From 8feb6233ad8b5cbb9a87373ac7a8c67aca9341a0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Maycon=20Mar=C3=A7=C3=A3o?=
 <68165646+Mmaycon@users.noreply.github.com>
Date: Wed, 11 Dec 2024 15:27:32 -0600
Subject: [PATCH] Delete notebooks/GeneOutlierDetection_example.ipynb

---
 notebooks/GeneOutlierDetection_example.ipynb | 696 -------------------
 1 file changed, 696 deletions(-)
 delete mode 100644 notebooks/GeneOutlierDetection_example.ipynb

diff --git a/notebooks/GeneOutlierDetection_example.ipynb b/notebooks/GeneOutlierDetection_example.ipynb
deleted file mode 100644
index 797a0e6..0000000
--- a/notebooks/GeneOutlierDetection_example.ipynb
+++ /dev/null
@@ -1,696 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 33,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# conda activate SpaceHack_MM\n",
-    "import numpy as np\n",
-    "import pandas as pd\n",
-    "import scanpy as sc\n",
-    "from sklearn.linear_model import RANSACRegressor, LinearRegression \n",
-    "import matplotlib.pyplot as plt\n",
-    "from sklearn.preprocessing import StandardScaler\n",
-    "from scipy import sparse\n",
-    "import numpy as np\n",
-    "import pandas as pd\n",
-    "import libpysal as lps\n",
-    "from esda import Moran\n",
-    "import seaborn as sns\n",
-    "from scipy.stats import pearsonr\n",
-    "import squidpy as sq\n",
-    "from matplotlib.lines import Line2D\n",
-    "\n",
-    "from spatial_compare import  SpatialCompare, spatial_detection_scores, detect_outliers\n",
-    "#If detect_outliers() is not working from spatial_compare, simply uncomment the function in the cell above."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 34,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def load_h5ad_data(file_path):\n",
-    "    adata = sc.read_h5ad(file_path)\n",
-    "    return adata\n",
-    "\n",
-    "\n",
-    "# def detect_outliers(adata1, adata2, transform_type='none', gene_name='', inlier_threshold=0.7, display_others_plot=False, display_outlier_plot=False):\n",
-    "#     \"\"\"\n",
-    "#     Detect outliers in gene expression data using RANSAC regression.\n",
-    "\n",
-    "#     Parameters:\n",
-    "#     - adata1: AnnData object for dataset 1.\n",
-    "#     - adata2: AnnData object for dataset 2.\n",
-    "#     - transform_type: Type of transformation to apply ('scale', 'log', or 'none').\n",
-    "#     - gene_name: Specific gene to visualize (if empty, visualizes the first inlier).\n",
-    "#     - inlier_threshold: Proportion of inliers required to classify a gene as an inlier. It’s a percentage of cells that got an \"Inlier\" label from RANSAC for a given gene based on their expression level. If your proportion_inliers >= inlier_threshold, the gene going through the loop will be labeled as an inlier. Otherwise, it'll be labeled as an outlier.\n",
-    "#     - display_others_plot: Boolean indicating whether to display the plot for a specific gene. Work in progress.\n",
-    "#     - display_outlier_plot: Boolean indicating whether to display the outlier plot.\n",
-    "\n",
-    "#     Returns:\n",
-    "#     - Prints lists of inlier and outlier genes.\n",
-    "#     \"\"\"\n",
-    "    \n",
-    "#     # Function to ensure dense matrix\n",
-    "#     def ensure_dense(matrix):\n",
-    "#         return matrix.toarray() if hasattr(matrix, 'toarray') else matrix\n",
-    "\n",
-    "#     # Prepare inputs\n",
-    "#     X = ensure_dense(adata1.X)  # Convert adata1.X to dense if necessary\n",
-    "#     Y = ensure_dense(adata2.X)  # Convert adata2.X to dense if necessary\n",
