Datasets
Models
Downloads: 1
Diff of
/datasets_csv/Preprocessing.ipynb
[000000]
..
[405115]
Switch to side-by-side view
--- a +++ b/datasets_csv/Preprocessing.ipynb @@ -0,0 +1,6448 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import os\n", + "from os.path import join\n", + "\n", + "import pandas as pd\n", + "import numpy as np\n", + "\n", + "label_col = 'survival_months'\n", + "n_bins = 4\n", + "eps = 1e-6" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "def add_bins(slide_data):\n", + " assert 'case_id' in slide_data.columns and 'censorship' in slide_data.columns\n", + " \n", + " patients_df = slide_data.drop_duplicates(['case_id']).copy()\n", + " uncensored_df = patients_df[patients_df['censorship'] < 1]\n", + " disc_labels, q_bins = pd.qcut(uncensored_df[label_col], q=n_bins, retbins=True, labels=False)\n", + " q_bins[-1] = slide_data[label_col].max() + eps\n", + " q_bins[0] = slide_data[label_col].min() - eps\n", + "\n", + " disc_labels, q_bins = pd.cut(patients_df[label_col], bins=q_bins, retbins=True, labels=False, right=False, include_lowest=True)\n", + " patients_df.insert(2, 'label', disc_labels.values.astype(int))\n", + "\n", + " patient_dict = {}\n", + " slide_data = slide_data.set_index('case_id')\n", + " for patient in patients_df['case_id']:\n", + " slide_ids = slide_data.loc[patient, 'slide_id']\n", + " if isinstance(slide_ids, str):\n", + " slide_ids = np.array(slide_ids).reshape(-1)\n", + " else:\n", + " slide_ids = slide_ids.values\n", + " patient_dict.update({patient:slide_ids})\n", + " \n", + " return q_bins, patient_dict, patients_df" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "slide_data = pd.read_csv('./tcga_gbmlgg_all_clean.csv.zip', compression='zip', header=0, index_col=0, sep=',', low_memory=False)\n", + "\n", + "n_bins = 4\n", + "eps = 1e-6\n", + "\n", + "### Asserts that 'case_id' is a column, not an index.\n", + "if 'case_id' not in slide_data:\n", + " slide_data.index = slide_data.index.str[:12]\n", + " slide_data['case_id'] = slide_data.index\n", + " slide_data = slide_data.reset_index(drop=True)\n", + "\n", + "q_bins, patients_dict, slide_data = add_bins(slide_data)\n", + "\n", + "slide_data.reset_index(drop=True, inplace=True)\n", + "slide_data = slide_data.assign(slide_id=slide_data['case_id'])\n", + "\n", + "label_dict = {}\n", + "key_count = 0\n", + "for i in range(len(q_bins)-1):\n", + " for c in [0, 1]:\n", + " label_dict.update({(i, c):key_count})\n", + " key_count+=1\n", + "\n", + "for i in slide_data.index:\n", + " key = slide_data.loc[i, 'label']\n", + " slide_data.at[i, 'disc_label'] = key\n", + " censorship = slide_data.loc[i, 'censorship']\n", + " key = (key, int(censorship))\n", + " slide_data.at[i, 'label'] = label_dict[key]\n", + "\n", + "bins = q_bins\n", + "num_classes=len(label_dict)\n", + "patients_df = slide_data.drop_duplicates(['case_id'])\n", + "patient_data = {'case_id':patients_df['case_id'].values, 'label':patients_df['label'].values}\n", + "\n", + "new_cols = list(slide_data.columns[-2:]) + list(slide_data.columns[:-2])\n", + "slide_data = slide_data[new_cols]\n", + "metadata = slide_data.columns[:11]" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "from sklearn.pipeline import Pipeline\n", + "from sklearn.decomposition import PCA\n", + "from sklearn.preprocessing import StandardScaler\n", + "\n", + "\n", + "def series_intersection(s1, s2):\n", + " return pd.Series(list(set(s1) & set(s2)))\n", + "\n", + "genomic_features = slide_data.drop(metadata, axis=1)\n", + "scaler_omic = StandardScaler().fit(genomic_features)" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/mahmoodlab/anaconda3/lib/python3.8/site-packages/IPython/core/interactiveshell.py:3071: DtypeWarning: Columns (2) have mixed types.Specify dtype option on import or set low_memory=False.