cell Type | N cells | svm | xgboost | Consensus Prediction |
|---|---|---|---|---|
| macrophage | 0 | 0.00 | 0.00 | 0.00 |
| pulmonary alveolar type 2 cell | 0 | 0.00 | 0.00 | 0.00 |
| basal cell | 0 | 0.00 | 0.00 | 0.00 |
| non-classical monocyte | 0 | 0.00 | 0.00 | 0.00 |
| capillary endothelial cell | 0 | 0.00 | 0.00 | 0.00 |
| club cell | 0 | 0.00 | 0.00 | 0.00 |
| classical monocyte | 0 | 0.00 | 0.00 | 0.00 |
| basophil | 0 | 0.00 | 0.00 | 0.00 |
| CD4-positive, alpha-beta T cell | 0 | 0.00 | 0.00 | 0.00 |
| respiratory goblet cell | 0 | 0.00 | 0.00 | 0.00 |
| lung ciliated cell | 0 | 0.00 | 0.00 | 0.00 |
| vein endothelial cell | 0 | 0.00 | 0.00 | 0.00 |
| lung microvascular endothelial cell | 0 | 0.00 | 0.00 | 0.00 |
| CD8-positive, alpha-beta T cell | 0 | 0.00 | 0.00 | 0.00 |
| fibroblast | 0 | 0.00 | 0.00 | 0.00 |
| intermediate monocyte | 0 | 0.00 | 0.00 | 0.00 |
| adventitial cell | 0 | 0.00 | 0.00 | 0.00 |
| endothelial cell of artery | 0 | 0.00 | 0.00 | 0.00 |
| pulmonary alveolar type 1 cell | 0 | 0.00 | 0.00 | 0.00 |
| neutrophil | 0 | 0.00 | 0.00 | 0.00 |
| dendritic cell | 0 | 0.00 | 0.00 | 0.00 |
| pericyte | 0 | 0.00 | 0.00 | 0.00 |
| effector CD8-positive, alpha-beta T cell | 0 | 0.00 | 0.00 | 0.00 |
| effector CD4-positive, alpha-beta T cell | 0 | 0.00 | 0.00 | 0.00 |
| bronchial smooth muscle cell | 0 | 0.00 | 0.00 | 0.00 |
| plasma cell | 0 | 0.00 | 0.00 | 0.00 |
| smooth muscle cell | 0 | 0.00 | 0.00 | 0.00 |
| endothelial cell of lymphatic vessel | 0 | 0.00 | 0.00 | 0.00 |
| mature NK T cell | 0 | 0.00 | 0.00 | 0.00 |
| pulmonary ionocyte | 0 | 0.00 | 0.00 | 0.00 |
| B cell | 0 | 0.00 | 0.00 | 0.00 |
The train accuracies are computed on the training data.
| Cell Type | N cells | svm | xgboost | Consensus Prediction |
|---|---|---|---|---|
| macrophage | 370 | 0.98 | 0.94 | 0.97 |
| pulmonary alveolar type 2 cell | 247 | 0.99 | 0.94 | 0.94 |
| basal cell | 60 | 0.92 | 0.88 | 0.93 |
| non-classical monocyte | 34 | 0.80 | 0.64 | 0.80 |
| capillary endothelial cell | 33 | 0.99 | 0.96 | 0.99 |
| club cell | 32 | 0.96 | 0.83 | 0.84 |
| classical monocyte | 27 | 0.98 | 0.96 | 0.96 |
| basophil | 23 | 1.00 | 1.00 | 1.00 |
| CD4-positive, alpha-beta T cell | 20 | 1.00 | 1.00 | 1.00 |
| respiratory goblet cell | 18 | 0.90 | 0.88 | 0.92 |
| lung ciliated cell | 15 | 1.00 | 0.94 | 0.94 |
| vein endothelial cell | 14 | 1.00 | 0.97 | 1.00 |
| lung microvascular endothelial cell | 14 | 1.00 | 1.00 | 1.00 |
| CD8-positive, alpha-beta T cell | 12 | 1.00 | 0.96 | 0.96 |
| fibroblast | 11 | 1.00 | 1.00 | 1.00 |
| intermediate monocyte | 9 | 1.00 | 1.00 | 1.00 |
| adventitial cell | 9 | 1.00 | 1.00 | 1.00 |
| endothelial cell of artery | 8 | 1.00 | 1.00 | 1.00 |
| pulmonary alveolar type 1 cell | 8 | 0.89 | 0.59 | 0.62 |
| neutrophil | 7 | 1.00 | 0.93 | 0.93 |
| dendritic cell | 6 | 1.00 | 0.92 | 0.92 |
| pericyte | 6 | 1.00 | 1.00 | 1.00 |
| effector CD8-positive, alpha-beta T cell | 3 | 1.00 | 1.00 | 1.00 |
| effector CD4-positive, alpha-beta T cell | 3 | 1.00 | 1.00 | 1.00 |
| bronchial smooth muscle cell | 3 | 1.00 | 1.00 | 1.00 |
| plasma cell | 2 | 1.00 | 1.00 | 1.00 |
| smooth muscle cell | 2 | 1.00 | 1.00 | 1.00 |
| endothelial cell of lymphatic vessel | 1 | 1.00 | 1.00 | 1.00 |
| mature NK T cell | 1 | 1.00 | 1.00 | 1.00 |
| pulmonary ionocyte | 1 | 1.00 | 1.00 | 1.00 |
| B cell | 1 | 1.00 | 1.00 | 1.00 |
References
Tabula Sapiens reveals transcription factor expression, senescence effects, and sex-specific features in cell types from 28 human organs and tissues, The Tabula Sapiens Consortium; bioRxiv, doi: https://doi.org/10.1101/2024.12.03.626516