-    "\n",
-    "#     genes1 = adata1.var_names\n",
-    "#     genes2 = adata2.var_names\n",
-    "\n",
-    "#     # Create DataFrames\n",
-    "#     df1 = pd.DataFrame(X, columns=genes1)\n",
-    "#     df2 = pd.DataFrame(Y, columns=genes2)\n",
-    "    \n",
-    "#     # Remove genes containing 'UnassignedCodeword' from both datasets\n",
-    "#     mask1 = ~df1.columns.str.contains('UnassignedCodeword|NegControlProbe|NegControlCodeword', case=False)\n",
-    "#     mask2 = ~df2.columns.str.contains('UnassignedCodeword|NegControlProbe|NegControlCodeword', case=False)\n",
-    "\n",
-    "#     df1 = df1.loc[:, mask1]\n",
-    "#     df2 = df2.loc[:, mask2]\n",
-    "\n",
-    "#     # Find common genes after filtering\n",
-    "#     common_genes = list(set(df1.columns).intersection(set(df2.columns)))\n",
-    "\n",
-    "#     # Initialize lists to store results\n",
-    "#     inlier_genes = []\n",
-    "#     outlier_genes = []\n",
-    "\n",
-    "#     # Analyze each common gene independently\n",
-    "#     for gene in common_genes:\n",
-    "#         # Extract expression levels for the current gene\n",
-    "#         X_gene = df1[gene].dropna().to_numpy()  # Drop NaN values if any\n",
-    "#         Y_gene = df2[gene].dropna().to_numpy()  # Drop NaN values if any\n",
-    "\n",
-    "#         # If either dataset has no data for this gene, skip it\n",
-    "#         if len(X_gene) == 0 or len(Y_gene) == 0:\n",
-    "#             continue\n",
-    "\n",
-    "#         # Apply transformations based on the transform_type parameter\n",
-    "#         if transform_type == 'log':\n",
-    "#             X_gene = np.log1p(X_gene)  # log(1 + x) handles zero values safely\n",
-    "#             Y_gene = np.log1p(Y_gene)\n",
-    "#         elif transform_type == 'scale':\n",
-    "#             scaler = StandardScaler()\n",
-    "#             X_gene = scaler.fit_transform(X_gene.reshape(-1, 1))\n",
-    "#             Y_gene = scaler.fit_transform(Y_gene.reshape(-1, 1))\n",
-    "\n",
-    "#         # Use only the minimum length of the two arrays for fitting\n",
-    "#         min_length = min(len(X_gene), len(Y_gene))\n",
-    "\n",
-    "#         # Fit RANSAC regressor for the current gene using only available data\n",
-    "#         ransac = RANSACRegressor(random_state=42)\n",
-    "#         ransac.fit(X_gene[:min_length].reshape(-1, 1), Y_gene[:min_length].reshape(-1, 1))\n",
-    "\n",
-    "#         # Extract inliers and outliers for this gene\n",
-    "#         inlier_mask = ransac.inlier_mask_\n",
-    "\n",
-    "#         # Calculate proportion of inliers\n",
-    "#         proportion_inliers = np.sum(inlier_mask) / min_length\n",
-    "        \n",
-    "#         # Check if proportion of inliers meets threshold\n",
-    "#         if proportion_inliers >= inlier_threshold:\n",
-    "#             inlier_genes.append(gene)\n",
-    "#         else:\n",
-    "#             outlier_genes.append(gene)\n",
-    "\n",
-    "#     # Select a specific gene to visualize (if provided)\n",
-    "#     selected_gene = gene_name if gene_name else (inlier_genes[0] if inlier_genes else None)\n",
-    "\n",
-    "#     if selected_gene and display_others_plot:\n",
-    "#         X_selected = df1[selected_gene].dropna().to_numpy().reshape(-1, 1)\n",
-    "#         Y_selected = df2[selected_gene].dropna().to_numpy().reshape(-1, 1)\n",
-    "\n",
-    "#         # Apply transformations for visualization based on transform_type\n",
-    "#         if transform_type == 'log':\n",
