canergen commited on
Commit
9a5d9ae
·
verified ·
1 Parent(s): 28c71ad

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +20 -22
README.md CHANGED
@@ -6,9 +6,10 @@ tags:
6
  - genomics
7
  - single-cell
8
  - model_cls_name:SCVI
9
- - scvi_version:1.2.1
10
  - anndata_version:0.11.1
11
  - modality:rna
 
12
  - annotated:False
13
  ---
14
 
@@ -50,10 +51,10 @@ space might still be useful for analysis.
50
 
51
  | Metric | Training Value | Validation Value |
52
  |-------------------------|----------------|------------------|
53
- | Mean Absolute Error | 0.99 | 1.03 |
54
- | Pearson Correlation | -0.07 | -0.20 |
55
- | Spearman Correlation | -0.07 | -0.03 |
56
- | R² (R-Squared) | -14.43 | -12.71 |
57
 
58
  The gene-wise coefficient of variation summarizes how well variation between different genes is
59
  preserved by the generated model expression. This value is usually quite high.
@@ -62,10 +63,10 @@ preserved by the generated model expression. This value is usually quite high.
62
 
63
  | Metric | Training Value |
64
  |-------------------------|----------------|
65
- | Mean Absolute Error | 1.07 |
66
- | Pearson Correlation | -0.12 |
67
- | Spearman Correlation | -0.00 |
68
- | R² (R-Squared) | -2.15 |
69
 
70
  </details>
71
 
@@ -82,18 +83,15 @@ cell-type.
82
 
83
  | Index | gene_f1 | lfc_mae | lfc_pearson | lfc_spearman | roc_auc | pr_auc | n_cells |
84
  | --- | --- | --- | --- | --- | --- | --- | --- |
85
- | 0 | 0.00 | 0.90 | 0.06 | 0.05 | 0.47 | 0.34 | 50.00 |
86
- | 1 | 0.00 | 0.94 | -0.10 | -0.10 | 0.34 | 0.16 | 48.00 |
87
- | 2 | 0.10 | 0.94 | -0.02 | -0.03 | 0.53 | 0.37 | 41.00 |
88
- | 3 | 0.20 | 0.82 | 0.17 | 0.15 | 0.56 | 0.36 | 39.00 |
89
- | 4 | 0.00 | 0.99 | 0.03 | -0.02 | 0.34 | 0.16 | 37.00 |
90
- | 5 | 0.40 | 0.95 | 0.07 | 0.04 | 0.64 | 0.36 | 37.00 |
91
- | 6 | 0.20 | 1.04 | -0.14 | -0.15 | 0.48 | 0.23 | 32.00 |
92
- | 7 | 0.30 | 1.01 | 0.14 | 0.13 | 0.52 | 0.19 | 31.00 |
93
- | 8 | 0.10 | 0.99 | 0.04 | 0.07 | 0.54 | 0.23 | 28.00 |
94
- | 9 | 0.10 | 1.09 | 0.05 | 0.04 | 0.45 | 0.28 | 26.00 |
95
- | 10 | 0.10 | 1.21 | 0.09 | 0.10 | 0.54 | 0.24 | 19.00 |
96
- | 11 | 0.00 | 1.97 | -0.01 | -0.08 | 0.53 | 0.32 | 12.00 |
97
 
98
  </details>
99
 
@@ -183,4 +181,4 @@ training process, the code is available at the link below.
183
 
184
  # References
185
 
186
- To be added...
 
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:synthetic
13
  - annotated:False
14
  ---
15
 
 
51
 
52
  | Metric | Training Value | Validation Value |
53
  |-------------------------|----------------|------------------|
54
+ | Mean Absolute Error | 0.62 | 0.62 |
55
+ | Pearson Correlation | -0.01 | 0.05 |
56
+ | Spearman Correlation | 0.01 | 0.06 |
57
+ | R² (R-Squared) | -17.08 | -22.65 |
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 | 0.70 |
67
+ | Pearson Correlation | -0.05 |
68
+ | Spearman Correlation | 0.04 |
69
+ | R² (R-Squared) | -1.39 |
70
 
71
  </details>
72
 
 
83
 
84
  | Index | gene_f1 | lfc_mae | lfc_pearson | lfc_spearman | roc_auc | pr_auc | n_cells |
85
  | --- | --- | --- | --- | --- | --- | --- | --- |
86
+ | 0 | 0.00 | 0.82 | -0.19 | -0.19 | 0.55 | 0.29 | 70.00 |
87
+ | 1 | 0.00 | 0.84 | -0.06 | -0.04 | 0.55 | 0.31 | 61.00 |
88
+ | 2 | 0.00 | 0.91 | -0.06 | -0.14 | 0.41 | 0.18 | 60.00 |
89
+ | 3 | 0.10 | 0.94 | -0.09 | -0.10 | 0.49 | 0.28 | 46.00 |
90
+ | 4 | 0.10 | 0.91 | -0.02 | -0.01 | 0.44 | 0.26 | 45.00 |
91
+ | 5 | 0.10 | 0.83 | 0.18 | 0.14 | 0.49 | 0.40 | 41.00 |
92
+ | 6 | 0.10 | 1.07 | -0.24 | -0.25 | 0.46 | 0.23 | 31.00 |
93
+ | 7 | 0.10 | 1.10 | -0.03 | -0.07 | 0.19 | 0.02 | 24.00 |
94
+ | 8 | 0.20 | 1.00 | 0.11 | 0.12 | 0.38 | 0.12 | 22.00 |
 
 
 
95
 
96
  </details>
97
 
 
181
 
182
  # References
183
 
184
+ scvi-tools team