popV/tabula_muris_Kidney_10x

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

Ageing is characterized by a progressive loss of physiological integrity, leading to impaired function and increased vulnerability to death. Despite rapid advances over recent years, many of the molecular and cellular processes that underlie the progressive loss of healthy physiology are poorly understood. To gain a better insight into these processes, here we generate a single-cell transcriptomic atlas across the lifespan of Mus musculus that includes data from 23 tissues and organs. We found cell-specific changes occurring across multiple cell types and organs, as well as age-related changes in the cellular composition of different organs. Using single-cell transcriptomic data, we assessed cell-type-specific manifestations of different hallmarks of ageing—such as senescence, genomic instability and changes in the immune system. This transcriptomic atlas—which we denote Tabula Muris Senis, or ‘Mouse Ageing Cell Atlas’—provides molecular information about how the most important hallmarks of ageing are reflected in a broad range of tissues and cell types.

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 bbknn	knn harmony	knn on scvi	onclass	scanvi	svm	xgboost	Consensus Prediction
kidney proximal convoluted tubule epithelial cell	468	0.92	0.87	0.87	0.82	0.00	0.86	0.89	0.92	0.91
B cell	322	0.98	0.99	0.98	0.99	0.00	0.98	0.98	0.98	0.99
epithelial cell of proximal tubule	293	0.88	0.85	0.80	0.70	0.00	0.77	0.84	0.86	0.85
kidney loop of Henle thick ascending limb epithelial cell	167	0.92	0.92	0.92	0.92	0.00	0.90	0.89	0.97	0.93
lymphocyte	142	0.96	0.84	0.95	0.97	0.00	0.92	0.98	0.97	0.99
macrophage	135	0.97	0.97	0.97	0.97	0.00	0.95	0.99	0.98	0.99
T cell	147	0.98	0.96	0.96	0.96	0.00	0.96	0.97	0.97	0.97
fenestrated endothelial cell	86	0.90	0.91	0.91	0.90	0.00	0.90	0.91	0.92	0.92
kidney collecting duct principal cell	86	0.96	0.98	0.95	0.97	0.00	0.97	0.98	0.98	0.98
kidney distal convoluted tubule epithelial cell	70	0.94	0.96	0.94	0.96	0.00	0.94	0.96	0.96	0.96
plasmatocyte	42	0.89	0.95	0.94	0.92	0.00	0.91	0.87	0.94	0.95
brush cell	30	0.90	0.95	0.92	0.84	0.00	0.84	0.82	0.89	0.90
kidney cortex artery cell	39	0.88	0.93	0.90	0.88	0.00	0.90	0.90	0.93	0.92
plasma cell	27	0.86	0.88	0.87	0.84	0.00	0.78	0.83	0.83	0.93
mesangial cell	25	0.88	0.96	0.91	0.88	0.00	0.92	0.94	0.94	0.94
kidney loop of Henle ascending limb epithelial cell	22	0.12	0.00	0.08	0.00	0.00	0.12	0.22	0.80	0.00
kidney capillary endothelial cell	24	0.76	0.79	0.81	0.80	0.00	0.74	0.81	0.79	0.81
fibroblast	18	0.92	0.97	0.92	0.94	0.00	0.89	0.97	0.97	0.97
kidney proximal straight tubule epithelial cell	12	0.00	0.00	0.00	0.00	0.00	0.00	0.27	0.29	0.00
natural killer cell	7	0.67	0.57	0.57	0.80	0.00	0.78	0.75	0.75	0.75
kidney collecting duct epithelial cell	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
leukocyte	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
kidney cell	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00

The train accuracies are computed on the training data.