\n", + " has_raised = await self.run_ast_nodes(code_ast.body, cell_name,\n" + ] + } + ], + "source": [ + "import os\n", + "from os.path import join\n", + "\n", + "import pandas as pd\n", + "import numpy as np\n", + "\n", + "signatures = pd.read_csv('./signatures.csv')\n", + "slide_df = pd.read_csv('./tcga_gbmlgg_all_clean.csv.zip')" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "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>Unnamed: 0</th>\n", + " <th>Unnamed: 0.1</th>\n", + " <th>case_id</th>\n", + " <th>slide_id</th>\n", + " <th>site</th>\n", + " <th>is_female</th>\n", + " <th>oncotree_code</th>\n", + " <th>age</th>\n", + " <th>survival_months</th>\n", + " <th>censorship</th>\n", + " <th>...</th>\n", + " <th>ZSCAN10_rnaseq</th>\n", + " <th>ZSCAN12_rnaseq</th>\n", + " <th>ZSCAN20_rnaseq</th>\n", + " <th>ZSCAN21_rnaseq</th>\n", + " <th>ZSCAN22_rnaseq</th>\n", + " <th>ZSCAN2_rnaseq</th>\n", + " <th>ZSCAN9_rnaseq</th>\n", + " <th>ZXDA_rnaseq</th>\n", + " <th>ZXDB_rnaseq</th>\n", + " <th>ZXDC_rnaseq</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>0</th>\n", + " <td>0</td>\n", + " <td>0</td>\n", + " <td>TCGA-02-0047</td>\n", + " <td>TCGA-02-0047-01Z-00-DX1.4755D138-5842-4159-848...</td>\n", + " <td>2</td>\n", + " <td>0.0</td>\n", + " <td>GBM</td>\n", + " <td>78.0</td>\n", + " <td>14.72</td>\n", + " <td>0.0</td>\n", + " <td>...</td>\n", + " <td>-0.1599</td>\n", + " <td>-0.59540</td>\n", + " <td>0.0813</td>\n", + " <td>-1.16960</td>\n", + " <td>-0.1728</td>\n", + " <td>-0.1144</td>\n", + " <td>-0.4155</td>\n", + " <td>0.4046</td>\n", + " <td>-0.01680</td>\n", + " <td>0.3026</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1</th>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>TCGA-06-0125</td>\n", + " <td>TCGA-06-0125-01Z-00-DX1.8e0915b2-8dc3-4753-806...</td>\n", + " <td>6</td>\n", + " <td>1.0</td>\n", + " <td>GBM</td>\n", + " <td>63.0</td>\n", + " <td>47.57</td>\n", + " <td>0.0</td>\n", + " <td>...</td>\n", + " <td>0.4608</td>\n", + " <td>0.52815</td>\n", + " <td>1.2580</td>\n", + " <td>1.41685</td>\n", + " <td>2.4839</td>\n", + " <td>-0.2388</td>\n", + " <td>0.9025</td>\n", + " <td>0.3242</td>\n", + " <td>1.01905</td>\n", + " <td>0.2265</td>\n", + " </tr>\n", + " <tr>\n", + " <th>2</th>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>TCGA-06-0125</td>\n", + " <td>TCGA-06-0125-01Z-00-DX2.4f9cef92-2bdb-480d-870...</td>\n", + " <td>6</td>\n", + " <td>1.0</td>\n", + " <td>GBM</td>\n", + " <td>63.0</td>\n", + " <td>47.57</td>\n", + " <td>0.0</td>\n", + " <td>...</td>\n", + " <td>0.4608</td>\n", + " <td>0.52815</td>\n", + " <td>1.2580</td>\n", + " <td>1.41685</td>\n", + " <td>2.4839</td>\n", + " <td>-0.2388</td>\n", + " <td>0.9025</td>\n", + " <td>0.3242</td>\n", + " <td>1.01905</td>\n", + " <td>0.2265</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3</th>\n", + " <td>3</td>\n", + " <td>3</td>\n", + " <td>TCGA-06-0129</td>\n", + " <td>TCGA-06-0129-01Z-00-DX1.b7bddf7d-f39e-45e7-a78...</td>\n", + " <td>6</td>\n", + " <td>0.0</td>\n", + " <td>GBM</td>\n", + " <td>30.0</td>\n", + " <td>33.64</td>\n", + " <td>0.0</td>\n", + " <td>...</td>\n", + " <td>-0.2960</td>\n", + " <td>-0.75980</td>\n", + " <td>1.2706</td>\n", + " <td>-0.14840</td>\n", + " <td>1.4803</td>\n", + " <td>1.5796</td>\n", + " <td>1.0245</td>\n", + " <td>1.0492</td>\n", + " <td>5.78560</td>\n", + " <td>1.7766</td>\n", + " </tr>\n", + " <tr>\n", + " <th>4</th>\n", + " <td>4</td>\n", + " <td>4</td>\n", + " <td>TCGA-06-0129</td>\n", + " <td>TCGA-06-0129-01Z-00-DX2.1ea78b46-1dc7-44d8-81b...</td>\n", + " <td>6</td>\n", + " <td>0.0</td>\n", + " <td>GBM</td>\n", + " <td>30.0</td>\n", + " <td>33.64</td>\n", + " <td>0.0</td>\n", + " <td>...</td>\n", + " <td>-0.2960</td>\n", + " <td>-0.75980</td>\n", + " <td>1.2706</td>\n", + " <td>-0.14840</td>\n", + " <td>1.4803</td>\n", + " <td>1.5796</td>\n", + " <td>1.0245</td>\n", + " <td>1.0492</td>\n", + " <td>5.78560</td>\n", + " <td>1.7766</td>\n", + " </tr>\n", + " <tr>\n", + " <th>...