MultiClass_MolBi.ipynb

       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>C&gt;A</td>\n",
       "      <td>ACA</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>C&gt;A</td>\n",
       "      <td>ACC</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2 rows × 9693 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  Mutation type Trinucleotide  ALL::TARGET-10-PAIXPH-03A-01D  \\\n",
       "0           C>A           ACA                              0   \n",
       "1           C>A           ACC                              0   \n",
       "\n",
       "   ALL::TARGET-10-PAKHZT-03A-01R  ALL::TARGET-10-PAKMVD-09A-01D  \\\n",
       "0                              0                              0   \n",
       "1                              0                              0   \n",
       "\n",
       "   ALL::TARGET-10-PAKSWW-03A-01D  ALL::TARGET-10-PALETF-03A-01D  \\\n",
       "0                              1                              0   \n",
       "1                              1                              0   \n",
       "\n",
       "   ALL::TARGET-10-PALLSD-09A-01D  ALL::TARGET-10-PAMDKS-03A-01D  \\\n",
       "0                              0                              0   \n",
       "1                              0                              0   \n",
       "\n",
       "   ALL::TARGET-10-PAPJIB-04A-01D  ...  Head-SCC::V-109  Head-SCC::V-112  \\\n",
       "0                              2  ...                0                0   \n",
       "1                              0  ...                1                0   \n",
       "\n",
       "   Head-SCC::V-116  Head-SCC::V-119  Head-SCC::V-123  Head-SCC::V-124  \\\n",
       "0                0                0                0                0   \n",
       "1                0                0                0                0   \n",
       "\n",
       "   Head-SCC::V-125  Head-SCC::V-14  Head-SCC::V-29  Head-SCC::V-98  \n",
       "0                0               0               0               1  \n",
       "1                0               1               0               0  \n",
       "\n",
       "[2 rows x 9693 columns]"
      ]
     },
     "execution_count": 358,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "other_wes_mut = pd.read_csv(\"./project_data/catalogs/WES/WES_Other.96.csv\")\n",
    "other_wes_mut.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 359,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Cancer Types</th>\n",
       "      <th>Sample Names</th>\n",
       "      <th>Accuracy</th>\n",
       "      <th>SBS1</th>\n",
       "      <th>SBS2</th>\n",
       "      <th>SBS3</th>\n",
       "      <th>SBS4</th>\n",
       "      <th>SBS5</th>\n",
       "      <th>SBS6</th>\n",
       "      <th>SBS7a</th>\n",
       "      <th>...</th>\n",
       "      <th>SBS51</th>\n",
       "      <th>SBS52</th>\n",
       "      <th>SBS53</th>\n",
       "      <th>SBS54</th>\n",
       "      <th>SBS55</th>\n",
       "      <th>SBS56</th>\n",
       "      <th>SBS57</th>\n",
       "      <th>SBS58</th>\n",
       "      <th>SBS59</th>\n",
       "      <th>SBS60</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ALL</td>\n",
       "      <td>TARGET-10-PAIXPH-03A-01D</td>\n",
       "      <td>0.529</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>ALL</td>\n",
       "      <td>TARGET-10-PAKHZT-03A-01R</td>\n",
       "      <td>0.696</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2 rows × 68 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  Cancer Types              Sample Names  Accuracy  SBS1  SBS2  SBS3  SBS4  \\\n",
       "0          ALL  TARGET-10-PAIXPH-03A-01D     0.529     0     0     0     0   \n",
       "1          ALL  TARGET-10-PAKHZT-03A-01R     0.696     0     0     0     0   \n",
       "\n",
       "   SBS5  SBS6  SBS7a  ...  SBS51  SBS52  SBS53  SBS54  SBS55  SBS56  SBS57  \\\n",
