add preprocessing tutorial with multiple examples

r/DestVI_in_R.ipynb

@@ -19,10 +19,23 @@
     "## Loading and processing data with Seurat"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "```{note}\n",
+    "For general pre-processing for various datatypes used by scvi-tools models, see the [preprocessing tutorial](https://docs.scvi-tools.org/en/stable/tutorials/notebooks/use_cases/preprocessing.html#spatial-transcriptomics).\n",
+    "```"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [],
    "source": [
     "# install.packages(\"Seurat\")\n",
@@ -41,7 +54,11 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [
     {
      "name": "stderr",
@@ -109,7 +126,11 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [],
    "source": [
     "cortex_sc_data <- readRDS(url(\"https://www.dropbox.com/s/cuowvm4vrf65pvq/allen_cortex.rds?dl=1\"))"
@@ -119,7 +140,10 @@
    "cell_type": "code",
    "execution_count": 4,
    "metadata": {
-    "tags": []
+    "tags": [],
+    "vscode": {
+     "languageId": "r"
+    }
    },
    "outputs": [
     {
@@ -235,7 +259,10 @@
    "cell_type": "code",
    "execution_count": 5,
    "metadata": {
-    "tags": []
+    "tags": [],
+    "vscode": {
+     "languageId": "r"
+    }
    },
    "outputs": [
     {
@@ -332,7 +359,10 @@
    "cell_type": "code",
    "execution_count": 6,
    "metadata": {
-    "tags": []
+    "tags": [],
+    "vscode": {
+     "languageId": "r"
+    }
    },
    "outputs": [
     {
@@ -3840,7 +3870,11 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [
     {
      "data": {
@@ -3862,7 +3896,10 @@
    "cell_type": "code",
    "execution_count": 8,
    "metadata": {
-    "tags": []
+    "tags": [],
+    "vscode": {
+     "languageId": "r"
+    }
    },
    "outputs": [
     {
@@ -3886,7 +3923,11 @@
   {
    "cell_type": "code",
    "execution_count": 9,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [],
    "source": [
     "cortex_sc_data <- NormalizeData(cortex_sc_data, normalization.method = \"LogNormalize\", scale.factor = 10000)\n",
@@ -3898,7 +3939,11 @@
   {
    "cell_type": "code",
    "execution_count": 10,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [
     {
      "data": {
@@ -3929,7 +3974,11 @@
   {
    "cell_type": "code",
    "execution_count": 11,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [
     {
      "name": "stderr",
@@ -3973,7 +4022,11 @@
   {
    "cell_type": "code",
    "execution_count": 12,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [],
    "source": [
     "library(reticulate)\n",
@@ -3994,7 +4047,11 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [],
    "source": [
     "cortex_sc_adata <- convertFormat(cortex_sc_data, from=\"seurat\", to=\"anndata\", main_layer=\"counts\", drop_single_values=FALSE)\n",
@@ -4011,7 +4068,11 @@
   {
    "cell_type": "code",
    "execution_count": 14,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [
     {
      "data": {
@@ -4037,7 +4098,11 @@
   {
    "cell_type": "code",
    "execution_count": 15,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [
     {
      "data": {
@@ -4057,7 +4122,11 @@
   {
    "cell_type": "code",
    "execution_count": 16,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [
     {
      "name": "stderr",
@@ -4104,7 +4173,11 @@
   {
    "cell_type": "code",
    "execution_count": 17,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [
     {
      "data": {
@@ -4123,7 +4196,11 @@
   {
    "cell_type": "code",
    "execution_count": 18,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [
     {
      "data": {
@@ -4143,7 +4220,11 @@
   {
    "cell_type": "code",
    "execution_count": 19,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [
     {
      "name": "stderr",
@@ -4190,7 +4271,11 @@
   {
    "cell_type": "code",
    "execution_count": 20,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [],
    "source": [
     "cortex_st_adata$obsm[\"proportions\"] <- stlvm$get_proportions()"
@@ -4199,7 +4284,11 @@
   {
    "cell_type": "code",
    "execution_count": 21,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [
     {
      "data": {
@@ -4297,7 +4386,11 @@
   {
    "cell_type": "code",
    "execution_count": 22,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [],
    "source": [
     "cortex_st_data[[\"predictions\"]] <- CreateAssayObject(data = t(py_to_r(cortex_st_adata$obsm$get(\"proportions\"))))"
@@ -4306,7 +4399,11 @@
   {
    "cell_type": "code",
    "execution_count": 27,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [
     {
      "name": "stderr",
@@ -4360,7 +4457,11 @@
   {
    "cell_type": "code",
    "execution_count": 30,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [
     {
      "name": "stderr",
@@ -4400,7 +4501,11 @@
   {
    "cell_type": "code",
    "execution_count": 36,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [
     {
      "data": {
@@ -4510,7 +4615,11 @@
   {
    "cell_type": "code",
    "execution_count": 43,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [],
    "source": [
     "ct_name <- \"L6 IT\"\n",
@@ -4527,7 +4636,11 @@
   {
    "cell_type": "code",
    "execution_count": 44,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [],
    "source": [
     "filtered_st_data <- cortex_st_data[, indices]\n",
@@ -4537,7 +4650,11 @@
   {
    "cell_type": "code",
    "execution_count": 45,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [
     {
      "name": "stderr",
@@ -4578,7 +4695,11 @@
   {
    "cell_type": "code",
    "execution_count": 46,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -4612,7 +4733,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
    "outputs": [],
    "source": []
   }