</th>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1037</th>\n", + " <td>1037</td>\n", + " <td>1037</td>\n", + " <td>TCGA-WY-A85A</td>\n", + " <td>TCGA-WY-A85A-01Z-00-DX1.CB302B89-F89A-40FD-A7D...</td>\n", + " <td>WY</td>\n", + " <td>0.0</td>\n", + " <td>ASTR</td>\n", + " <td>20.0</td>\n", + " <td>43.36</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-0.2997</td>\n", + " <td>-0.67560</td>\n", + " <td>0.2714</td>\n", + " <td>0.36210</td>\n", + " <td>-0.2401</td>\n", + " <td>1.4333</td>\n", + " <td>0.2715</td>\n", + " <td>-0.5415</td>\n", + " <td>-0.69620</td>\n", + " <td>-0.1123</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1038</th>\n", + " <td>1038</td>\n", + " <td>1038</td>\n", + " <td>TCGA-WY-A85B</td>\n", + " <td>TCGA-WY-A85B-01Z-00-DX1.1E4B796A-A1E3-45F9-807...</td>\n", + " <td>WY</td>\n", + " <td>0.0</td>\n", + " <td>ASTR</td>\n", + " <td>24.0</td>\n", + " <td>45.76</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-0.0678</td>\n", + " <td>0.30360</td>\n", + " <td>0.3361</td>\n", + " <td>1.21610</td>\n", + " <td>0.9365</td>\n", + " <td>1.4954</td>\n", + " <td>1.4201</td>\n", + " <td>-0.3525</td>\n", + " <td>0.52860</td>\n", + " <td>0.1971</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1039</th>\n", + " <td>1039</td>\n", + " <td>1039</td>\n", + " <td>TCGA-WY-A85C</td>\n", + " <td>TCGA-WY-A85C-01Z-00-DX1.E0A6429A-91B3-4FFE-9FF...</td>\n", + " <td>WY</td>\n", + " <td>0.0</td>\n", + " <td>ASTR</td>\n", + " <td>36.0</td>\n", + " <td>46.85</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>0.0320</td>\n", + " <td>-1.01940</td>\n", + " <td>0.6582</td>\n", + " <td>2.55740</td>\n", + " <td>1.4708</td>\n", + " <td>0.8381</td>\n", + " <td>2.9481</td>\n", + " <td>0.1252</td>\n", + " <td>0.75300</td>\n", + " <td>0.9603</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1040</th>\n", + " <td>1040</td>\n", + " <td>1040</td>\n", + " <td>TCGA-WY-A85D</td>\n", + " <td>TCGA-WY-A85D-01Z-00-DX1.FB8C252B-7A88-4B14-B3C...</td>\n", + " <td>WY</td>\n", + " <td>0.0</td>\n", + " <td>OAST</td>\n", + " <td>60.0</td>\n", + " <td>37.68</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-0.3021</td>\n", + " <td>-0.34820</td>\n", + " <td>-0.4824</td>\n", + " <td>1.57910</td>\n", + " <td>0.0187</td>\n", + " <td>-0.7983</td>\n", + " <td>1.4101</td>\n", + " <td>-1.0976</td>\n", + " <td>-1.00950</td>\n", + " <td>0.5940</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1041</th>\n", + " <td>1041</td>\n", + " <td>1041</td>\n", + " <td>TCGA-WY-A85E</td>\n", + " <td>TCGA-WY-A85E-01Z-00-DX1.AA7A4C1F-99AA-490D-B6D...</td>\n", + " <td>WY</td>\n", + " <td>1.0</td>\n", + " <td>OAST</td>\n", + " <td>48.0</td>\n", + " <td>20.80</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-0.2576</td>\n", + " <td>0.89960</td>\n", + " <td>-0.7533</td>\n", + " <td>1.42710</td>\n", + " <td>-0.6667</td>\n", + " <td>0.8354</td>\n", + " <td>1.2988</td>\n", + " <td>-0.4902</td>\n", + " <td>-0.42940</td>\n", + " <td>-2.0717</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "<p>1042 rows × 2842 columns</p>\n", + "</div>" + ], + "text/plain": [ + " Unnamed: 0 Unnamed: 0.1 case_id \\\n", + "0 0 0 TCGA-02-0047 \n", + "1 1 1 TCGA-06-0125 \n", + "2 2 2 TCGA-06-0125 \n", + "3 3 3 TCGA-06-0129 \n", + "4 4 4 TCGA-06-0129 \n", + "... ... ... ... \n", + "1037 1037 1037 TCGA-WY-A85A \n", + "1038 1038 1038 TCGA-WY-A85B \n", + "1039 1039 1039 TCGA-WY-A85C \n", + "1040 1040 1040 TCGA-WY-A85D \n", + "1041 1041 1041 TCGA-WY-A85E \n", + "\n", + " slide_id site is_female \\\n", + "0 TCGA-02-0047-01Z-00-DX1.4755D138-5842-4159-848... 2 0.0 \n", + "1 TCGA-06-0125-01Z-00-DX1.8e0915b2-8dc3-4753-806... 6 1.0 \n", + "2 TCGA-06-0125-01Z-00-DX2.4f9cef92-2bdb-480d-870... 