       "0     0     0      0  ...      0      0      0      1      0      0      0   \n",
       "1     0     0      0  ...      0      0      0      1      0      0      0   \n",
       "\n",
       "   SBS58  SBS59  SBS60  \n",
       "0      0      0      0  \n",
       "1      0      0      0  \n",
       "\n",
       "[2 rows x 68 columns]"
      ]
     },
     "execution_count": 359,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "other_wes_act = pd.read_csv(\"./project_data/activities/WES/WES_Other.activities.csv\")\n",
    "other_wes_act.head(2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Imports and helpers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 360,
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import sklearn\n",
    "from sklearn.decomposition import PCA\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "#import torch \n",
    "\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.metrics import roc_auc_score\n",
    "from sklearn.metrics import classification_report\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import label_binarize\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "\n",
    "\n",
    "def plot_confusion_mat(y_test, y_pred, labs=None, size=None, title=None):\n",
    "    \"\"\"\n",
    "    prepare_mut_df plots a confucion matrix.\n",
    "\n",
    "    :param y_test: a vector containing numerically encoded label values used in model test \n",
    "    :param y_pred: a vector containing numerically encoded label values from prediction\n",
    "    :param pre_sample_limit: a lits of labeling strings for plotting\n",
    "    :param size: a tuple containing x,y size of the plot\n",
    "    :param title: a title for the whole plot\n",
    "    :return: no value\n",
    "    \"\"\"\n",
    "\n",
    "    plt.figure(figsize=(12,10))\n",
    "    \n",
    "    cm = sklearn.metrics.confusion_matrix(y_test, y_pred)\n",
    "    if size is not None:\n",
    "        plt.figure(figsize=size)\n",
    "    if labs is None:\n",
    "        sns.heatmap(cm, square=False, annot=True, fmt='d', cmap='viridis', cbar=True)\n",
    "    else:\n",
    "        sns.heatmap(cm, square=False, annot=True, fmt='d', cmap='viridis', xticklabels=labs, yticklabels=labs, cbar=True)\n",
    "    \n",
    "    #plt.xlabel('Predicted label')\n",
    "    #plt.ylabel('True label')\n",
    "\n",
    "    if title is not None:\n",
    "        plt.title(title)\n",
    "    #plt.ylim(0, 2)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Dataset preprocess routines"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 361,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "def prepare_mut_df(raw_mutation_dfs, is_profile, pre_sample_limit=None, small_sample_limit=None, grouping=True):\n",
    "    \"\"\"\n",
    "    prepare_mut_df prepares a data set for further analysis from WGS & WES profile or acitvity catalogs.\n",
    "\n",
    "    :param raw_mutation_dfs: a list containing data frames to combine \n",
    "    :param is_profile: True/False wheter we are dealing with profile data, if false activities data is asumed\n",
    "    :param pre_sample_limit: cull smaller than the specified limit samples per tumor type before grouping\n",
    "    :param small_sample_limit: cull smaller than the specified limit samples per tumor type after grouping\n",
    "    :param True/False wheter to do tissue related grouping or not\n",
    "    :return: Pandas dataframe with samples in rows, mutations in columns as wella as tissue grouping column tumor_type\n",
    "    \"\"\" \n",
    "    mutations_all = pd.DataFrame()\n",
    "\n",
    "    #######################################\n",
    "    # Combining data and rename some items\n",
    "    #######################################\n",
    "\n",
    "    for df in raw_mutation_dfs:\n",
    "        # Make a copy of the original data frame and start processing from there\n",