Cell Type	N cells	celltypist	knn bbknn	knn harmony	knn on scvi	onclass	scanvi	svm	xgboost	Consensus Prediction
kidney proximal convoluted tubule epithelial cell	3992	0.92	0.87	0.86	0.84	0.00	0.89	0.92	0.94	0.93
B cell	2802	0.98	0.98	0.98	0.98	0.00	0.98	0.99	0.99	0.99
epithelial cell of proximal tubule	2760	0.89	0.87	0.80	0.77	0.00	0.86	0.90	0.91	0.90
kidney loop of Henle thick ascending limb epithelial cell	1387	0.93	0.94	0.93	0.93	0.00	0.96	0.97	0.98	0.95
lymphocyte	1394	0.94	0.80	0.96	0.95	0.00	0.93	0.97	0.97	0.98
macrophage	1272	0.96	0.96	0.96	0.97	0.00	0.96	0.98	0.98	0.98
T cell	1212	0.98	0.98	0.98	0.97	0.00	0.98	0.99	0.99	0.98
fenestrated endothelial cell	941	0.93	0.95	0.94	0.93	0.00	0.96	0.98	0.99	0.96
kidney collecting duct principal cell	703	0.96	0.97	0.96	0.96	0.00	0.97	0.99	0.99	0.97
kidney distal convoluted tubule epithelial cell	674	0.93	0.95	0.94	0.94	0.00	0.95	0.99	0.98	0.95
plasmatocyte	454	0.91	0.95	0.92	0.93	0.00	0.93	0.97	0.98	0.96
brush cell	384	0.90	0.93	0.93	0.92	0.00	0.94	0.97	0.98	0.98
kidney cortex artery cell	342	0.85	0.92	0.89	0.88	0.00	0.92	0.97	0.97	0.94
plasma cell	298	0.87	0.87	0.83	0.81	0.00	0.83	0.94	0.92	0.96
mesangial cell	236	0.89	0.97	0.95	0.93	0.00	0.94	0.99	1.00	0.98
kidney loop of Henle ascending limb epithelial cell	179	0.23	0.33	0.25	0.01	0.00	0.77	0.85	0.90	0.49
kidney capillary endothelial cell	137	0.70	0.76	0.74	0.74	0.00	0.89	0.96	0.98	0.82
fibroblast	143	0.97	0.99	0.95	0.95	0.00	0.98	1.00	1.00	0.97
kidney proximal straight tubule epithelial cell	83	0.00	0.00	0.00	0.00	0.00	0.68	0.64	0.68	0.62
natural killer cell	59	0.81	0.85	0.86	0.79	0.00	0.82	0.87	0.88	0.85
kidney collecting duct epithelial cell	24	0.00	0.00	0.00	0.00	0.00	0.92	1.00	0.96	0.08
leukocyte	4	0.00	0.00	0.00	0.00	0.00	0.80	1.00	1.00	0.00
kidney cell	2	0.00	0.00	0.00	0.00	0.00	0.40	1.00	1.00	0.00

References

A single-cell transcriptomic atlas characterizes ageing tissues in the mouse, The Tabula Muris Consortium, Nicole Almanzar, Jane Antony, Ankit S. Baghel, Isaac Bakerman, Ishita Bansal, Ben A. Barres, Philip A. Beachy, Daniela Berdnik, Biter Bilen, Douglas Brownfield, Corey Cain, Charles K. F. Chan, Michelle B. Chen, Michael F. Clarke, Stephanie D. Conley, Spyros Darmanis, Aaron Demers, Kubilay Demir, Antoine de Morree, Tessa Divita, Haley du Bois, Hamid Ebadi, F. Hernán Espinoza, Matt Fish, Qiang Gan, Benson M. George, Astrid Gillich, Rafael Gòmez-Sjöberg, Foad Green, Geraldine Genetiano, Xueying Gu, Gunsagar S. Gulati, Oliver Hahn, Michael Seamus Haney, Yan Hang, Lincoln Harris, Mu He, Shayan Hosseinzadeh, Albin Huang, Kerwyn Casey Huang, Tal Iram, Taichi Isobe, Feather Ives, Robert C. Jones, Kevin S. Kao, Jim Karkanias, Guruswamy Karnam, Andreas Keller, Aaron M. Kershner, Nathalie Khoury, Seung K. Kim, Bernhard M. Kiss, William Kong, Mark A. Krasnow, Maya E. Kumar, Christin S. Kuo, Jonathan Lam, Davis P. Lee, Song E. Lee, Benoit Lehallier, Olivia Leventhal, Guang Li, Qingyun Li, Ling Liu, Annie Lo, Wan-Jin Lu, Maria F. Lugo-Fagundo, Anoop Manjunath, Andrew P. May, Ashley Maynard, Aaron McGeever, Marina McKay, M. Windy McNerney, Bryan Merrill, Ross J. Metzger, Marco Mignardi, Dullei Min, Ahmad N. Nabhan, Norma F. Neff, Katharine M. Ng, Patricia K. Nguyen, Joseph Noh, Roel Nusse, Róbert Pálovics, Rasika Patkar, Weng Chuan Peng, Lolita Penland, Angela Oliveira Pisco, Katherine Pollard, Robert Puccinelli, Zhen Qi, Stephen R. Quake, Thomas A. Rando, Eric J. Rulifson, Nicholas Schaum, Joe M. Segal, Shaheen S. Sikandar, Rahul Sinha, Rene V. Sit, Justin Sonnenburg, Daniel Staehli, Krzysztof Szade, Michelle Tan, Weilun Tan, Cristina Tato, Krissie Tellez, Laughing Bear Torrez Dulgeroff, Kyle J. Travaglini, Carolina Tropini, Margaret Tsui, Lucas Waldburger, Bruce M. Wang, Linda J. van Weele, Kenneth Weinberg, Irving L. Weissman, Michael N. Wosczyna, Sean M. Wu, Tony Wyss-Coray, Jinyi Xiang, Soso Xue, Kevin A. Yamauchi, Andrew C. Yang, Lakshmi P. Yerra, Justin Youngyunpipatkul, Brian Yu, Fabio Zanini, Macy E. Zardeneta, Alexander Zee, Chunyu Zhao, Fan Zhang, Hui Zhang, Martin Jinye Zhang, Lu Zhou, James Zou; Nature, doi: https://doi.org/10.1038/s41586-020-2496-1