Merge pull request #8 from rsinghlab/refactor

further refactoring and batch improvement
rsinghlab · Nov 5, 2024 · f4979fc · f4979fc
2 parents 3485f77 + b1d5421
commit f4979fc
Show file tree

Hide file tree

Showing 1,456 changed files with 237 additions and 376,632 deletions.
diff --git a/Analysis.ipynb b/Analysis.ipynb
@@ -137,9 +137,7 @@
    "source": [
     "# Convert the data to a DataFrame for easier manipulation\n",
     "adata.obs = adata.obs.reset_index(drop=False)\n",
-    "df_expression = pd.DataFrame(\n",
-    "    adata.X.todense(), columns=adata.var_names\n",
-    ")\n",
+    "df_expression = pd.DataFrame(adata.X.todense(), columns=adata.var_names)\n",
     "df_expression[\"sex\"] = adata.obs[\"sex\"]\n",
     "df_expression[\"age\"] = adata.obs[\"age\"]\n",
     "\n",
@@ -200,7 +198,6 @@
     }
    ],
    "source": [
-    "\n",
     "# Plot gene expression over age by sex in a subplot grid\n",
     "import math\n",
     "\n",
@@ -212,7 +209,7 @@
     "rows = math.ceil(num_genes / cols)\n",
     "\n",
     "# Create subplots\n",
-    "fig, axes = plt.subplots(rows, cols, figsize=(5*cols, 4*rows))\n",
+    "fig, axes = plt.subplots(rows, cols, figsize=(5 * cols, 4 * rows))\n",
     "axes = axes.flatten()\n",
     "\n",
     "# Colors for sexes\n",
@@ -387,7 +384,7 @@
     "rows = math.ceil(num_genes / cols)\n",
     "\n",
     "# Create subplots\n",
-    "fig, axes = plt.subplots(rows, cols, figsize=(4*cols, 4*rows))\n",
+    "fig, axes = plt.subplots(rows, cols, figsize=(4 * cols, 4 * rows))\n",
     "axes = axes.flatten()  # Flatten in case of single row\n",
     "\n",
     "for idx, gene in enumerate(valid_matched_genes):\n",
@@ -421,7 +418,9 @@
     "\n",
     "# Calculate total variance explained\n",
     "total_variance_explained = sum(adata_vis.uns[\"pca\"][\"variance_ratio\"])\n",
-    "print(f\"Total variance explained by the first 50 PCs: {total_variance_explained*100:.2f}%\")\n",
+    "print(\n",
+    "    f\"Total variance explained by the first 50 PCs: {total_variance_explained*100:.2f}%\"\n",
+    ")\n",
     "\n",
     "# Compute the neighborhood graph and UMAP\n",
     "sc.pp.neighbors(adata_vis, n_pcs=50)\n",
@@ -511,7 +510,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.9.17"
   },
   "orig_nbformat": 4
  },

diff --git a/Analysis/batch_corrected/.DS_Store b/Analysis/batch_corrected/.DS_Store
diff --git a/Analysis/batch_corrected/body/CNN/age/full_data/celltype_all/sextype_all/Analysis/Stats.JSON b/Analysis/batch_corrected/body/CNN/age/full_data/celltype_all/sextype_all/Analysis/Stats.JSON
diff --git a/...d/body/CNN/age/full_data/celltype_all/sextype_all/Analysis/confusion_matrix.png b/...d/body/CNN/age/full_data/celltype_all/sextype_all/Analysis/confusion_matrix.png
diff --git a/...orrected/body/CNN/age/full_data/celltype_all/sextype_all/Analysis/roc_curve.png b/...orrected/body/CNN/age/full_data/celltype_all/sextype_all/Analysis/roc_curve.png
diff --git a/...d/body/CNN/age/full_data/celltype_all/sextype_all/Analysis/training_metrics.png b/...d/body/CNN/age/full_data/celltype_all/sextype_all/Analysis/training_metrics.png
diff --git a/...corrected/head/CNN/age/full_data/celltype_all/Analysis/SHAP/SHAP_Summary_30.png b/...corrected/head/CNN/age/full_data/celltype_all/Analysis/SHAP/SHAP_Summary_30.png
diff --git a/..._corrected/head/CNN/age/full_data/celltype_all/Analysis/SHAP/SHAP_Summary_5.png b/..._corrected/head/CNN/age/full_data/celltype_all/Analysis/SHAP/SHAP_Summary_5.png
diff --git a/...corrected/head/CNN/age/full_data/celltype_all/Analysis/SHAP/SHAP_Summary_50.png b/...corrected/head/CNN/age/full_data/celltype_all/Analysis/SHAP/SHAP_Summary_50.png
diff --git a/...corrected/head/CNN/age/full_data/celltype_all/Analysis/SHAP/SHAP_Summary_70.png b/...corrected/head/CNN/age/full_data/celltype_all/Analysis/SHAP/SHAP_Summary_70.png
diff --git a/...cted/head/CNN/age/full_data/celltype_all/Analysis/SHAP/SHAP_Summary_Overall.png b/...cted/head/CNN/age/full_data/celltype_all/Analysis/SHAP/SHAP_Summary_Overall.png
diff --git a/Analysis/batch_corrected/head/CNN/age/full_data/celltype_all/Analysis/Stats.JSON b/Analysis/batch_corrected/head/CNN/age/full_data/celltype_all/Analysis/Stats.JSON
diff --git a/...tch_corrected/head/CNN/age/full_data/celltype_all/Analysis/confusion_matrix.png b/...tch_corrected/head/CNN/age/full_data/celltype_all/Analysis/confusion_matrix.png
diff --git a/...ysis/batch_corrected/head/CNN/age/full_data/celltype_all/Analysis/roc_curve.png b/...ysis/batch_corrected/head/CNN/age/full_data/celltype_all/Analysis/roc_curve.png
diff --git a/...tch_corrected/head/CNN/age/full_data/celltype_all/Analysis/training_metrics.png b/...tch_corrected/head/CNN/age/full_data/celltype_all/Analysis/training_metrics.png
diff --git a/Analysis/uncorrected/.DS_Store b/Analysis/uncorrected/.DS_Store
diff --git a/Analysis/uncorrected/all/CNN/age/full_data/celltype_all/sextype_all/Results/Stats.JSON b/Analysis/uncorrected/all/CNN/age/full_data/celltype_all/sextype_all/Results/Stats.JSON
diff --git a/...ted/all/CNN/age/full_data/celltype_all/sextype_all/Results/confusion_matrix.png b/...ted/all/CNN/age/full_data/celltype_all/sextype_all/Results/confusion_matrix.png