6 1.0 \n", + "3 TCGA-06-0129-01Z-00-DX1.b7bddf7d-f39e-45e7-a78... 6 0.0 \n", + "4 TCGA-06-0129-01Z-00-DX2.1ea78b46-1dc7-44d8-81b... 6 0.0 \n", + "... ... ... ... \n", + "1037 TCGA-WY-A85A-01Z-00-DX1.CB302B89-F89A-40FD-A7D... WY 0.0 \n", + "1038 TCGA-WY-A85B-01Z-00-DX1.1E4B796A-A1E3-45F9-807... WY 0.0 \n", + "1039 TCGA-WY-A85C-01Z-00-DX1.E0A6429A-91B3-4FFE-9FF... WY 0.0 \n", + "1040 TCGA-WY-A85D-01Z-00-DX1.FB8C252B-7A88-4B14-B3C... WY 0.0 \n", + "1041 TCGA-WY-A85E-01Z-00-DX1.AA7A4C1F-99AA-490D-B6D... WY 1.0 \n", + "\n", + " oncotree_code age survival_months censorship ... ZSCAN10_rnaseq \\\n", + "0 GBM 78.0 14.72 0.0 ... -0.1599 \n", + "1 GBM 63.0 47.57 0.0 ... 0.4608 \n", + "2 GBM 63.0 47.57 0.0 ... 0.4608 \n", + "3 GBM 30.0 33.64 0.0 ... -0.2960 \n", + "4 GBM 30.0 33.64 0.0 ... -0.2960 \n", + "... ... ... ... ... ... ... \n", + "1037 ASTR 20.0 43.36 1.0 ... -0.2997 \n", + "1038 ASTR 24.0 45.76 1.0 ... -0.0678 \n", + "1039 ASTR 36.0 46.85 1.0 ... 0.0320 \n", + "1040 OAST 60.0 37.68 1.0 ... -0.3021 \n", + "1041 OAST 48.0 20.80 1.0 ... -0.2576 \n", + "\n", + " ZSCAN12_rnaseq ZSCAN20_rnaseq ZSCAN21_rnaseq ZSCAN22_rnaseq \\\n", + "0 -0.59540 0.0813 -1.16960 -0.1728 \n", + "1 0.52815 1.2580 1.41685 2.4839 \n", + "2 0.52815 1.2580 1.41685 2.4839 \n", + "3 -0.75980 1.2706 -0.14840 1.4803 \n", + "4 -0.75980 1.2706 -0.14840 1.4803 \n", + "... ... ... ... ... \n", + "1037 -0.67560 0.2714 0.36210 -0.2401 \n", + "1038 0.30360 0.3361 1.21610 0.9365 \n", + "1039 -1.01940 0.6582 2.55740 1.4708 \n", + "1040 -0.34820 -0.4824 1.57910 0.0187 \n", + "1041 0.89960 -0.7533 1.42710 -0.6667 \n", + "\n", + " ZSCAN2_rnaseq ZSCAN9_rnaseq ZXDA_rnaseq ZXDB_rnaseq ZXDC_rnaseq \n", + "0 -0.1144 -0.4155 0.4046 -0.01680 0.3026 \n", + "1 -0.2388 0.9025 0.3242 1.01905 0.2265 \n", + "2 -0.2388 0.9025 0.3242 1.01905 0.2265 \n", + "3 1.5796 1.0245 1.0492 5.78560 1.7766 \n", + "4 1.5796 1.0245 1.0492 5.78560 1.7766 \n", + "... ... ... ... ... ... \n", + "1037 1.4333 0.2715 -0.5415 -0.69620 -0.1123 \n", + "1038 1.4954 1.4201 -0.3525 0.52860 0.1971 \n", + "1039 0.8381 2.9481 0.1252 0.75300 0.9603 \n", + "1040 -0.7983 1.4101 -1.0976 -1.00950 0.5940 \n", + "1041 0.8354 1.2988 -0.4902 -0.42940 -2.0717 \n", + "\n", + "[1042 rows x 2842 columns]" + ] + }, + "execution_count": 43, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.read_csv(fname)" + ] + }, + { + "cell_type": "code", + "execution_count": 76, + "metadata": {}, + "outputs": [], + "source": [ + "omic_from_signatures = []\n", + "for col in signatures.columns:\n", + " omic = signatures[col].dropna().unique()\n", + " omic_from_signatures.append(omic)\n", + "\n", + "omic_from_signatures = np.concatenate(omic_from_signatures)" + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/mahmoodlab/anaconda3/lib/python3.8/site-packages/IPython/core/interactiveshell.py:3071: DtypeWarning: Columns (3) have mixed types.Specify dtype option on import or set low_memory=False.\n", + " has_raised = await self.run_ast_nodes(code_ast.body, cell_name,\n" + ] + } + ], + "source": [ + "for fname in os.listdir('./'):\n", + " if fname.endswith('.csv.zip'):\n", + " slide_df = pd.read_csv(fname)" + ] + }, + { + "cell_type": "code", + "execution_count": 81, + "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>Unnamed: 0</th>\n", + " <th>Unnamed: 0.1</th>\n", + " <th>case_id</th>\n", + " <th>slide_id</th>\n", + " <th>site</th>\n", + " <th>is_female</th>\n", + " <th>oncotree_code</th>\n", + " <th>age</th>\n", + " <th>survival_months</th>\n", + " <th>censorship</th>\n", + " <th>...</th>\n", + " <th>ZSCAN10_rnaseq</th>\n", + " <th>ZSCAN12_rnaseq</th>\n", + " <th>ZSCAN20_rnaseq</th>\n", + " <th>ZSCAN21_rnaseq</th>\n", + " <th>ZSCAN22_rnaseq</th>\n", + " <th>ZSCAN2_rnaseq</th>\n", + " <th>ZSCAN9_rnaseq</th>\n", + " <th>ZXDA_rnaseq</th>\n", + " <th>ZXDB_rnaseq</th>\n", + " <th>ZXDC_rnaseq</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>0</th>\n", + " <td>0</td>\n", + " <td>0</td>\n", + " <td>TCGA-05-4249</td>\n", + " <td>TCGA-05-4249-01Z-00-DX1.9fce0297-cc19-4c04-872...