canergen commited on
Commit
5604f7b
·
verified ·
1 Parent(s): dfc70ae

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +21 -21
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 | 2.45 |
55
  | Pearson Correlation | 0.84 | 0.81 |
56
  | Spearman Correlation | 0.86 | 0.84 |
57
- | R² (R-Squared) | 0.52 | 0.49 |
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 | 13.48 |
67
- | Pearson Correlation | 0.59 |
68
- | Spearman Correlation | 0.66 |
69
- | R² (R-Squared) | -1.49 |
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
- | neutrophil | 0.94 | 2.25 | 0.64 | 0.87 | 0.19 | 0.84 | 2911.00 |
87
- | CD4-positive, alpha-beta T cell | 0.94 | 1.96 | 0.62 | 0.90 | 0.34 | 0.79 | 2025.00 |
88
- | monocyte | 0.87 | 1.79 | 0.64 | 0.88 | 0.40 | 0.77 | 1389.00 |
89
- | CD8-positive, alpha-beta T cell | 0.86 | 2.95 | 0.58 | 0.85 | 0.32 | 0.74 | 1147.00 |
90
- | granulocyte | 0.79 | 2.38 | 0.64 | 0.89 | 0.46 | 0.83 | 853.00 |
91
- | plasma cell | 0.75 | 2.35 | 0.71 | 0.91 | 0.19 | 0.85 | 825.00 |
92
- | erythroid progenitor cell | 0.64 | 2.46 | 0.67 | 0.91 | 0.49 | 0.89 | 757.00 |
93
- | mature NK T cell | 0.78 | 3.77 | 0.58 | 0.76 | 0.33 | 0.69 | 678.00 |
94
- | hematopoietic stem cell | 0.89 | 2.27 | 0.65 | 0.87 | 0.53 | 0.85 | 617.00 |
95
- | memory B cell | 0.87 | 4.54 | 0.56 | 0.68 | 0.33 | 0.70 | 310.00 |
96
- | common myeloid progenitor | 0.72 | 2.72 | 0.69 | 0.89 | 0.54 | 0.88 | 287.00 |
97
- | macrophage | 0.86 | 4.43 | 0.63 | 0.70 | 0.34 | 0.78 | 265.00 |
98
- | naive B cell | 0.88 | 5.59 | 0.57 | 0.66 | 0.27 | 0.66 | 142.00 |
99
- | erythrocyte | 0.90 | 5.34 | 0.53 | 0.47 | 0.33 | 0.90 | 87.00 |
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 | 2.38 | 2.47 |
55
  | Pearson Correlation | 0.84 | 0.81 |
56
  | Spearman Correlation | 0.86 | 0.84 |
57
+ | R² (R-Squared) | 0.54 | 0.48 |
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 | 13.58 |
67
+ | Pearson Correlation | 0.58 |
68
+ | Spearman Correlation | 0.65 |
69
+ | R² (R-Squared) | -1.50 |
70
 
71
  </details>
72
 
 
83
 
84
  | Index | gene_f1 | lfc_mae | lfc_pearson | lfc_spearman | roc_auc | pr_auc | n_cells |
85
  | --- | --- | --- | --- | --- | --- | --- | --- |
86
+ | neutrophil | 0.94 | 2.21 | 0.66 | 0.88 | 0.19 | 0.84 | 2911.00 |
87
+ | CD4-positive, alpha-beta T cell | 0.94 | 1.93 | 0.64 | 0.91 | 0.33 | 0.79 | 2025.00 |
88
+ | monocyte | 0.87 | 1.70 | 0.68 | 0.89 | 0.40 | 0.78 | 1389.00 |
89
+ | CD8-positive, alpha-beta T cell | 0.85 | 2.94 | 0.58 | 0.84 | 0.32 | 0.74 | 1147.00 |
90
+ | granulocyte | 0.76 | 2.42 | 0.63 | 0.87 | 0.47 | 0.84 | 853.00 |
91
+ | plasma cell | 0.76 | 2.29 | 0.72 | 0.92 | 0.19 | 0.85 | 825.00 |
92
+ | erythroid progenitor cell | 0.62 | 2.48 | 0.67 | 0.91 | 0.49 | 0.89 | 757.00 |
93
+ | mature NK T cell | 0.81 | 3.78 | 0.57 | 0.77 | 0.33 | 0.69 | 678.00 |
94
+ | hematopoietic stem cell | 0.89 | 2.25 | 0.65 | 0.87 | 0.53 | 0.85 | 617.00 |
95
+ | memory B cell | 0.89 | 4.68 | 0.55 | 0.68 | 0.33 | 0.70 | 310.00 |
96
+ | common myeloid progenitor | 0.73 | 2.48 | 0.73 | 0.89 | 0.54 | 0.88 | 287.00 |
97
+ | macrophage | 0.84 | 4.55 | 0.62 | 0.69 | 0.34 | 0.79 | 265.00 |
98
+ | naive B cell | 0.89 | 5.33 | 0.60 | 0.68 | 0.26 | 0.66 | 142.00 |
99
+ | erythrocyte | 0.91 | 5.13 | 0.55 | 0.49 | 0.33 | 0.90 | 87.00 |
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