-    "#             X_selected = np.log1p(X_selected)\n",
-    "#             Y_selected = np.log1p(Y_selected)\n",
-    "#         elif transform_type == 'scale':\n",
-    "#             scaler = StandardScaler()\n",
-    "#             X_selected = scaler.fit_transform(X_selected)\n",
-    "#             Y_selected = scaler.fit_transform(Y_selected)\n",
-    "\n",
-    "#         # Align lengths for visualization\n",
-    "#         min_length = min(len(X_selected), len(Y_selected))\n",
-    "\n",
-    "#         ransac.fit(X_selected[:min_length], Y_selected[:min_length])\n",
-    "#         inlier_mask_visual = ransac.inlier_mask_\n",
-    "\n",
-    "#         plt.figure(figsize=(8, 5))\n",
-    "#         plt.scatter(X_selected[inlier_mask_visual], Y_selected[inlier_mask_visual], color='blue', label='Inliers')\n",
-    "#         plt.scatter(X_selected[~inlier_mask_visual], Y_selected[~inlier_mask_visual], color='red', label='Outliers')\n",
-    "\n",
-    "#         # Plotting the RANSAC fit line based on transformed data\n",
-    "#         plt.plot(X_selected, ransac.predict(X_selected), color='green', label='RANSAC fit')\n",
-    "\n",
-    "#         plt.xlabel(f'Gene Expression (Dataset 1) - {selected_gene}')\n",
-    "#         plt.ylabel(f'Gene Expression (Dataset 2) - {selected_gene}')\n",
-    "#         plt.title(f'RANSAC Outlier Detection for {selected_gene}')\n",
-    "#         plt.legend()\n",
-    "#         plt.show()\n",
-    "#     else:\n",
-    "#         print(\"No inliers found to visualize or plotting is disabled.\")\n",
-    "\n",
-    "#         # Print outlier and inlier genes\n",
-    "#         print(\"Inlier Genes:\", inlier_genes)\n",
-    "#         print(\"Inlier nGenes:\", len(inlier_genes))\n",
-    "#         print(\"Outlier Genes:\", outlier_genes)\n",
-    "#         print(\"Outlier nGenes:\", len(outlier_genes))\n",
-    "\n",
-    "#     if display_outlier_plot:\n",
-    "    \n",
-    "#         # Step 1: Extract common genes\n",
-    "#         common_genes = adata1.var_names.intersection(adata2.var_names)\n",
-    "\n",
-    "#         # Step 2: Sort common genes\n",
-    "#         sorted_common_genes = sorted(common_genes)\n",
-    "\n",
-    "#         # Step 3: Reorder AnnData objects based on sorted common genes\n",
-    "#         adata1_sorted = adata1[:, sorted_common_genes]\n",
-    "#         adata2_sorted = adata2[:, sorted_common_genes]\n",
-    "\n",
-    "#         # Step 4: Calculate average expression for sorted common genes\n",
-    "#         avg_expr_adata1 = np.asarray(adata1_sorted.X.mean(axis=0)).flatten()\n",
-    "#         avg_expr_adata2 = np.asarray(adata2_sorted.X.mean(axis=0)).flatten()\n",
-    "\n",
-    "#         # Check shapes\n",
-    "#         print(\"Shape of avg_expr_adata1:\", avg_expr_adata1.shape)\n",
-    "#         print(\"Shape of avg_expr_adata2:\", avg_expr_adata2.shape)\n",
-    "\n",
-    "#         # Step 5: Log-transform the average expression values\n",
-    "#         log_avg_expr_adata1 = np.log1p(avg_expr_adata1)  # log(1 + x)\n",
-    "#         log_avg_expr_adata2 = np.log1p(avg_expr_adata2)\n",
-    "\n",
-    "#         # Step 6: Create a DataFrame with ordered data\n",
-    "#         data = pd.DataFrame({\n",
-    "#             'gene': sorted_common_genes,\n",
-    "#             'adata1_avg': log_avg_expr_adata1,\n",
-    "#             'adata2_avg': log_avg_expr_adata2\n",
-    "#         })\n",
-    "\n",
-    "#         # Step 7: Create a new column for color based on outlier genes\n",