</td>\n", + " <td>5</td>\n", + " <td>0.0</td>\n", + " <td>LUAD</td>\n", + " <td>67.0</td>\n", + " <td>50.03</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-0.1238</td>\n", + " <td>0.7530</td>\n", + " <td>0.6552</td>\n", + " <td>-1.0013</td>\n", + " <td>0.2353</td>\n", + " <td>2.6532</td>\n", + " <td>1.1103</td>\n", + " <td>0.6149</td>\n", + " <td>0.5725</td>\n", + " <td>0.2889</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1</th>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>TCGA-05-4250</td>\n", + " <td>TCGA-05-4250-01Z-00-DX1.90f67fdf-dff9-46ca-af7...</td>\n", + " <td>5</td>\n", + " <td>1.0</td>\n", + " <td>LUAD</td>\n", + " <td>79.0</td>\n", + " <td>3.98</td>\n", + " <td>0.0</td>\n", + " <td>...</td>\n", + " <td>-0.1238</td>\n", + " <td>0.4810</td>\n", + " <td>-0.8255</td>\n", + " <td>0.2825</td>\n", + " <td>-1.2502</td>\n", + " <td>-0.9024</td>\n", + " <td>-0.1472</td>\n", + " <td>0.5118</td>\n", + " <td>-0.1673</td>\n", + " <td>-0.8006</td>\n", + " </tr>\n", + " <tr>\n", + " <th>2</th>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>TCGA-05-4382</td>\n", + " <td>TCGA-05-4382-01Z-00-DX1.76b49a4c-dbbb-48b0-b67...</td>\n", + " <td>5</td>\n", + " <td>0.0</td>\n", + " <td>LUAD</td>\n", + " <td>68.0</td>\n", + " <td>19.94</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>0.3265</td>\n", + " <td>0.4462</td>\n", + " <td>1.1847</td>\n", + " <td>0.8765</td>\n", + " <td>-0.7999</td>\n", + " <td>1.7566</td>\n", + " <td>1.1757</td>\n", + " <td>-0.4399</td>\n", + " <td>-0.2751</td>\n", + " <td>-0.4668</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3</th>\n", + " <td>3</td>\n", + " <td>3</td>\n", + " <td>TCGA-05-4384</td>\n", + " <td>TCGA-05-4384-01Z-00-DX1.CA68BF29-BBE3-4C8E-B48...</td>\n", + " <td>5</td>\n", + " <td>0.0</td>\n", + " <td>LUAD</td>\n", + " <td>66.0</td>\n", + " <td>13.99</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-0.1238</td>\n", + " <td>-0.0369</td>\n", + " <td>0.5766</td>\n", + " <td>0.0083</td>\n", + " <td>0.1344</td>\n", + " <td>0.8299</td>\n", + " <td>0.6599</td>\n", + " <td>1.4844</td>\n", + " <td>0.9748</td>\n", + " <td>0.7481</td>\n", + " </tr>\n", + " <tr>\n", + " <th>4</th>\n", + " <td>4</td>\n", + " <td>4</td>\n", + " <td>TCGA-05-4390</td>\n", + " <td>TCGA-05-4390-01Z-00-DX1.858E64DF-DD3E-4F43-B7C...</td>\n", + " <td>5</td>\n", + " <td>1.0</td>\n", + " <td>LUAD</td>\n", + " <td>58.0</td>\n", + " <td>36.99</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-0.1238</td>\n", + " <td>0.4751</td>\n", + " <td>1.2404</td>\n", + " <td>0.6932</td>\n", + " <td>-0.2792</td>\n", + " <td>2.1326</td>\n", + " <td>0.1621</td>\n", + " <td>-0.0462</td>\n", + " <td>1.8418</td>\n", + " <td>-0.9922</td>\n", + " </tr>\n", + " <tr>\n", + " <th>...</th>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " </tr>\n", + " <tr>\n", + " <th>511</th>\n", + " <td>511</td>\n", + " <td>511</td>\n", + " <td>TCGA-NJ-A55O</td>\n", + " <td>TCGA-NJ-A55O-01Z-00-DX1.8E23C821-B8BB-4D89-9E3...</td>\n", + " <td>NJ</td>\n", + " <td>1.0</td>\n", + " <td>LUAD</td>\n", + " <td>56.0</td>\n", + " <td>0.43</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-0.0781</td>\n", + " <td>-0.2368</td>\n", + " <td>0.5056</td>\n", + " <td>-0.2771</td>\n", + " <td>0.1067</td>\n", + " <td>-0.0153</td>\n", + " <td>-0.2546</td>\n", + " <td>-0.4205</td>\n", + " <td>-0.3773</td>\n", + " <td>0.0551</td>\n", + " </tr>\n", + " <tr>\n", + " <th>512</th>\n", + " <td>512</td>\n", + " <td>512</td>\n", + " <td>TCGA-NJ-A55R</td>\n", + " <td>TCGA-NJ-A55R-01Z-00-DX1.2E2B3642-4E1C-47DB-AF7...