popV/tabula_sapiens_Prostate

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	celltypist	knn on bbknn	knn on harmony	knn on scvi	onclass	scanvi	svm	xgboost	Consensus Prediction
luminal cell of prostate epithelium	1072	0.94	0.96	0.97	0.96	0.00	0.93	0.95	0.94	0.96
basal cell of prostate epithelium	345	0.84	0.88	0.90	0.88	0.00	0.84	0.86	0.85	0.89
CD8-positive, alpha-beta T cell	246	0.94	0.87	0.95	0.85	0.00	0.92	0.96	0.96	0.96
endothelial cell	117	0.98	0.96	0.98	0.97	0.00	0.98	0.97	0.96	0.98
macrophage	92	0.98	0.98	0.98	0.98	0.00	0.98	0.97	0.96	0.98
fibroblast	60	0.96	0.97	0.99	0.90	0.00	0.96	0.97	0.96	0.98
mature NK T cell	50	0.89	0.11	0.92	0.43	0.00	0.83	0.95	0.91	0.95
smooth muscle cell	50	0.95	0.96	0.95	0.83	0.00	0.93	0.91	0.93	0.96
neutrophil	23	0.96	0.98	0.98	0.96	0.00	0.96	0.96	0.98	0.96
erythrocyte	22	0.95	0.81	0.95	0.95	0.00	0.75	0.98	1.00	0.98
CD4-positive, alpha-beta T cell	13	0.12	0.00	0.14	0.10	0.00	0.47	0.77	0.96	0.25
B cell	8	0.88	0.80	0.88	0.82	0.00	0.89	1.00	0.89	0.94
mast cell	4	0.73	0.80	1.00	0.67	0.00	0.47	1.00	1.00	0.89
T cell	1	0.00	0.00	0.00	0.00	0.00	0.20	0.00	0.00	0.00

The train accuracies are computed on the training data.

Cell Type	N cells	celltypist	knn on bbknn	knn on harmony	knn on scvi	onclass	scanvi	svm	xgboost	Consensus Prediction
luminal cell of prostate epithelium	9580	0.95	0.95	0.98	0.97	0.00	0.93	0.95	0.95	0.97
basal cell of prostate epithelium	3150	0.86	0.87	0.94	0.92	0.00	0.86	0.89	0.88	0.91
CD8-positive, alpha-beta T cell	2270	0.94	0.88	0.95	0.91	0.00	0.94	0.95	0.97	0.97
endothelial cell	1088	0.98	0.96	0.98	0.98	0.00	0.97	0.98	0.97	0.98
macrophage	930	0.97	0.98	0.98	0.98	0.00	0.99	0.99	0.99	0.99
fibroblast	459	0.96	0.96	0.98	0.93	0.00	0.96	0.98	0.98	0.99
mature NK T cell	437	0.87	0.20	0.91	0.57	0.00	0.87	0.92	0.93	0.95
smooth muscle cell	427	0.96	0.93	0.97	0.89	0.00	0.93	0.98	0.96	0.98
neutrophil	238	0.96	0.99	0.99	0.99	0.00	0.98	0.99	1.00	0.99
erythrocyte	117	0.88	0.75	0.97	0.94	0.00	0.65	0.99	0.97	0.97
CD4-positive, alpha-beta T cell	103	0.27	0.00	0.23	0.06	0.00	0.66	0.75	0.94	0.44
B cell	93	0.83	0.81	0.83	0.83	0.00	0.95	0.97	0.96	0.96
mast cell	22	0.79	0.57	1.00	0.56	0.00	0.59	1.00	1.00	0.98
T cell	13	0.00	0.00	0.25	0.27	0.00	0.47	0.96	0.68	0.88

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