canergen commited on
Commit
18e1dd3
·
verified ·
1 Parent(s): 54782dc

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +19 -19
README.md CHANGED
@@ -51,10 +51,10 @@ space might still be useful for analysis.
51
 
52
  | Metric | Training Value | Validation Value |
53
  |-------------------------|----------------|------------------|
54
- | Mean Absolute Error | 2.39 | 2.55 |
55
  | Pearson Correlation | 0.72 | 0.68 |
56
- | Spearman Correlation | 0.66 | 0.64 |
57
- | R² (R-Squared) | 0.03 | -0.11 |
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 | 17.57 |
67
  | Pearson Correlation | 0.57 |
68
  | Spearman Correlation | 0.59 |
69
- | R² (R-Squared) | -2.51 |
70
 
71
  </details>
72
 
@@ -83,20 +83,20 @@ cell-type.
83
 
84
  | Index | gene_f1 | lfc_mae | lfc_pearson | lfc_spearman | roc_auc | pr_auc | n_cells |
85
  | --- | --- | --- | --- | --- | --- | --- | --- |
86
- | luminal epithelial cell of mammary gland | 0.92 | 0.60 | 0.79 | 0.97 | 0.48 | 0.91 | 5378.00 |
87
- | T cell | 0.94 | 2.03 | 0.60 | 0.83 | 0.18 | 0.83 | 2324.00 |
88
  | fibroblast of breast | 0.91 | 1.24 | 0.67 | 0.93 | 0.44 | 0.89 | 2066.00 |
89
- | basal cell | 0.88 | 3.06 | 0.60 | 0.76 | 0.33 | 0.72 | 476.00 |
90
- | vein endothelial cell | 0.85 | 3.15 | 0.67 | 0.80 | 0.38 | 0.79 | 263.00 |
91
- | macrophage | 0.76 | 3.56 | 0.61 | 0.75 | 0.32 | 0.79 | 219.00 |
92
- | plasma cell | 0.77 | 3.47 | 0.58 | 0.71 | 0.19 | 0.86 | 194.00 |
93
- | endothelial cell of artery | 0.82 | 4.10 | 0.60 | 0.71 | 0.41 | 0.76 | 168.00 |
94
- | pericyte | 0.82 | 4.67 | 0.59 | 0.62 | 0.37 | 0.70 | 106.00 |
95
- | vascular associated smooth muscle cell | 0.76 | 5.43 | 0.55 | 0.54 | 0.38 | 0.72 | 71.00 |
96
- | B cell | 0.53 | 7.92 | 0.40 | 0.37 | 0.34 | 0.73 | 43.00 |
97
- | endothelial cell of lymphatic vessel | 0.50 | 6.51 | 0.51 | 0.44 | 0.40 | 0.70 | 32.00 |
98
- | mature NK T cell | 0.48 | 6.09 | 0.44 | 0.43 | 0.32 | 0.78 | 19.00 |
99
- | mast cell | 0.29 | 7.12 | 0.38 | 0.32 | 0.38 | 0.75 | 16.00 |
100
 
101
  </details>
102
 
@@ -188,7 +188,7 @@ scvi-tools documentation for details. -->
188
  If provided by the original uploader, for those interested in understanding or replicating the
189
  training process, the code is available at the link below.
190
 
191
- **Training Code URL**: Not provided by uploader
192
 
193
  </details>
194
 
 
51
 
52
  | Metric | Training Value | Validation Value |
53
  |-------------------------|----------------|------------------|
54
+ | Mean Absolute Error | 2.40 | 2.57 |
55
  | Pearson Correlation | 0.72 | 0.68 |
56
+ | Spearman Correlation | 0.67 | 0.62 |
57
+ | R² (R-Squared) | 0.04 | -0.12 |
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 | 17.47 |
67
  | Pearson Correlation | 0.57 |
68
  | Spearman Correlation | 0.59 |
69
+ | R² (R-Squared) | -2.35 |
70
 
71
  </details>
72
 
 
83
 
84
  | Index | gene_f1 | lfc_mae | lfc_pearson | lfc_spearman | roc_auc | pr_auc | n_cells |
85
  | --- | --- | --- | --- | --- | --- | --- | --- |
86
+ | luminal epithelial cell of mammary gland | 0.93 | 0.62 | 0.78 | 0.97 | 0.48 | 0.91 | 5378.00 |
87
+ | T cell | 0.93 | 2.01 | 0.60 | 0.83 | 0.18 | 0.83 | 2324.00 |
88
  | fibroblast of breast | 0.91 | 1.24 | 0.67 | 0.93 | 0.44 | 0.89 | 2066.00 |
89
+ | basal cell | 0.89 | 3.02 | 0.60 | 0.75 | 0.33 | 0.72 | 476.00 |
90
+ | vein endothelial cell | 0.86 | 3.36 | 0.64 | 0.80 | 0.38 | 0.79 | 263.00 |
91
+ | macrophage | 0.76 | 3.71 | 0.59 | 0.74 | 0.34 | 0.79 | 219.00 |
92
+ | plasma cell | 0.75 | 3.57 | 0.57 | 0.68 | 0.21 | 0.86 | 194.00 |
93
+ | endothelial cell of artery | 0.83 | 3.94 | 0.62 | 0.72 | 0.40 | 0.76 | 168.00 |
94
+ | pericyte | 0.80 | 5.00 | 0.56 | 0.60 | 0.37 | 0.70 | 106.00 |
95
+ | vascular associated smooth muscle cell | 0.69 | 5.39 | 0.55 | 0.54 | 0.38 | 0.71 | 71.00 |
96
+ | B cell | 0.46 | 7.85 | 0.41 | 0.37 | 0.33 | 0.73 | 43.00 |
97
+ | endothelial cell of lymphatic vessel | 0.53 | 6.39 | 0.52 | 0.45 | 0.38 | 0.69 | 32.00 |
98
+ | mature NK T cell | 0.47 | 5.67 | 0.48 | 0.47 | 0.29 | 0.77 | 19.00 |
99
+ | mast cell | 0.22 | 7.31 | 0.37 | 0.30 | 0.38 | 0.75 | 16.00 |
100
 
101
  </details>
102
 
 
188
  If provided by the original uploader, for those interested in understanding or replicating the
189
  training process, the code is available at the link below.
190
 
191
+ **Training Code URL**: https://github.com/YosefLab/scvi-hub-models/blob/main/src/scvi_hub_models/TS_train_all_tissues.ipynb
192
 
193
  </details>
194