</td>\n", + " <td>NJ</td>\n", + " <td>0.0</td>\n", + " <td>LUAD</td>\n", + " <td>67.0</td>\n", + " <td>19.81</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>6.1880</td>\n", + " <td>0.2405</td>\n", + " <td>0.0751</td>\n", + " <td>1.9723</td>\n", + " <td>0.6093</td>\n", + " <td>0.6135</td>\n", + " <td>1.7846</td>\n", + " <td>0.0588</td>\n", + " <td>-0.1157</td>\n", + " <td>1.2831</td>\n", + " </tr>\n", + " <tr>\n", + " <th>513</th>\n", + " <td>513</td>\n", + " <td>513</td>\n", + " <td>TCGA-NJ-A7XG</td>\n", + " <td>TCGA-NJ-A7XG-01Z-00-DX1.4A876254-653C-410B-A36...</td>\n", + " <td>NJ</td>\n", + " <td>0.0</td>\n", + " <td>LUAD</td>\n", + " <td>49.0</td>\n", + " <td>20.27</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-0.1238</td>\n", + " <td>-0.0041</td>\n", + " <td>-0.8129</td>\n", + " <td>-0.4409</td>\n", + " <td>0.6778</td>\n", + " <td>-0.5506</td>\n", + " <td>1.4350</td>\n", + " <td>-1.5823</td>\n", + " <td>-1.3015</td>\n", + " <td>0.4371</td>\n", + " </tr>\n", + " <tr>\n", + " <th>514</th>\n", + " <td>514</td>\n", + " <td>514</td>\n", + " <td>TCGA-O1-A52J</td>\n", + " <td>TCGA-O1-A52J-01Z-00-DX1.26F6ECCA-D614-4950-98E...</td>\n", + " <td>O1</td>\n", + " <td>1.0</td>\n", + " <td>LUAD</td>\n", + " <td>74.0</td>\n", + " <td>59.07</td>\n", + " <td>0.0</td>\n", + " <td>...</td>\n", + " <td>-0.1238</td>\n", + " <td>-0.1263</td>\n", + " <td>0.8472</td>\n", + " <td>-0.3943</td>\n", + " <td>-0.7671</td>\n", + " <td>-1.1313</td>\n", + " <td>-0.9671</td>\n", + " <td>4.2234</td>\n", + " <td>0.9716</td>\n", + " <td>0.6699</td>\n", + " </tr>\n", + " <tr>\n", + " <th>515</th>\n", + " <td>515</td>\n", + " <td>515</td>\n", + " <td>TCGA-S2-AA1A</td>\n", + " <td>TCGA-S2-AA1A-01Z-00-DX1.4B5D5FAE-8305-4D2D-B24...</td>\n", + " <td>S2</td>\n", + " <td>1.0</td>\n", + " <td>LUAD</td>\n", + " <td>68.0</td>\n", + " <td>16.85</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-0.1238</td>\n", + " <td>0.5292</td>\n", + " <td>-0.8343</td>\n", + " <td>0.7741</td>\n", + " <td>-0.6405</td>\n", + " <td>-0.3901</td>\n", + " <td>0.0245</td>\n", + " <td>0.5245</td>\n", + " <td>-0.1738</td>\n", + " <td>2.4043</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "<p>516 rows × 3106 columns</p>\n", + "</div>" + ], + "text/plain": [ + " Unnamed: 0 Unnamed: 0.1 case_id \\\n", + "0 0 0 TCGA-05-4249 \n", + "1 1 1 TCGA-05-4250 \n", + "2 2 2 TCGA-05-4382 \n", + "3 3 3 TCGA-05-4384 \n", + "4 4 4 TCGA-05-4390 \n", + ".. ... ... ... \n", + "511 511 511 TCGA-NJ-A55O \n", + "512 512 512 TCGA-NJ-A55R \n", + "513 513 513 TCGA-NJ-A7XG \n", + "514 514 514 TCGA-O1-A52J \n", + "515 515 515 TCGA-S2-AA1A \n", + "\n", + " slide_id site is_female \\\n", + "0 TCGA-05-4249-01Z-00-DX1.9fce0297-cc19-4c04-872... 5 0.0 \n", + "1 TCGA-05-4250-01Z-00-DX1.90f67fdf-dff9-46ca-af7... 5 1.0 \n", + "2 TCGA-05-4382-01Z-00-DX1.76b49a4c-dbbb-48b0-b67... 5 0.0 \n", + "3 TCGA-05-4384-01Z-00-DX1.CA68BF29-BBE3-4C8E-B48... 5 0.0 \n", + "4 TCGA-05-4390-01Z-00-DX1.858E64DF-DD3E-4F43-B7C... 5 1.0 \n", + ".. ... ... ... \n", + "511 TCGA-NJ-A55O-01Z-00-DX1.8E23C821-B8BB-4D89-9E3... NJ 1.0 \n", + "512 TCGA-NJ-A55R-01Z-00-DX1.2E2B3642-4E1C-47DB-AF7... NJ 0.0 \n", + "513 TCGA-NJ-A7XG-01Z-00-DX1.4A876254-653C-410B-A36... NJ 0.0 \n", + "514 TCGA-O1-A52J-01Z-00-DX1.26F6ECCA-D614-4950-98E... O1 1.0 \n", + "515 TCGA-S2-AA1A-01Z-00-DX1.4B5D5FAE-8305-4D2D-B24... S2 1.0 \n", + "\n", + " oncotree_code age survival_months censorship ... ZSCAN10_rnaseq \\\n", + "0 LUAD 67.0 50.03 1.0 ... -0.1238 \n", + "1 LUAD 79.0 3.98 0.0 ... -0.1238 \n", + "2 LUAD 68.0 19.94 1.0 ... 0.3265 \n", + "3 LUAD 66.0 13.99 1.0 ... -0.1238 \n", + "4 LUAD 58.0 36.99 1.0 ... -0.1238 \n", + ".. ... ... ... ... ... ... \n", + "511 LUAD 56.0 0.43 1.0 ... -0.0781 \n", + "512 LUAD 67.0 19.81 1.0 ... 