Hugging Face's logo

scvi-tools
/
tabula-sapiens-lymph_node-scvi

TensorBoard
scvi-tools
biology
genomics
single-cell
model_cls_name:SCVI
scvi_version:1.4.2
anndata_version:0.12.7
modality:rna
tissue:various
annotated:True
Model card Files
xet
Metrics Community
OriKron commited on
Commit
4ff9df8
·
verified ·
1 Parent(s): 6956aac

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +58 -54
README.md CHANGED
@@ -6,8 +6,8 @@ tags:
6
  - genomics
7
  - single-cell
8
  - model_cls_name:SCVI
9
- - scvi_version:1.2.0
10
- - anndata_version:0.11.1
11
  - modality:rna
12
  - tissue:various
13
  - annotated:True
@@ -20,7 +20,7 @@ The learned low-dimensional latent representation of the data can be used for vi
20
  clustering.
21
 
22
  scVI takes as input a scRNA-seq gene expression matrix with cells and genes.
23
- We provide an extensive [user guide](https://docs.scvi-tools.org/en/1.2.0/user_guide/models/scvi.html).
24
 
25
  - See our original manuscript for further details of the model:
26
  [scVI manuscript](https://www.nature.com/articles/s41592-018-0229-2).
@@ -28,7 +28,7 @@ We provide an extensive [user guide](https://docs.scvi-tools.org/en/1.2.0/user_g
28
  to leverage pre-trained models.
29
 
30
  This model can be used for fine tuning on new data using our Arches framework:
31
- [Arches tutorial](https://docs.scvi-tools.org/en/1.0.0/tutorials/notebooks/scarches_scvi_tools.html).
32
 
33
 
34
  # Model Description
@@ -51,10 +51,10 @@ space might still be useful for analysis.
51
 
52
  | Metric | Training Value | Validation Value |
53
  |-------------------------|----------------|------------------|
54
- | Mean Absolute Error | 1.52 | 1.56 |
55
- | Pearson Correlation | 0.83 | 0.82 |
56
- | Spearman Correlation | 0.75 | 0.75 |
57
- | R² (R-Squared) | 0.35 | 0.28 |
58
 
59
  The gene-wise coefficient of variation summarizes how well variation between different genes is
60
  preserved by the generated model expression. This value is usually quite high.
@@ -63,10 +63,10 @@ preserved by the generated model expression. This value is usually quite high.
63
 
64
  | Metric | Training Value |
65
  |-------------------------|----------------|
66
- | Mean Absolute Error | 24.66 |
67
- | Pearson Correlation | 0.68 |
68
- | Spearman Correlation | 0.74 |
69
- | R² (R-Squared) | -0.67 |
70
 
