Hugging Face's logo

scvi-tools
/
heart-cell-atlas-scvi

scvi-tools
biology
genomics
single-cell
model_cls_name:SCVI
scvi_version:1.2.0
anndata_version:0.11.1
modality:rna
tissue:heart
annotated:True
Model card Files Community
canergen commited on
Commit
e1f875f
·
verified ·
1 Parent(s): d59eb56

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +17 -17
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 | 1.14 | 1.16 |
55
- | Pearson Correlation | 0.65 | 0.64 |
56
- | Spearman Correlation | 0.70 | 0.71 |
57
- | R² (R-Squared) | 0.12 | 0.14 |
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 | 2.68 |
67
  | Pearson Correlation | 0.85 |
68
  | Spearman Correlation | 0.95 |
69
- | R² (R-Squared) | -0.01 |
70
 
71
  </details>
72
 
@@ -83,17 +83,17 @@ cell-type.
83
 
84
  | Index | gene_f1 | lfc_mae | lfc_pearson | lfc_spearman | roc_auc | pr_auc | n_cells |
85
  | --- | --- | --- | --- | --- | --- | --- | --- |
86
- | Ventricular_Cardiomyocyte | 0.94 | 1.19 | 0.65 | 0.96 | 0.29 | 0.91 | 5307.00 |
87
- | Endothelial | 0.97 | 0.90 | 0.63 | 0.91 | 0.26 | 0.94 | 4109.00 |
88
- | Pericytes | 0.92 | 1.06 | 0.40 | 0.85 | 0.21 | 0.87 | 3204.00 |
89
- | Fibroblast | 0.94 | 1.28 | 0.60 | 0.93 | 0.35 | 0.90 | 2446.00 |
90
- | Atrial_Cardiomyocyte | 0.93 | 2.31 | 0.55 | 0.87 | 0.36 | 0.84 | 1009.00 |
91
- | Myeloid | 0.88 | 2.19 | 0.53 | 0.87 | 0.40 | 0.90 | 957.00 |
92
- | Lymphoid | 0.90 | 3.20 | 0.46 | 0.77 | 0.31 | 0.85 | 653.00 |
93
- | Smooth_muscle_cells | 0.85 | 2.90 | 0.53 | 0.74 | 0.33 | 0.80 | 641.00 |
94
- | Neuronal | 0.43 | 5.10 | 0.48 | 0.48 | 0.38 | 0.65 | 153.00 |
95
- | Adipocytes | 0.84 | 4.31 | 0.55 | 0.74 | 0.51 | 0.80 | 145.00 |
96
- | Mesothelial | 0.37 | 9.51 | 0.34 | 0.28 | 0.40 | 0.65 | 17.00 |
97
 
98
  </details>
99
 
 
51
 
52
  | Metric | Training Value | Validation Value |
53
  |-------------------------|----------------|------------------|
54
+ | Mean Absolute Error | 1.24 | 1.31 |
55
+ | Pearson Correlation | 0.52 | 0.49 |
56
+ | Spearman Correlation | 0.58 | 0.56 |
57
+ | R² (R-Squared) | -0.84 | -0.95 |
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 | 2.67 |
67
  | Pearson Correlation | 0.85 |
68
  | Spearman Correlation | 0.95 |
69
+ | R² (R-Squared) | 0.03 |
70
 
71
  </details>
72
 
 
83
 
84
  | Index | gene_f1 | lfc_mae | lfc_pearson | lfc_spearman | roc_auc | pr_auc | n_cells |
85
  | --- | --- | --- | --- | --- | --- | --- | --- |
86
+ | Ventricular_Cardiomyocyte | 0.96 | 1.33 | 0.65 | 0.96 | 0.29 | 0.91 | 5307.00 |
87
+ | Endothelial | 0.93 | 0.89 | 0.64 | 0.91 | 0.26 | 0.94 | 4109.00 |
88
+ | Pericytes | 0.94 | 1.08 | 0.48 | 0.85 | 0.22 | 0.87 | 3204.00 |
89
+ | Fibroblast | 0.94 | 1.38 | 0.60 | 0.91 | 0.36 | 0.90 | 2446.00 |
90
+ | Atrial_Cardiomyocyte | 0.95 | 2.28 | 0.49 | 0.84 | 0.38 | 0.84 | 1009.00 |
91
+ | Myeloid | 0.90 | 2.24 | 0.53 | 0.87 | 0.40 | 0.90 | 957.00 |
92
+ | Lymphoid | 0.92 | 3.25 | 0.47 | 0.76 | 0.31 | 0.85 | 653.00 |
93
+ | Smooth_muscle_cells | 0.84 | 2.98 | 0.51 | 0.73 | 0.36 | 0.81 | 641.00 |
94
+ | Neuronal | 0.51 | 5.32 | 0.44 | 0.46 | 0.38 | 0.67 | 153.00 |
95
+ | Adipocytes | 0.77 | 4.52 | 0.52 | 0.72 | 0.52 | 0.80 | 145.00 |
96
+ | Mesothelial | 0.29 | 10.24 | 0.30 | 0.20 | 0.39 | 0.64 | 17.00 |
97
 
98
  </details>
99