-    "#         data['color'] = np.where(data['gene'].isin(outlier_genes), 'red', 'blue')\n",
-    "\n",
-    "#         # Step 8: Create scatter plot with colors for outliers and inliers\n",
-    "#         plt.figure(figsize=(8, 6))\n",
-    "        \n",
-    "#         sns.scatterplot(data=data, x='adata1_avg', y='adata2_avg', hue='color', palette={'red': 'red', 'blue': 'blue'}, legend=False)\n",
-    "\n",
-    "#         # Step 9: Annotate outlier genes on the plot\n",
-    "#         for index, row in data.iterrows():\n",
-    "#             if row['color'] == 'red':\n",
-    "#                 plt.text(row['adata1_avg'], row['adata2_avg'], row['gene'], fontsize=9, ha='right', va='bottom')\n",
-    "\n",
-    "#         # Step 10: Calculate and display correlation coefficient on log-transformed data\n",
-    "#         correlation = np.corrcoef(data['adata1_avg'], data['adata2_avg'])[0, 1]\n",
-    "#         plt.title(f'Scatter Plot of Log-Transformed Average Gene Expression\\nCorrelation: {correlation:.2f}')\n",
-    "#         plt.xlabel('Log-Transformed Average Expression in adata1')\n",
-    "#         plt.ylabel('Log-Transformed Average Expression in adata2')\n",
-    "#         plt.grid(True)\n",
-    "\n",
-    "#         # Custom legend handles to match colors\n",
-    "#         legend_elements = [\n",
-    "#             Line2D([0], [0], marker='o', color='w', label='Inlier Genes', markerfacecolor='blue', markersize=10),\n",
-    "#             Line2D([0], [0], marker='o', color='w', label='Outlier Genes', markerfacecolor='red', markersize=10)\n",
-    "#         ]\n",
-    "\n",
-    "#         plt.legend(handles=legend_elements, title='Gene Type')\n",
-    "#         plt.show()\n",
-    "    \n",
-    "#     return inlier_genes, outlier_genes\n",
-    "\n",
-    "\n",
-    "\n",
-    "\n",
-    "\n",
-    "def calculate_moran_scores(gene_list, adata, distance_threshold, x_coord_col='x_centroid', y_coord_col='y_centroid'):\n",
-    "    \"\"\"\n",
-    "    Calculate Moran's I scores for a list of genes in a given AnnData object.\n",
-    "\n",
-    "    Parameters:\n",
-    "    - gene_list: List of genes to analyze.\n",
-    "    - adata: AnnData object containing the expression data and spatial coordinates.\n",
-    "    - distance_threshold: Distance threshold for creating spatial weights.\n",
-    "    - x_coord_col: Name of the column in adata.obs for x coordinates.\n",
-    "    - y_coord_col: Name of the column in adata.obs for y coordinates.\n",
-    "\n",
-    "    Returns:\n",
-    "    - DataFrame containing Moran's I scores and p-values for each gene.\n",
-    "    \"\"\"\n",
-    "    \n",
-    "    # Step 1: Filter the AnnData object for the genes of interest\n",
-    "    filtered_genes = [gene for gene in gene_list if gene in adata.var_names]\n",
-    "\n",
-    "    # Extract the expression data for the filtered genes\n",
-    "    gene_expression = adata[:, filtered_genes].X  # This will give a sparse matrix\n",
-    "\n",
-    "    # Convert sparse matrix to dense if necessary\n",
-    "    if hasattr(gene_expression, 'toarray'):\n",
-    "        gene_expression = gene_expression.toarray()  # Convert to dense if it's sparse\n",
-    "\n",
-    "    # Step 2: Extract coordinates from adata.obs using specified columns\n",
-    "    coords = adata.obs[[x_coord_col, y_coord_col]].values\n",
-    "\n",
-    "    # Step 3: Create a spatial weights matrix (distance-based)\n",
-    "    w = lps.weights.DistanceBand(coords, threshold=distance_threshold)\n",
-    "\n",
-    "    # Step 4: Calculate Moran's I for each gene of interest\n",