    "        mutations  = df.copy()\n",
    "    \n",
    "        if is_profile:\n",
    "            mutations['mut_tri'] = mutations.apply(lambda a: '{}_{}'.format(a['Mutation type'], a['Trinucleotide']), axis=1)\n",
    "            mutations = mutations.set_index('mut_tri').drop(['Mutation type', 'Trinucleotide'], axis=1)\n",
    "            mutations = mutations.T\n",
    "        else:\n",
    "            mutations['mut_tri'] = mutations.apply(lambda a: '{}::{}'.format(a['Cancer Types'], a['Sample Names']), axis=1)\n",
    "            mutations = mutations.set_index('mut_tri').drop(['Cancer Types', 'Sample Names', 'Accuracy'], axis=1)\n",
    "     \n",
    "        # Rename some index names\n",
    "        renamed_items = list(mutations.index)\n",
    "        index_items = list(mutations.index)\n",
    "   \n",
    "        # Combine rows for low count labels\n",
    "        for i in range(len(index_items)):\n",
    "            result = index_items[i]    \n",
    "            renamed_items[i] = result.replace('Ca', 'CA')\n",
    "       \n",
    "        mutations.rename(index=dict(zip(index_items, renamed_items)), inplace = True)\n",
    "   \n",
    "        # Normalize \n",
    "        row_sums = mutations.sum(axis=1)\n",
    "        mutations = mutations.divide(row_sums, axis = 0)\n",
    "\n",
    "        mutations_all = pd.concat([mutations_all, mutations])\n",
    "\n",
    "    # Figure out tumor types based on the first part of the index\n",
    "    tumor_types = [a.split(':')[0] for a in mutations_all.index]\n",
    "    \n",
    "    # Form an additional column of the types to the data frame\n",
    "    mutations_all[\"tumor_types\"] = tumor_types\n",
    "\n",
    "    ##############################################\n",
    "    # Pre culling of samples based on small counts\n",
    "    ##############################################\n",
    "\n",
    "    print(\"Pre cull dim\", mutations_all.shape)\n",
    "    if pre_sample_limit is not None:\n",
    "        mutations_all = cull_small_sample_counts(mutations_all, pre_sample_limit)\n",
    "\n",
    "    tumor_types = mutations_all[\"tumor_types\"] \n",
    "    print(\"After pre cull dim\", mutations_all.shape)\n",
    "    \n",
    "\n",
    "    ################################################\n",
    "    # Grouping (done changing the tumor_type column)\n",
    "    ################################################\n",
    "    if grouping:\n",
    "        def substitute(name):\n",
    "            tissue_groups = ['Bone', 'Breast', 'Cervix', 'CNS', 'Eye', 'Liver', 'Lymph', 'Lung', 'Kidney', 'Myeloid', 'Panc' ]\n",
    "            \n",
    "            for to_sub in tissue_groups:\n",
    "                name = re.sub( to_sub + r'(-\\w*)', to_sub, name)\n",
    "            return name\n",
    "\n",
    "        # Combine rows for low count labels\n",
    "        mutations_all[\"tumor_types\"] = mutations_all[\"tumor_types\"].apply(substitute)\n",
    "    \n",
    "    \n",
    "    #########################################################\n",
    "    # Post grouping culling of samples based on sample size\n",
    "    #########################################################\n",
    "\n",
    "    if small_sample_limit is not None:\n",
    "        mutations_all = cull_small_sample_counts(mutations_all, small_sample_limit)\n",
    "\n",
    "    print(\"After post cull dim\", mutations_all.shape)\n",
    "   \n",
    "    mutations_all.sort_index(inplace=True)\n",
    "\n",
    "    tumor_types = mutations_all[\"tumor_types\"] \n",
    "\n",
    "    # Prepare a list with all the types appearing only once\n",
    "    unique_tumor_types = sorted(list(set(tumor_types)))\n",
    "    \n",
    "    return (mutations_all, unique_tumor_types)\n",
    "\n",
    "\n",
    "def cull_small_sample_counts(mutations, small_sample_limit):\n",
    "    \"\"\"\n",