6.1880 \n", + "513 LUAD 49.0 20.27 1.0 ... -0.1238 \n", + "514 LUAD 74.0 59.07 0.0 ... -0.1238 \n", + "515 LUAD 68.0 16.85 1.0 ... -0.1238 \n", + "\n", + " ZSCAN12_rnaseq ZSCAN20_rnaseq ZSCAN21_rnaseq ZSCAN22_rnaseq \\\n", + "0 0.7530 0.6552 -1.0013 0.2353 \n", + "1 0.4810 -0.8255 0.2825 -1.2502 \n", + "2 0.4462 1.1847 0.8765 -0.7999 \n", + "3 -0.0369 0.5766 0.0083 0.1344 \n", + "4 0.4751 1.2404 0.6932 -0.2792 \n", + ".. ... ... ... ... \n", + "511 -0.2368 0.5056 -0.2771 0.1067 \n", + "512 0.2405 0.0751 1.9723 0.6093 \n", + "513 -0.0041 -0.8129 -0.4409 0.6778 \n", + "514 -0.1263 0.8472 -0.3943 -0.7671 \n", + "515 0.5292 -0.8343 0.7741 -0.6405 \n", + "\n", + " ZSCAN2_rnaseq ZSCAN9_rnaseq ZXDA_rnaseq ZXDB_rnaseq ZXDC_rnaseq \n", + "0 2.6532 1.1103 0.6149 0.5725 0.2889 \n", + "1 -0.9024 -0.1472 0.5118 -0.1673 -0.8006 \n", + "2 1.7566 1.1757 -0.4399 -0.2751 -0.4668 \n", + "3 0.8299 0.6599 1.4844 0.9748 0.7481 \n", + "4 2.1326 0.1621 -0.0462 1.8418 -0.9922 \n", + ".. ... ... ... ... ... \n", + "511 -0.0153 -0.2546 -0.4205 -0.3773 0.0551 \n", + "512 0.6135 1.7846 0.0588 -0.1157 1.2831 \n", + "513 -0.5506 1.4350 -1.5823 -1.3015 0.4371 \n", + "514 -1.1313 -0.9671 4.2234 0.9716 0.6699 \n", + "515 -0.3901 0.0245 0.5245 -0.1738 2.4043 \n", + "\n", + "[516 rows x 3106 columns]" + ] + }, + "execution_count": 81, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "fname = '../dataset_csv/tcga_luad_all_clean.csv.zip'\n", + "slide_df = pd.read_csv(fname)\n", + "slide_df" + ] + }, + { + "cell_type": "code", + "execution_count": 79, + "metadata": {}, + "outputs": [], + "source": [ + "fname = '../dataset_csv/tcga_luad_all_clean.csv.zip'\n", + "slide_df = pd.read_csv(fname)\n", + "omic_overlap = np.concatenate([omic_from_signatures+mode for mode in ['_mut', '_cnv', '_rnaseq']])\n", + "omic_overlap = sorted(series_intersection(omic_overlap, slide_df.columns))\n", + "slide_df[list(slide_df.columns[:9]) + omic_overlap].to_csv('../dataset_csv_sig/%s' % fname)" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/mahmoodlab/anaconda3/lib/python3.8/site-packages/IPython/core/interactiveshell.py:3071: DtypeWarning: Columns (3) have mixed types.Specify dtype option on import or set low_memory=False.\n", + " has_raised = await self.run_ast_nodes(code_ast.body, cell_name,\n" + ] + } + ], + "source": [ + "for fname in os.listdir('./'):\n", + " if fname.endswith('.csv.zip'):\n", + " slide_df = pd.read_csv(fname)" + ] + }, + { + "cell_type": "code", + "execution_count": 55, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "'tcga_luad_all_clean.csv.zip'" + ] + }, + "execution_count": 55, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "fname" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/mahmoodlab/anaconda3/lib/python3.8/site-packages/IPython/core/interactiveshell.py:3071: DtypeWarning: Columns (2) have mixed types.Specify dtype option on import or set low_memory=False.\n", + " has_raised = await self.run_ast_nodes(code_ast.body, cell_name,\n" + ] + } + ], + "source": [ + "\n", + "\n", + "omic_from_signatures = []\n", + "for col in signatures.columns:\n", + " omic = signatures[col].dropna().unique()\n", + " omic_from_signatures.append(omic)\n", + "\n", + "omic_from_signatures = np.concatenate(omic_from_signatures)\n", + "\n", + "def series_intersection(s1, s2):\n", + " return pd.Series(list(set(s1) & set(s2)))\n", + "\n", + "signatures = pd.read_csv('./signatures.csv')\n", + "slide_df = pd.read_csv('./tcga_gbmlgg_all_clean.csv.zip')\n", + "rnaseq_overlap = np.concatenate([omic_from_signatures+mode for mode in ['_rnaseq']])\n", + "rnaseq_overlap = sorted(series_intersection(rnaseq_overlap, slide_df.columns))\n", + "genomics_mut_cnv = list(slide_df.columns[slide_df.columns.str.contains('_mut|_cnv')])" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [], + "source": [ + "_ = slide_df[list(slide_df.columns[:9]) + rnaseq_overlap + genomics_mut_cnv]" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "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>case_id</th>\n", + " <th>slide_id</th>\n", + " <th>site</th>\n", + " <th>is_female</th>\n", + " <th>oncotree_code</th>\n", + " <th>age</th>\n", + " <th>survival_months</th>\n", + " <th>censorship</th>\n", + " <th>train</th>\n", + " <th>AAK1_rnaseq</th>\n", + " <th>...