-    "    results = []\n",
-    "    \n",
-    "    for i, gene in enumerate(filtered_genes):\n",
-    "        moran = Moran(gene_expression[:, i], w)\n",
-    "        results.append({\n",
-    "            'Gene': gene,\n",
-    "            'Moran_I': moran.I,\n",
-    "            'p_value': moran.p_sim\n",
-    "        })\n",
-    "\n",
-    "    # Convert results to DataFrame\n",
-    "    results_df = pd.DataFrame(results)\n",
-    "    \n",
-    "    return results_df\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 35,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "## Load data \n",
-    "\n",
-    "## Touchstone project data\n",
-    "file_path_1 = '/mnt/scratch1/maycon/SpaceHack/spatial_compare/data/UOA_CR_FFPE_BR_1_SYD_C_R1_adata1.h5ad'\n",
-    "file_path_2 = '/mnt/scratch1/maycon/SpaceHack/spatial_compare/data/UOA_XR_FFPE_BR_1_SYD_C_R1_adata2.h5ad'\n",
-    "adata1 = load_h5ad_data(file_path_1) # breast CosMx (downsized data)\n",
-    "adata2 = load_h5ad_data(file_path_2) # breast Xenium (downsized data)\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 36,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "No inliers found to visualize or plotting is disabled.\n",
-      "Inlier Genes: ['CCR7', 'ITGAX', 'VWF', 'IL7R', 'CD8A', 'C1QA', 'KRT7', 'FOXP3', 'MKI67', 'NCAM1', 'CX3CR1', 'S100A8', 'PRF1', 'PTGDS', 'MS4A1', 'PGR', 'CPA3', 'KRT8', 'MMP12', 'CD68', 'C1QC', 'BASP1', 'CCL8', 'DPT', 'PDCD1', 'CD14', 'KDR', 'CD3G', 'CD163', 'NDUFA4L2', 'NKG7', 'AIF1', 'CD19', 'ITGAM', 'CTSG', 'PECAM1', 'EGFR', 'CXCL5', 'PPARG', 'CD86', 'CD9', 'LTB', 'FASN', 'IGF1', 'ACTG2', 'ADGRE5', 'IL2RG', 'HAVCR2', 'CD79A', 'SQLE', 'KRT14', 'AQP3', 'KLRF1', 'PIGR', 'CD69', 'CENPF', 'FCER1G', 'GZMA', 'ESR1', 'APOC1', 'GNLY', 'CEACAM6', 'AR', 'MMP1', 'TACSTD2', 'SERPINA3', 'CLEC14A', 'MRC1', 'LAG3', 'RAMP2', 'ANGPT2', 'KRT23', 'TCF7', 'CD93', 'KLRB1', 'MZB1', 'CD27', 'CD80', 'TNFRSF17', 'GATA3', 'S100A4', 'DUSP5', 'GPR183', 'KIT', 'PDCD1LG2', 'SELL', 'IL3RA', 'PDGFRA', 'CD83', 'TIGIT', 'CD3E', 'CD4', 'CXCR4', 'IL2RA', 'EPCAM', 'TOP2A', 'TCL1A', 'CCL5', 'CXCL16', 'CDH1', 'SNAI1', 'GZMK', 'CTLA4', 'ADIPOQ', 'KRT5', 'CD274', 'CAV1', 'MYH11', 'DUSP2', 'CCND1']\n",
-      "Inlier nGenes: 110\n",
-      "Outlier Genes: ['CXCL12', 'DST', 'LYZ', 'ACTA2', 'PDGFRB', 'CCDC80', 'MMP2', 'ERBB2', 'LUM', 'PTPRC']\n",
-      "Outlier nGenes: 10\n",
-      "Shape of avg_expr_adata1: (120,)\n",
-      "Shape of avg_expr_adata2: (120,)\n"
-     ]
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 800x600 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "## Detect Outlier Genes \n",
-    "inlier_genes, outlier_genes = detect_outliers(adata1, adata2, transform_type='none', gene_name='', inlier_threshold=0.7, display_others_plot=False, display_outlier_plot=True)\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 37,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "      Gene   Moran_I  p_value\n",
-      "0     CCR7 -0.000242    0.500\n",
-      "1    ITGAX  0.000792    0.323\n",
-      "2      VWF  0.003432    0.063\n",
-      "3     IL7R  0.001454    0.211\n",
-      "4     CD8A  0.004243    0.030\n",
-      "..     ...       ...      ...\n",
-      "105  CD274  0.001459    0.226\n",
-      "106   CAV1  0.002651    0.115\n",
-      "107  MYH11  0.003631    0.054\n",
-      "108  DUSP2  0.002808    0.103\n",
-      "109  CCND1  0.026340    0.001\n",
-      "\n",
-      "[110 rows x 3 columns]\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/mnt/scratch1/miniconda3/envs/SpaceHack_MM/lib/python3.11/site-packages/libpysal/weights/util.py:826: UserWarning: The weights matrix is not fully connected: \n",