    "    prepare_mut_df prepares a data set for further analysis from WGS & WES profile or acitvity catalogs.\n",
    "\n",
    "    :param raw_mutation_dfs: a list containing data frames to combine \n",
    "    :param is_profile: True/False wheter we are dealing with profile data, if false activities data is asumed\n",
    "    :param pre_sample_limit: cull smaller than the specified limit samples per tumor type before grouping\n",
    "    :param small_sample_limit: cull smaller than the specified limit samples per tumor type after grouping\n",
    "    :param True/False wheter to do tissue related grouping or not\n",
    "    :return: Pandas dataframe with samples in rows, mutations in columns as wella as tissue grouping column tumor_type\n",
    "    \"\"\"\n",
    "    counts = mutations[\"tumor_types\"].value_counts()\n",
    "    big_counts = counts[list(counts > small_sample_limit)]\n",
    "    big_index = mutations[\"tumor_types\"].isin(list(big_counts.index))\n",
    "    mutations = mutations[big_index]\n",
    "\n",
    "    return mutations\n",
    "\n",
    "def print_dset_diag(mut_df, unique_tumor_types, small_sample_limit):\n",
    "    \"\"\"\n",
    "    print_dset_diag prints textual diagnostics of a profile or activities data frame\n",
    "\n",
    "    :param mut_df: the data frame to use to print info \n",
    "    :param unique_tumor_types: an array of the tumor types obtained previously\n",
    "    :param small_sample_limit: an integer of the cut off limit used in the data processing step\n",
    "    :return: no value\n",
    "    \"\"\"\n",
    "    # Check if the data frame is ok\n",
    "    print(\"\\n---Data set diagnostics print---\\n\")\n",
    "    print(\"Missing entries in mutations:\", mut_df.isnull().sum().sum())\n",
    "    print(\"The shape of the mutations data frame\", mut_df.shape)\n",
    "\n",
    "    # Check to see if the rows are normalized to one, take a sample from the data frame\n",
    "    norm_df = mut_df.sample(n=5, random_state=5)\n",
    "    print(\"Checking normalization: sum of some rows:\\n\", norm_df.iloc[:,0:-1].sum(axis=1))\n",
    "    print(\"\\n\")\n",
    "\n",
    "    # Check some counts of tumor types\n",
    "    tumor_counts = mut_df[\"tumor_types\"].value_counts() #.sort_values(ascending=True)\n",
    "    print(\"Tumor counts:\\n\", tumor_counts)\n",
    "    print(\"\\n\")\n",
    "\n",
    "    small_counts = tumor_counts < 1.5*small_sample_limit\n",
    "    print(\"Tumor types with smallish counts:\",  sum(small_counts))\n",
    "\n",
    "    print(tumor_counts[small_counts])\n",
    "    print(\"\\n\")\n",
    "\n",
    "    # Tumor types\n",
    "    print(\"Unique tumor types: \", len(unique_tumor_types))\n",
    "    print(unique_tumor_types)\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Createa a profile set with no grouping and no limits for reference"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 362,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pre cull dim (23829, 97)\n",
      "After pre cull dim (23829, 97)\n",
      "After post cull dim (23829, 97)\n",
      "Profile data:\n",
      "\n",
      "---Data set diagnostics print---\n",
      "\n",
      "Missing entries in mutations: 0\n",
      "The shape of the mutations data frame (23829, 97)\n",
      "Checking normalization: sum of some rows:\n",
      " Thymoma::TCGA-4V-A9QI-01A-11D-A423-09    1.0\n",
      "CNS-Medullo::SP107464                    1.0\n",
      "Prost-AdenoCA::SP114926                  1.0\n",
      "CNS-Medullo::SP78663                     1.0\n",
      "Sarcoma-bone::IC086T_WGS                 1.0\n",
      "dtype: float64\n",
      "\n",
      "\n",
      "Tumor counts:\n",
      " Breast-cancer       1637\n",
      "Liver-HCC           1318\n",
      "ColoRect-AdenoCA    1185\n",
      "Prost-AdenoCA       1091\n",
      "Skin-Melanoma       1070\n",
      "                    ... \n",