71
  </details>
72
 
@@ -83,28 +83,31 @@ cell-type.
83
 
84
  | Index | gene_f1 | lfc_mae | lfc_pearson | lfc_spearman | roc_auc | pr_auc | n_cells |
85
  | --- | --- | --- | --- | --- | --- | --- | --- |
86
- | B cell | 0.96 | 0.56 | 0.80 | 0.96 | 0.30 | 0.87 | 15249.00 |
87
- | effector CD4-positive, alpha-beta T cell | 0.90 | 1.10 | 0.55 | 0.90 | 0.27 | 0.77 | 6908.00 |
88
- | effector CD8-positive, alpha-beta T cell | 0.95 | 1.33 | 0.54 | 0.89 | 0.27 | 0.78 | 5860.00 |
89
- | T cell | 0.86 | 1.67 | 0.50 | 0.83 | 0.25 | 0.71 | 3848.00 |
90
- | type I NK T cell | 0.88 | 1.44 | 0.61 | 0.85 | 0.30 | 0.71 | 3758.00 |
91
- | plasma cell | 0.88 | 0.82 | 0.77 | 0.94 | 0.35 | 0.91 | 2426.00 |
92
- | innate lymphoid cell | 0.76 | 1.59 | 0.53 | 0.77 | 0.25 | 0.58 | 2052.00 |
93
- | macrophage | 0.77 | 1.66 | 0.72 | 0.92 | 0.45 | 0.88 | 1086.00 |
94
- | regulatory T cell | 0.84 | 2.83 | 0.57 | 0.74 | 0.40 | 0.71 | 881.00 |
95
- | mature NK T cell | 0.83 | 3.92 | 0.55 | 0.64 | 0.40 | 0.65 | 437.00 |
96
- | classical monocyte | 0.80 | 4.30 | 0.60 | 0.71 | 0.47 | 0.76 | 161.00 |
97
- | endothelial cell | 0.69 | 2.94 | 0.71 | 0.85 | 0.57 | 0.85 | 143.00 |
98
- | intermediate monocyte | 0.73 | 3.94 | 0.64 | 0.74 | 0.51 | 0.79 | 134.00 |
99
- | mast cell | 0.82 | 4.77 | 0.62 | 0.64 | 0.38 | 0.74 | 119.00 |
100
- | stromal cell | 0.69 | 3.65 | 0.70 | 0.81 | 0.53 | 0.85 | 111.00 |
101
- | neutrophil | 0.87 | 4.86 | 0.61 | 0.58 | 0.39 | 0.83 | 107.00 |
102
- | CD1c-positive myeloid dendritic cell | 0.71 | 4.13 | 0.65 | 0.72 | 0.52 | 0.79 | 68.00 |
103
- | CD141-positive myeloid dendritic cell | 0.67 | 4.59 | 0.62 | 0.62 | 0.49 | 0.75 | 48.00 |
104
- | hematopoietic stem cell | 0.53 | 5.15 | 0.56 | 0.51 | 0.46 | 0.66 | 34.00 |
105
- | non-classical monocyte | 0.75 | 5.22 | 0.58 | 0.56 | 0.40 | 0.69 | 31.00 |
106
- | erythrocyte | 0.65 | 5.66 | 0.48 | 0.42 | 0.42 | 0.80 | 24.00 |
107
- | mature conventional dendritic cell | 0.57 | 6.28 | 0.50 | 0.44 | 0.38 | 0.62 | 17.00 |
 
 
 
108
 
109
  </details>
110
 
@@ -124,6 +127,7 @@ These provide the settings to setup the original model:
124
  "dropout_rate": 0.05,
125
  "dispersion": "gene",
126
  "gene_likelihood": "nb",
 