-      " There are 2 disconnected components.\n",
-      " There is 1 island with id: 6.\n",
-      "  w = W(neighbors, weights, ids, **kwargs)\n",
-      "/mnt/scratch1/miniconda3/envs/SpaceHack_MM/lib/python3.11/site-packages/libpysal/weights/distance.py:844: UserWarning: The weights matrix is not fully connected: \n",
-      " There are 2 disconnected components.\n",
-      " There is 1 island with id: 6.\n",
-      "  W.__init__(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "('WARNING: ', 6, ' is an island (no neighbors)')\n",
-      "      Gene   Moran_I  p_value\n",
-      "0     CCR7  0.017073    0.002\n",
-      "1    ITGAX  0.042209    0.001\n",
-      "2      VWF  0.081410    0.001\n",
-      "3     IL7R  0.118944    0.001\n",
-      "4     CD8A  0.036440    0.001\n",
-      "..     ...       ...      ...\n",
-      "105  CD274  0.015878    0.002\n",
-      "106   CAV1  0.063528    0.001\n",
-      "107  MYH11  0.131886    0.001\n",
-      "108  DUSP2  0.028345    0.001\n",
-      "109  CCND1  0.153887    0.001\n",
-      "\n",
-      "[110 rows x 3 columns]\n"
-     ]
-    }
-   ],
-   "source": [
-    "## Run calculate_moran_scores - inlier_genes\n",
-    "moran_results_1_fIn = calculate_moran_scores(inlier_genes, adata1, 100, x_coord_col='CenterX_global_px', y_coord_col='CenterX_global_px')\n",
-    "print(moran_results_1_fIn)\n",
-    "\n",
-    "moran_results_2_fIn = calculate_moran_scores(inlier_genes, adata2, 100, x_coord_col='x_centroid', y_coord_col='y_centroid')\n",
-    "print(moran_results_2_fIn)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "46\n",
-      "59\n",
-      "94\n",
-      "11\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Moran's stats \n",
-    "print((moran_results_1_fIn['p_value'] <= 0.05).sum())\n",
-    "print((moran_results_1_fIn['p_value'] > 0.05).sum())\n",
-    "\n",
-    "print((moran_results_2_fIn['p_value'] <= 0.05).sum())\n",
-    "print((moran_results_2_fIn['p_value'] > 0.05).sum())\n",
-    "\n",
-    "# Filter results by statistical sig\n",
-    "moran_results_1_fIn = pd.DataFrame(moran_results_1_fIn)\n",
-    "filtered_res_1_fIn = moran_results_1_fIn[moran_results_1_fIn['p_value'] <= 0.05]\n",
-    "\n",
-    "moran_results_2_fIn = pd.DataFrame(moran_results_2_fIn)\n",
-    "filtered_res_2_fIn = moran_results_2_fIn[moran_results_2_fIn['p_value'] <= 0.05]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "       Gene   Moran_I  p_value\n",
-      "0       DST  0.004361    0.040\n",
-      "1   TACSTD2  0.037557    0.001\n",
-      "2     ERBB2  0.048934    0.001\n",
-      "3     GATA3  0.028035    0.001\n",
-      "4       LUM  0.035582    0.001\n",
-      "5       LYZ  0.005770    0.016\n",
-      "6     CCND1  0.026340    0.001\n",
-      "7     PTPRC  0.000380    0.379\n",
-      "8      KRT8  0.044091    0.001\n",
-      "9      MMP2  0.022994    0.001\n",
-      "10    BASP1  0.008584    0.002\n",
-      "11   CXCL12  0.024871    0.001\n",
-      "12   FCER1G  0.004530    0.029\n",
-      "13      CD4  0.002465    0.105\n",
-      "14   PDGFRB  0.012646    0.001\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/mnt/scratch1/miniconda3/envs/SpaceHack_MM/lib/python3.11/site-packages/libpysal/weights/util.py:826: UserWarning: The weights matrix is not fully connected: \n",
-      " There are 2 disconnected components.\n",
-      " There is 1 island with id: 6.\n",
-      "  w = W(neighbors, weights, ids, **kwargs)\n",