      "Myeloid-MDS            4\n",
      "Eye-RB                 4\n",
      "Breast-DCIS            3\n",
      "Cervix-AdenoCA         2\n",
      "Bone-cancer            2\n",
      "Name: tumor_types, Length: 82, dtype: int64\n",
      "\n",
      "\n",
      "Tumor types with smallish counts: 0\n",
      "Series([], Name: tumor_types, dtype: int64)\n",
      "\n",
      "\n",
      "Unique tumor types:  82\n",
      "['ALL', 'AML', 'Adrenal-neoplasm', 'Biliary-AdenoCA', 'Bladder-TCC', 'Blood-CMDI', 'Bone-Benign', 'Bone-Epith', 'Bone-Osteosarc', 'Bone-cancer', 'Breast-AdenoCA', 'Breast-DCIS', 'Breast-Fibroadenoma', 'Breast-LobularCA', 'Breast-cancer', 'CNS-GBM', 'CNS-LGG', 'CNS-Medullo', 'CNS-Oligo', 'CNS-PiloAstro', 'CNS-glioma-NOS', 'Cervix-AdenoCA', 'Cervix-CA', 'Cervix-SCC', 'ColoRect-AdenoCA', 'ColoRect-Adenoma', 'DLBC', 'Eso-AdenoCA', 'Eso-SCC', 'Ewings', 'Eye-Melanoma', 'Eye-RB', 'Head-SCC', 'Kidney-ChRCC', 'Kidney-NOS', 'Kidney-Papillary', 'Kidney-RCC', 'Kidney-Wilms', 'Liver-Benign', 'Liver-HCC', 'Lung-AdenoCA', 'Lung-CArcinoid', 'Lung-NOS', 'Lung-SCC', 'Lung-Small', 'Lymph-BNHL', 'Lymph-CLL', 'Lymph-NOS', 'Lymph-TNHL', 'Lymph-cHL', 'Meninges-Meningioma', 'Mesothelium-Mesothelioma', 'Myeloid-AML', 'Myeloid-MDS', 'Myeloid-MPN', 'Neuroblastoma', 'Oral-SCC', 'Ovary-AdenoCA', 'Panc-AdenoCA', 'Panc-Endocrine', 'Panc-Other', 'Para-AdenoCA', 'Para-Adenoma', 'Pheochromocytoma', 'Pit-All', 'Prost-AdenoCA', 'Prost-Adenoma', 'Sarcoma', 'Sarcoma-bone', 'Skin-BCC', 'Skin-Melanoma', 'Skin-SCC', 'Small-Intestine-carcinoid', 'SoftTissue-Leiomyo', 'SoftTissue-Liposarc', 'Stomach-AdenoCA', 'Testis-CA', 'Thy-AdenoCA', 'Thymoma', 'Transitional-cell-carcinoma', 'UCS', 'Uterus-AdenoCA']\n"
     ]
    }
   ],
   "source": [
    "profile_raw_data_sets = [PCAWG_wgs_mut, TCGA_wes_mut, nonPCAWG_wgs_mut, other_wes_mut]\n",
    "\n",
    "profile_all_no_grp, prf_unique_tumor_types_no_grp = prepare_mut_df(profile_raw_data_sets, True, pre_sample_limit = 0, small_sample_limit = 0, grouping=False)\n",
    "\n",
    "# Print some diagnostics from the prepared data set\n",
    "print(\"Profile data:\")\n",
    "print_dset_diag(profile_all_no_grp, prf_unique_tumor_types_no_grp, 0)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Create a profile data set with tissue grouping\n",
    "\n",
    "From all profile sets, a combined data frame is made, which has samples in the rows and features in the columns."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 363,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pre cull dim (23829, 97)\n",
      "After pre cull dim (23814, 97)\n",
      "After post cull dim (23678, 97)\n",
      "Profile data:\n",
      "\n",
      "---Data set diagnostics print---\n",
      "\n",
      "Missing entries in mutations: 0\n",
      "The shape of the mutations data frame (23678, 97)\n",
      "Checking normalization: sum of some rows:\n",
      " ALL::SJBALL020936_D1                           1.0\n",
      "Breast-cancer::TCGA-C8-A274-01A-11D-A16D-09    1.0\n",
      "Prost-AdenoCA::TCGA-EJ-7317-01A-31D-2114-08    1.0\n",
      "Kidney-RCC::ccRCC-103                          1.0\n",
      "Eso-SCC::420                                   1.0\n",
      "dtype: float64\n",
      "\n",
      "\n",
      "Tumor counts:\n",
      " Breast                         1855\n",
      "Lung                           1668\n",
      "CNS                            1595\n",
      "Liver                          1358\n",
      "Kidney                         1269\n",
      "Lymph                          1192\n",
      "ColoRect-AdenoCA               1185\n",
      "Panc                           1157\n",
      "Prost-AdenoCA                  1091\n",
      "Skin-Melanoma                  1070\n",
      "Head-SCC                        798\n",
      "Stomach-AdenoCA                 667\n",
      "Eso-SCC                         599\n",
      "Thy-AdenoCA                     560\n",