127
  "latent_distribution": "normal",
128
  "use_batch_norm": "none",
129
  "use_layer_norm": "both",
@@ -139,9 +143,9 @@ These provide the settings to setup the original model:
139
  Arguments passed to setup_anndata of the original model:
140
  ```json
141
  {
142
- "layer": null,
143
  "batch_key": "donor_assay",
144
- "labels_key": "cell_ontology_class",
145
  "size_factor_key": null,
146
  "categorical_covariate_keys": null,
147
  "continuous_covariate_keys": null
@@ -154,15 +158,15 @@ Arguments passed to setup_anndata of the original model:
154
  <summary><strong>Data Registry</strong></summary>
155
 
156
  Registry elements for AnnData manager:
157
- | Registry Key | scvi-tools Location |
158
- |-------------------|--------------------------------------|
159
- | X | adata.X |
160
- | batch | adata.obs['_scvi_batch'] |
161
- | labels | adata.obs['_scvi_labels'] |
162
- | latent_qzm | adata.obsm['scvi_latent_qzm'] |
163
- | latent_qzv | adata.obsm['scvi_latent_qzv'] |
164
- | minify_type | adata.uns['_scvi_adata_minify_type'] |
165
- | observed_lib_size | adata.obs['observed_lib_size'] |
166
 
167
  - **Data is Minified**: False
168
 
@@ -171,16 +175,16 @@ Registry elements for AnnData manager:
171
  <details>
172
  <summary><strong>Summary Statistics</strong></summary>
173
 
174
- | Summary Stat Key | Value |
175
  |--------------------------|-------|
176
- | n_batch | 4 |
177
- | n_cells | 43502 |
178
- | n_extra_categorical_covs | 0 |
179
- | n_extra_continuous_covs | 0 |
180
- | n_labels | 22 |
181
- | n_latent_qzm | 20 |
182
- | n_latent_qzv | 20 |
183
- | n_vars | 3000 |
184
 
185
  </details>
186
 
 
6
  - genomics
7
  - single-cell
8
  - model_cls_name:SCVI
9
+ - scvi_version:1.4.2
10
+ - anndata_version:0.12.7
11
  - modality:rna
12
  - tissue:various
13
  - annotated:True
 
20
  clustering.
21
 
22
  scVI takes as input a scRNA-seq gene expression matrix with cells and genes.
23
+ We provide an extensive [user guide](https://docs.scvi-tools.org/en/stable/user_guide/models/scvi.html).
24
 
25
  - See our original manuscript for further details of the model:
26
  [scVI manuscript](https://www.nature.com/articles/s41592-018-0229-2).
 
28
  to leverage pre-trained models.
29
 
30
  This model can be used for fine tuning on new data using our Arches framework:
31
+ [Arches tutorial](https://docs.scvi-tools.org/en/stable/tutorials/notebooks/scrna/scarches_scvi_tools.html).
32
 
33
 
34
  # Model Description
 
51
 
52
  | Metric | Training Value | Validation Value |
53
  |-------------------------|----------------|------------------|
54
+ | Mean Absolute Error | 1.52 | 1.54 |
55
+ | Pearson Correlation | 0.82 | 0.81 |
56
+ | Spearman Correlation | 0.81 | 0.80 |
57
+ | R² (R-Squared) | 0.44 | 0.40 |
58
 
59
  The gene-wise coefficient of variation summarizes how well variation between different genes is
60
  preserved by the generated model expression. This value is usually quite high.
 
63
 
64
  | Metric | Training Value |
65
  |-------------------------|----------------|
66
+ | Mean Absolute Error | 32.40 |
67
+ | Pearson Correlation | 0.66 |
68
+ | Spearman Correlation | 0.75 |
69
+ | R² (R-Squared) | 0.09 |
70
 
71
  </details>
72
 
 
83
 
84
  | Index | gene_f1 | lfc_mae | lfc_pearson | lfc_spearman | roc_auc | pr_auc | n_cells |
85
  | --- | --- | --- | --- | --- | --- | --- | --- |
86
+ | B cell | 0.94 | 0.20 | 0.97 | 0.99 | 0.04 | 0.02 | 54746.00 |
87
+ | CD4-positive, alpha-beta T cell | 0.95 | 0.27 | 0.77 | 0.97 | 0.31 | 0.11 | 39280.00 |
88
+ | CD8-positive, alpha-beta T cell | 0.92 | 0.39 | 0.72 | 0.94 | 0.37 | 0.30 | 14682.00 |
89
+ | plasma cell | 0.84 | 0.32 | 0.91 | 0.98 | 0.22 | 0.06 | 5944.00 |
90
+ | naive thymus-derived CD4-positive, alpha-beta T cell | 0.89 | 0.78 | 0.59 | 0.89 | 0.22 | 0.22 | 4154.00 |
91
+ | macrophage | 0.79 | 0.74 | 0.78 | 0.95 | 0.97 | 0.64 | 1794.00 |
92
+ | natural killer cell | 0.91 | 1.51 | 0.52 | 0.82 | 0.43 | 0.38 | 1579.00 |
93
+ | T cell | 0.86 | 1.85 | 0.57 | 0.80 | 0.11 | 0.08 | 1281.00 |
94
+ | mature NK T cell | 0.89 | 1.42 | 0.59 | 0.80 | 0.51 | 0.44 | 1024.00 |
95
+ | regulatory T cell | 0.85 | 1.74 | 0.58 | 0.79 | 0.28 | 0.19 | 968.00 |
96
+ | monocyte | 0.75 | 1.04 | 0.71 | 0.93 | 0.43 | 0.32 | 766.00 |
97
+ | innate lymphoid cell | 0.36 | 2.00 | 0.66 | 0.82 | 0.05 | 0.02 | 745.00 |
98
+ | classical monocyte | 0.85 | 1.99 | 0.63 | 0.86 | 0.60 | 0.46 | 552.00 |
99
+ | neutrophil | 0.87 | 4.67 | 0.56 | 0.65 | 0.27 | 0.02 | 303.00 |
100
+ | intermediate monocyte | 0.81 | 2.90 | 0.63 | 0.82 | 0.24 | 0.04 | 281.00 |
101
+ | mast cell | 0.79 | 3.68 | 0.62 | 0.69 | 0.28 | 0.02 | 212.00 |
102
+ | endothelial cell | 0.65 | 1.77 | 0.67 | 0.86 | 0.13 | 0.03 | 196.00 |
103
+ | myeloid dendritic cell | 0.77 | 3.34 | 0.62 | 0.78 | 0.22 | 0.02 | 122.00 |
104
+ | CD4-positive, alpha-beta thymocyte | 0.56 | 5.34 | 0.60 | 0.75 | 0.18 | 0.02 | 122.00 |
105
+ | stromal cell | 0.60 | 3.51 | 0.62 | 0.78 | 0.21 | 0.02 | 111.00 |
106
+ | non-classical monocyte | 0.77 | 4.40 | 0.60 | 0.65 | 0.29 | 0.02 | 71.00 |
107
+ | CD8-positive, alpha-beta thymocyte | 0.52 | 6.83 | 0.54 | 0.65 | 0.27 | 0.02 | 59.00 |
108
+ | erythrocyte | 0.21 | 7.58 | 0.36 | 0.26 | 0.46 | 0.03 | 42.00 |
109
+ | plasmacytoid dendritic cell | 0.46 | 6.54 | 0.47 | 0.36 | 0.40 | 0.03 | 16.00 |
110
+ | hematopoietic precursor cell | 0.38 | 6.40 | 0.49 | 0.40 | 0.34 | 0.02 | 12.00 |
111
 
112
  </details>
113
 
 
127
  "dropout_rate": 0.05,
128
  "dispersion": "gene",
129
  "gene_likelihood": "nb",
130
+ "use_observed_lib_size": true,
131
  "latent_distribution": "normal",
132
  "use_batch_norm": "none",
133
  "use_layer_norm": "both",
 
143
  Arguments passed to setup_anndata of the original model:
144
  ```json
145
  {
146
+ "layer": "counts",
147
  "batch_key": "donor_assay",
148
+ "labels_key": "cell_type",
149
  "size_factor_key": null,
150
  "categorical_covariate_keys": null,
151
  "continuous_covariate_keys": null
 