-      "/mnt/scratch1/miniconda3/envs/SpaceHack_MM/lib/python3.11/site-packages/libpysal/weights/distance.py:844: UserWarning: The weights matrix is not fully connected: \n",
-      " There are 2 disconnected components.\n",
-      " There is 1 island with id: 6.\n",
-      "  W.__init__(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "('WARNING: ', 6, ' is an island (no neighbors)')\n",
-      "       Gene   Moran_I  p_value\n",
-      "0       DST  0.175399    0.001\n",
-      "1   TACSTD2  0.206515    0.001\n",
-      "2     ERBB2  0.310598    0.001\n",
-      "3     GATA3  0.230100    0.001\n",
-      "4       LUM  0.165535    0.001\n",
-      "5       LYZ  0.185562    0.001\n",
-      "6     CCND1  0.153887    0.001\n",
-      "7     PTPRC  0.135836    0.001\n",
-      "8      KRT8  0.267421    0.001\n",
-      "9      MMP2  0.151345    0.001\n",
-      "10    BASP1  0.078890    0.001\n",
-      "11   CXCL12  0.181896    0.001\n",
-      "12   FCER1G  0.059119    0.001\n",
-      "13      CD4  0.069058    0.001\n",
-      "14   PDGFRB  0.075063    0.001\n"
-     ]
-    }
-   ],
-   "source": [
-    "## Run calculate_moran_scores - outier_genes\n",
-    "moran_results_1_fOut = calculate_moran_scores(outlier_genes, adata1, 100, x_coord_col='CenterX_global_px', y_coord_col='CenterX_global_px')\n",
-    "print(moran_results_1_fOut)\n",
-    "\n",
-    "moran_results_2_fOut = calculate_moran_scores(outlier_genes, adata2, 100, x_coord_col='x_centroid', y_coord_col='y_centroid')\n",
-    "print(moran_results_2_fOut)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "13\n",
-      "2\n",
-      "15\n",
-      "0\n"
-     ]
-    }
-   ],
-   "source": [
-    "## Check the statistics for moran's test\n",
-    "print((moran_results_1_fOut['p_value'] <= 0.05).sum())\n",
-    "print((moran_results_1_fOut['p_value'] > 0.05).sum())\n",
-    "\n",
-    "print((moran_results_2_fOut['p_value'] <= 0.05).sum())\n",
-    "print((moran_results_2_fOut['p_value'] > 0.05).sum())\n",
-    "\n",
-    "# Filter results by statistical sig\n",
-    "moran_results_1_fOut = pd.DataFrame(moran_results_1_fOut)\n",
-    "filtered_res_1_fOut = moran_results_1_fOut[moran_results_1_fOut['p_value'] <= 0.05]\n",
-    "\n",
-    "moran_results_2_fOut = pd.DataFrame(moran_results_2_fOut)\n",
-    "filtered_res_2_fOut = moran_results_2_fOut[moran_results_2_fOut['p_value'] <= 0.05]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 45,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1600x600 with 2 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "## Visualizing Moran's score #1\n",
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "import seaborn as sns\n",
-    "import matplotlib.pyplot as plt\n",
-    "\n",
-    "# Merging inlier and outlier data\n",
-    "merged_inliers = pd.merge(filtered_res_1_fIn[['Gene', 'Moran_I']], filtered_res_2_fIn[['Gene', 'Moran_I']], on='Gene', suffixes=('_Dataset1', '_Dataset2'))\n",
-    "merged_outliers = pd.merge(filtered_res_1_fOut[['Gene', 'Moran_I']], filtered_res_2_fOut[['Gene', 'Moran_I']], on='Gene', suffixes=('_Dataset1', '_Dataset2'))\n",
-    "\n",
-    "# Calculate correlation coefficients and R-squared for inliers\n",
-    "correlation_coefficient_in = np.corrcoef(merged_inliers['Moran_I_Dataset1'], merged_inliers['Moran_I_Dataset2'])[0, 1]\n",
-    "r_squared_in = correlation_coefficient_in ** 2\n",
-    "\n",
-    "# Calculate correlation coefficients and R-squared for outliers\n",
-    "correlation_coefficient_out = np.corrcoef(merged_outliers['Moran_I_Dataset1'], merged_outliers['Moran_I_Dataset2'])[0, 1]\n",