      "AML                             556\n",
      "Ovary-AdenoCA                   549\n",
      "Uterus-AdenoCA                  548\n",
      "DLBC                            512\n",
      "Biliary-AdenoCA                 487\n",
      "Eso-AdenoCA                     486\n",
      "Transitional-cell-carcinoma     389\n",
      "Neuroblastoma                   379\n",
      "Blood-CMDI                      357\n",
      "Sarcoma                         346\n",
      "ALL                             308\n",
      "Cervix                          289\n",
      "Ewings                          275\n",
      "Adrenal-neoplasm                247\n",
      "Sarcoma-bone                    203\n",
      "Testis-CA                       191\n",
      "Pheochromocytoma                182\n",
      "Bladder-TCC                     168\n",
      "Eye                             161\n",
      "Skin-BCC                        129\n",
      "CNS-NOS                         128\n",
      "Oral-SCC                        126\n",
      "Thymoma                         123\n",
      "Mesothelium-Mesothelioma        112\n",
      "Myeloid                          67\n",
      "Bone                             65\n",
      "Meninges-Meningioma              65\n",
      "Prost-Adenoma                    63\n",
      "UCS                              57\n",
      "Skin-SCC                         46\n",
      "Name: tumor_types, dtype: int64\n",
      "\n",
      "\n",
      "Tumor types with smallish counts: 1\n",
      "Skin-SCC    46\n",
      "Name: tumor_types, dtype: int64\n",
      "\n",
      "\n",
      "Unique tumor types:  44\n",
      "['ALL', 'AML', 'Adrenal-neoplasm', 'Biliary-AdenoCA', 'Bladder-TCC', 'Blood-CMDI', 'Bone', 'Breast', 'CNS', 'CNS-NOS', 'Cervix', 'ColoRect-AdenoCA', 'DLBC', 'Eso-AdenoCA', 'Eso-SCC', 'Ewings', 'Eye', 'Head-SCC', 'Kidney', 'Liver', 'Lung', 'Lymph', 'Meninges-Meningioma', 'Mesothelium-Mesothelioma', 'Myeloid', 'Neuroblastoma', 'Oral-SCC', 'Ovary-AdenoCA', 'Panc', 'Pheochromocytoma', 'Prost-AdenoCA', 'Prost-Adenoma', 'Sarcoma', 'Sarcoma-bone', 'Skin-BCC', 'Skin-Melanoma', 'Skin-SCC', 'Stomach-AdenoCA', 'Testis-CA', 'Thy-AdenoCA', 'Thymoma', 'Transitional-cell-carcinoma', 'UCS', 'Uterus-AdenoCA']\n"
     ]
    }
   ],
   "source": [
    "small_sample_limit = 35\n",
    "pre_sample_limit = 5\n",
    "\n",
    "profile_mut_all, prf_unique_tumor_types = prepare_mut_df(profile_raw_data_sets, True, pre_sample_limit, small_sample_limit, grouping=True)\n",
    "\n",
    "# Print some diagnostics from the prepared data set\n",
    "print(\"Profile data:\")\n",
    "print_dset_diag(profile_mut_all, prf_unique_tumor_types, small_sample_limit)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Dataset preprocess for activites data with grouping"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 364,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pre cull dim (23829, 66)\n",
      "After pre cull dim (23814, 66)\n",
      "After post cull dim (23678, 66)\n",
      "Activities data:\n",
      "\n",
      "---Data set diagnostics print---\n",
      "\n",
      "Missing entries in mutations: 0\n",
      "The shape of the mutations data frame (23678, 66)\n",
      "Checking normalization: sum of some rows:\n",
      " mut_tri\n",
      "ALL::SJBALL020936_D1                           1.0\n",
      "Breast-cancer::TCGA-C8-A274-01A-11D-A16D-09    1.0\n",
      "Prost-AdenoCA::TCGA-EJ-7317-01A-31D-2114-08    1.0\n",
      "Kidney-RCC::ccRCC-103                          1.0\n",
      "Eso-SCC::420                                   1.0\n",
      "dtype: float64\n",
      "\n",
      "\n",
      "Tumor counts:\n",
      " Breast                         1855\n",
      "Lung                           1668\n",
      "CNS                            1595\n",
      "Liver                          1358\n",
      "Kidney                         1269\n",
