Added notebooks for several additional cancer types outside of AML, including CRC, BRCA, and SKCM

Author: Ashford-A

models/SKCM/SKCM_bulk_pipeline.pkl

@@ -829,7 +829,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "id": "7bece2e0",
    "metadata": {},
    "outputs": [
@@ -839,6 +839,15 @@
      "text": [
       "Loading count matrix ... (this may take 2-5 min)\n"
      ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "KeyboardInterrupt\n",
+      "\n"
+     ]
     }
    ],
    "source": [

models/SKCM/SKCM_heatmap.pdf

@@ -1744,7 +1744,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 23,
    "id": "90126937",
    "metadata": {},
    "outputs": [
@@ -1753,7 +1753,21 @@
      "output_type": "stream",
      "text": [
       "13:50:06 | INFO     | scope.pipeline.sc_pipeline — === SingleCellPipeline.fit ===\n",
-      "13:50:06 | INFO     | scope.preprocessing.single_cell — SingleCellPreprocessor fitted.\n"
+      "13:50:06 | INFO     | scope.preprocessing.single_cell — SingleCellPreprocessor fitted.\n",
+      "13:52:16 | INFO     | scope.utils.gene_utils — Gene universe: 16214 shared, 4316 bulk-only, 10470 sc-only\n",
+      "13:54:18 | INFO     | scope.preprocessing.alignment — BulkSCAligner fitted (method=moment_matching, n_genes=16214).\n",
+      "13:54:18 | INFO     | scope.pipeline.sc_pipeline — SingleCellPipeline.fit complete.\n",
+      "13:54:18 | INFO     | scope.pipeline.sc_pipeline — === SingleCellPipeline.transform ===\n",
+      "13:56:48 | WARNING  | scope.pipeline.sc_pipeline — 4316 / 20530 bulk genes absent from sc data (will be zero-padded).\n",
+      "14:10:27 | INFO     | scope.pipeline.sc_pipeline — Projected 200128 cells into 200-D latent space.\n",
+      "14:10:31 | INFO     | scope.pipeline.sc_pipeline — Inferred probabilities for 22 mutations.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Inferred mutation probability columns: ['mutation_prob_PIK3CA', 'mutation_prob_PIK3R1', 'mutation_prob_PTEN', 'mutation_prob_AKT1', 'mutation_prob_TP53', 'mutation_prob_CDH1', 'mutation_prob_ERBB2', 'mutation_prob_ERBB3', 'mutation_prob_KRAS', 'mutation_prob_BRAF', 'mutation_prob_GATA3', 'mutation_prob_RUNX1', 'mutation_prob_FOXA1', 'mutation_prob_BRCA1', 'mutation_prob_BRCA2', 'mutation_prob_PALB2', 'mutation_prob_ATM', 'mutation_prob_KMT2C', 'mutation_prob_ARID1A', 'mutation_prob_MAP3K1', 'mutation_prob_RB1', 'mutation_prob_CCND1']\n"
      ]
     }
    ],
@@ -1784,21 +1798,58 @@
    "execution_count": null,
    "id": "dc506e05",
    "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/opt/homebrew/Cellar/micromamba/2.5.0_1/envs/scope-dev/lib/python3.10/site-packages/umap/umap_.py:1952: UserWarning: n_jobs value 1 overridden to 1 by setting random_state. Use no seed for parallelism.\n",
+      "  warn(\n"
+     ]
+    }
+   ],
+   "source": [
+    "adata_sc = compute_umap(adata_sc, obsm_key=\"X_svd\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0de7b082-a42d-47b2-9e72-99144c24d937",
+   "metadata": {},
    "outputs": [],
    "source": [
-    "adata_sc = compute_umap(adata_sc, obsm_key=\"X_svd\")\n",
-    "\n",
     "ct_col = next((c for c in adata_sc.obs.columns\n",
     "               if \"celltype\" in c.lower() or \"cell_type\" in c.lower()), \"sample_id\")\n",
     "\n",
-    "fig, axes = plt.subplots(1, 2, figsize=(14, 5))\n",
+    "fig, axes = plt.subplots(2, 1, figsize=(14, 12))\n",
     "sc.pl.umap(adata_sc, color=ct_col,      ax=axes[0], show=False, title=\"Cell type\")\n",
     "sc.pl.umap(adata_sc, color=\"sample_id\", ax=axes[1], show=False, title=\"Patient\")\n",
     "plt.tight_layout()\n",
     "fig.savefig(os.path.join(MODELS_DIR, \"BRCA_umap_celltype.pdf\"), bbox_inches=\"tight\")\n",
     "plt.show()\n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c4b4b183-853a-49a1-9058-9580382ce2a3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(adata_sc)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "54269169-a965-4389-b2b9-eec4f674f07a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sc.pl.umap(adata_sc, color=\"sample_id\", ax=axes[1], show=False, title=\"Patient\")\n"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -1807,7 +1858,7 @@
    "outputs": [],
    "source": [
     "top_muts = (\n",
-    "    mutation_labels.sum().sort_values(ascending=False).head(6).index.tolist()\n",
+    "    mutation_labels.sum().sort_values(ascending=False).index.tolist()\n",
     ")\n",
     "fig = plot_mutation_probabilities(adata_sc, mutations=top_muts)\n",
     "fig.savefig(os.path.join(MODELS_DIR, \"BRCA_mutation_probs.pdf\"), bbox_inches=\"tight\")\n",
@@ -1822,6 +1873,7 @@
    "outputs": [],
    "source": [
     "fig, ax = plot_mutation_heatmap(adata_sc, cluster_key=ct_col, mutations=top_muts)\n",
+    "fig.set_size_inches(20, 8)  # width, height in inches\n",
     "fig.savefig(os.path.join(MODELS_DIR, \"BRCA_heatmap.pdf\"), bbox_inches=\"tight\")\n",
     "plt.show()\n"
    ]