158
  <summary><strong>Data Registry</strong></summary>
159
 
160
  Registry elements for AnnData manager:
161
+ | Registry Key | scvi-tools Location |
162
+ |--------------------------|--------------------------------------|
163
+ | X | adata.layers['counts'] |
164
+ | batch | adata.obs['_scvi_batch'] |
165
+ | labels | adata.obs['_scvi_labels'] |
166
+ | latent_qzm | adata.obsm['scvi_latent_qzm'] |
167
+ | latent_qzv | adata.obsm['scvi_latent_qzv'] |
168
+ | minify_type | adata.uns['_scvi_adata_minify_type'] |
169
+ | observed_lib_size | adata.obs['observed_lib_size'] |
170
 
171
  - **Data is Minified**: False
172
 
 
175
  <details>
176
  <summary><strong>Summary Statistics</strong></summary>
177
 
178
+ | Summary Stat Key | Value |
179
  |--------------------------|-------|
180
+ | n_batch | 12 |
181
+ | n_cells | 129062 |
182
+ | n_extra_categorical_covs | 0 |
183
+ | n_extra_continuous_covs | 0 |
184
+ | n_labels | 25 |
185
+ | n_latent_qzm | 20 |
186
+ | n_latent_qzv | 20 |
187
+ | n_vars | 3000 |
188
 
189
  </details>
190