      "Lymph                          1192\n",
      "ColoRect-AdenoCA               1185\n",
      "Panc                           1157\n",
      "Prost-AdenoCA                  1091\n",
      "Skin-Melanoma                  1070\n",
      "Head-SCC                        798\n",
      "Stomach-AdenoCA                 667\n",
      "Eso-SCC                         599\n",
      "Thy-AdenoCA                     560\n",
      "AML                             556\n",
      "Ovary-AdenoCA                   549\n",
      "Uterus-AdenoCA                  548\n",
      "DLBC                            512\n",
      "Biliary-AdenoCA                 487\n",
      "Eso-AdenoCA                     486\n",
      "Transitional-cell-carcinoma     389\n",
      "Neuroblastoma                   379\n",
      "Blood-CMDI                      357\n",
      "Sarcoma                         346\n",
      "ALL                             308\n",
      "Cervix                          289\n",
      "Ewings                          275\n",
      "Adrenal-neoplasm                247\n",
      "Sarcoma-bone                    203\n",
      "Testis-CA                       191\n",
      "Pheochromocytoma                182\n",
      "Bladder-TCC                     168\n",
      "Eye                             161\n",
      "Skin-BCC                        129\n",
      "CNS-NOS                         128\n",
      "Oral-SCC                        126\n",
      "Thymoma                         123\n",
      "Mesothelium-Mesothelioma        112\n",
      "Myeloid                          67\n",
      "Bone                             65\n",
      "Meninges-Meningioma              65\n",
      "Prost-Adenoma                    63\n",
      "UCS                              57\n",
      "Skin-SCC                         46\n",
      "Name: tumor_types, dtype: int64\n",
      "\n",
      "\n",
      "Tumor types with smallish counts: 1\n",
      "Skin-SCC    46\n",
      "Name: tumor_types, dtype: int64\n",
      "\n",
      "\n",
      "Unique tumor types:  44\n",
      "['ALL', 'AML', 'Adrenal-neoplasm', 'Biliary-AdenoCA', 'Bladder-TCC', 'Blood-CMDI', 'Bone', 'Breast', 'CNS', 'CNS-NOS', 'Cervix', 'ColoRect-AdenoCA', 'DLBC', 'Eso-AdenoCA', 'Eso-SCC', 'Ewings', 'Eye', 'Head-SCC', 'Kidney', 'Liver', 'Lung', 'Lymph', 'Meninges-Meningioma', 'Mesothelium-Mesothelioma', 'Myeloid', 'Neuroblastoma', 'Oral-SCC', 'Ovary-AdenoCA', 'Panc', 'Pheochromocytoma', 'Prost-AdenoCA', 'Prost-Adenoma', 'Sarcoma', 'Sarcoma-bone', 'Skin-BCC', 'Skin-Melanoma', 'Skin-SCC', 'Stomach-AdenoCA', 'Testis-CA', 'Thy-AdenoCA', 'Thymoma', 'Transitional-cell-carcinoma', 'UCS', 'Uterus-AdenoCA']\n"
     ]
    }
   ],
   "source": [
    "act_raw_data_sets = [PCAWG_wgs_act, TCGA_wes_act, nonPCAWG_wgs_act, other_wes_act]\n",
    "act_mut_all, act_unique_tumor_types = prepare_mut_df(act_raw_data_sets, False, pre_sample_limit, small_sample_limit, grouping=True)\n",
    "\n",
    "# Print some diagnostics from the prepared data set\n",
    "print(\"Activities data:\")\n",
    "print_dset_diag(act_mut_all, act_unique_tumor_types, small_sample_limit)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Check profile data without grouping"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 365,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Some content from the full profile set:\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>mut_tri</th>\n",
       "      <th>C&gt;A_ACA</th>\n",
       "      <th>C&gt;A_ACC</th>\n",
       "      <th>C&gt;A_ACG</th>\n",
       "      <th>C&gt;A_ACT</th>\n",
       "      <th>C&gt;A_CCA</th>\n",
       "      <th>C&gt;A_CCC</th>\n",
       "      <th>C&gt;A_CCG</th>\n",
       "      <th>C&gt;A_CCT</th>\n",
       "      <th>C&gt;A_GCA</th>\n",
       "      <th>C&gt;A_GCC</th>\n",
       "      <th>...</th>\n",
       "      <th>T&gt;G_CTT</th>\n",
       "      <th>T&gt;G_GTA</th>\n",