-    "r_squared_out = correlation_coefficient_out ** 2\n",
-    "\n",
-    "# Set up the matplotlib figure with subplots\n",
-    "fig, axes = plt.subplots(1, 2, figsize=(16, 6))\n",
-    "\n",
-    "# Inlier Genes Plot\n",
-    "sns.regplot(data=merged_inliers, x='Moran_I_Dataset1', y='Moran_I_Dataset2', ax=axes[0], scatter_kws={'alpha':0.7}, line_kws={'color':'blue'})\n",
-    "axes[0].set_title('Inlier Genes Moran I Values')\n",
-    "axes[0].set_xlabel('Moran I (Dataset 1)')\n",
-    "axes[0].set_ylabel('Moran I (Dataset 2)')\n",
-    "axes[0].axhline(0, color='red', linestyle='--')\n",
-    "axes[0].axvline(0, color='red', linestyle='--')\n",
-    "axes[0].text(0.05, 0.95, f'R² = {r_squared_in:.3f}', transform=axes[0].transAxes, fontsize=12, verticalalignment='top')\n",
-    "axes[0].grid()\n",
-    "\n",
-    "# Outlier Genes Plot\n",
-    "sns.regplot(data=merged_outliers, x='Moran_I_Dataset1', y='Moran_I_Dataset2', ax=axes[1], scatter_kws={'alpha':0.7}, line_kws={'color':'blue'})\n",
-    "axes[1].set_title('Outlier Genes Moran I Values')\n",
-    "axes[1].set_xlabel('Moran I (Dataset 1)')\n",
-    "axes[1].set_ylabel('Moran I (Dataset 2)')\n",
-    "axes[1].axhline(0, color='red', linestyle='--')\n",
-    "axes[1].axvline(0, color='red', linestyle='--')\n",
-    "axes[1].text(0.05, 0.95, f'R² = {r_squared_out:.3f}', transform=axes[1].transAxes, fontsize=12, verticalalignment='top')\n",
-    "axes[1].grid()\n",
-    "\n",
-    "# Adjust layout for better spacing\n",
-    "plt.tight_layout()\n",
-    "\n",
-    "# Show the combined plot\n",
-    "plt.show()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 47,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1000x600 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "## Visualizing Moran's score #2\n",
-    "\n",
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "import seaborn as sns\n",
-    "import matplotlib.pyplot as plt\n",
-    "\n",
-    "# Merging inlier data\n",
-    "inliers_dataset_1 = filtered_res_1_fIn[['Gene', 'Moran_I']].copy()\n",
-    "inliers_dataset_1['Group'] = 'Inlier Dataset 1'\n",
-    "inliers_dataset_2 = filtered_res_2_fIn[['Gene', 'Moran_I']].copy()\n",
-    "inliers_dataset_2['Group'] = 'Inlier Dataset 2'\n",
-    "\n",
-    "# Merging outlier data\n",
-    "outliers_dataset_1 = filtered_res_1_fOut[['Gene', 'Moran_I']].copy()\n",
-    "outliers_dataset_1['Group'] = 'Outlier Dataset 1'\n",
-    "outliers_dataset_2 = filtered_res_2_fOut[['Gene', 'Moran_I']].copy()\n",
-    "outliers_dataset_2['Group'] = 'Outlier Dataset 2'\n",
-    "\n",
-    "# Concatenating all datasets into one DataFrame\n",
-    "all_data = pd.concat([inliers_dataset_1, inliers_dataset_2, outliers_dataset_1, outliers_dataset_2])\n",
-    "\n",
-    "# Renaming columns for clarity\n",
-    "all_data.rename(columns={'Moran_I': 'Moran_Score'}, inplace=True)\n",
-    "\n",
-    "# Set up the matplotlib figure\n",
-    "plt.figure(figsize=(10, 6))\n",
-    "\n",
-    "# Create a boxplot\n",
-    "sns.boxplot(x='Group', y='Moran_Score', data=all_data)\n",
-    "\n",
-    "# Add titles and labels\n",
-    "plt.title('Boxplot of Moran\\'s Scores for Inlier and Outlier Genes')\n",
-    "plt.xlabel('Gene Set by Dataset')\n",
-    "plt.ylabel('Moran\\'s Score')\n",
-    "\n",
-    "# Show grid\n",
-    "plt.grid()\n",
-    "\n",
-    "# Show the plot\n",
-    "plt.show()\n"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "SpaceHack_MM",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.10"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}