       "      <th>T&gt;G_GTC</th>\n",
       "      <th>T&gt;G_GTG</th>\n",
       "      <th>T&gt;G_GTT</th>\n",
       "      <th>T&gt;G_TTA</th>\n",
       "      <th>T&gt;G_TTC</th>\n",
       "      <th>T&gt;G_TTG</th>\n",
       "      <th>T&gt;G_TTT</th>\n",
       "      <th>tumor_types</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>ALL::11</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.133333</td>\n",
       "      <td>0.066667</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.066667</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.066667</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>ALL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ALL::2211636</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>ALL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ALL::2211638</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>ALL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ALL::2211640</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>ALL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ALL::2211642</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>ALL</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 97 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "mut_tri       C>A_ACA  C>A_ACC  C>A_ACG  C>A_ACT  C>A_CCA  C>A_CCC  C>A_CCG  \\\n",
       "ALL::11           0.0      0.0      0.0      0.0      0.0      0.0      0.0   \n",
       "ALL::2211636      0.0      0.0      0.0      0.0      0.0      0.0      0.0   \n",
       "ALL::2211638      0.0      0.0      0.0      0.0      0.0      0.0      0.0   \n",
       "ALL::2211640      0.0      0.0      0.0      0.0      0.0      0.0      0.0   \n",
       "ALL::2211642      0.0      0.0      0.0      0.0      0.0      0.0      0.0   \n",
       "\n",
       "mut_tri        C>A_CCT   C>A_GCA  C>A_GCC  ...   T>G_CTT  T>G_GTA   T>G_GTC  \\\n",
       "ALL::11       0.133333  0.066667      0.0  ...  0.066667      0.0  0.066667   \n",
       "ALL::2211636  0.000000  0.000000      0.0  ...  0.000000      0.0  0.000000   \n",
       "ALL::2211638  0.000000  0.000000      0.0  ...  0.000000      0.0  0.000000   \n",
       "ALL::2211640  0.000000  0.000000      0.0  ...  0.000000      0.0  0.000000   \n",
       "ALL::2211642  0.000000  0.000000      0.0  ...  0.000000      0.0  0.000000   \n",
       "\n",
       "mut_tri       T>G_GTG  T>G_GTT   T>G_TTA  T>G_TTC  T>G_TTG  T>G_TTT  \\\n",
       "ALL::11           0.0      0.0  0.000000      0.0      0.0      0.0   \n",
       "ALL::2211636      0.0      0.0  0.000000      0.0      0.0      0.0   \n",
       "ALL::2211638      0.0      0.0  0.333333      0.0      0.0      0.0   \n",
       "ALL::2211640      0.0      0.0  0.000000      0.0      0.0      0.0   \n",
       "ALL::2211642      0.0      0.0  0.000000      0.0      0.0      0.0   \n",
       "\n",
       "mut_tri       tumor_types  \n",
       "ALL::11               ALL  \n",
       "ALL::2211636          ALL  \n",
       "ALL::2211638          ALL  \n",
       "ALL::2211640          ALL  \n",
       "ALL::2211642          ALL  \n",
       "\n",
       "[5 rows x 97 columns]"
      ]
     },
     "execution_count": 365,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print(\"Some content from the full profile set:\")\n",
    "profile_mut_all.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 366,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1800x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(25, 5))\n",
    "sns.set_theme()\n",
    "profile_all_no_grp[\"tumor_types\"].value_counts().sort_index().plot(kind=\"bar\")\n",
    "plt.xticks(rotation=90);\n",
    "plt.title(\"Tumor types in profile data without grouping\");"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Check profile data with grouping"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 367,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",