</th>\n", + " <th>AGAP2_cnv</th>\n", + " <th>TSPAN31_cnv</th>\n", + " <th>CDK4_cnv</th>\n", + " <th>MARCH9_cnv</th>\n", + " <th>CYP27B1_cnv</th>\n", + " <th>METTL1_cnv</th>\n", + " <th>TSFM_cnv</th>\n", + " <th>AVIL_cnv</th>\n", + " <th>CTDSP2_cnv</th>\n", + " <th>RN7SKP65_cnv</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>0</th>\n", + " <td>TCGA-02-0047</td>\n", + " <td>TCGA-02-0047-01Z-00-DX1.4755D138-5842-4159-848...</td>\n", + " <td>2</td>\n", + " <td>0.0</td>\n", + " <td>GBM</td>\n", + " <td>78.0</td>\n", + " <td>14.72</td>\n", + " <td>0.0</td>\n", + " <td>1.0</td>\n", + " <td>1.5517</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>0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1</th>\n", + " <td>TCGA-06-0125</td>\n", + " <td>TCGA-06-0125-01Z-00-DX1.8e0915b2-8dc3-4753-806...</td>\n", + " <td>6</td>\n", + " <td>1.0</td>\n", + " <td>GBM</td>\n", + " <td>63.0</td>\n", + " <td>47.57</td>\n", + " <td>0.0</td>\n", + " <td>1.0</td>\n", + " <td>0.5557</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>0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>2</th>\n", + " <td>TCGA-06-0125</td>\n", + " <td>TCGA-06-0125-01Z-00-DX2.4f9cef92-2bdb-480d-870...</td>\n", + " <td>6</td>\n", + " <td>1.0</td>\n", + " <td>GBM</td>\n", + " <td>63.0</td>\n", + " <td>47.57</td>\n", + " <td>0.0</td>\n", + " <td>1.0</td>\n", + " <td>0.5557</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>0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3</th>\n", + " <td>TCGA-06-0129</td>\n", + " <td>TCGA-06-0129-01Z-00-DX1.b7bddf7d-f39e-45e7-a78...</td>\n", + " <td>6</td>\n", + " <td>0.0</td>\n", + " <td>GBM</td>\n", + " <td>30.0</td>\n", + " <td>33.64</td>\n", + " <td>0.0</td>\n", + " <td>1.0</td>\n", + " <td>0.6442</td>\n", + " <td>...</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " </tr>\n", + " <tr>\n", + " <th>4</th>\n", + " <td>TCGA-06-0129</td>\n", + " <td>TCGA-06-0129-01Z-00-DX2.1ea78b46-1dc7-44d8-81b...</td>\n", + " <td>6</td>\n", + " <td>0.0</td>\n", + " <td>GBM</td>\n", + " <td>30.0</td>\n", + " <td>33.64</td>\n", + " <td>0.0</td>\n", + " <td>1.0</td>\n", + " <td>0.6442</td>\n", + " <td>...</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " </tr>\n", + " <tr>\n", + " <th>...</th>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1037</th>\n", + " <td>TCGA-WY-A85A</td>\n", + " <td>TCGA-WY-A85A-01Z-00-DX1.CB302B89-F89A-40FD-A7D...</td>\n", + " <td>WY</td>\n", + " <td>0.0</td>\n", + " <td>ASTR</td>\n", + " <td>20.0</td>\n", + " <td>43.36</td>\n", + " <td>1.0</td>\n", + " <td>1.0</td>\n", + " <td>-0.3841</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>0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1038</th>\n", + " <td>TCGA-WY-A85B</td>\n", + " <td>TCGA-WY-A85B-01Z-00-DX1.1E4B796A-A1E3-45F9-807...</td>\n", + " <td>WY</td>\n", + " <td>0.0</td>\n", + " <td>ASTR</td>\n", + " <td>24.0</td>\n", + " <td>45.76</td>\n", + " <td>1.0</td>\n", + " <td>1.0</td>\n", + " <td>-0.4479</td>\n", + " <td>...</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1039</th>\n", + " <td>TCGA-WY-A85C</td>\n", + " <td>TCGA-WY-A85C-01Z-00-DX1.E0A6429A-91B3-4FFE-9FF...</td>\n", + " <td>WY</td>\n", + " <td>0.0</td>\n", + " <td>ASTR</td>\n", + " <td>36.0</td>\n", + " <td>46.85</td>\n", + " <td>1.0</td>\n", + " <td>1.0</td>\n", + " <td>-0.2472</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>0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1040</th>\n", + " <td>TCGA-WY-A85D</td>\n", + " <td>TCGA-WY-A85D-01Z-00-DX1.FB8C252B-7A88-4B14-B3C...</td>\n", + " <td>WY</td>\n", + " <td>0.0</td>\n", + " <td>OAST</td>\n", + " <td>60.0</td>\n", + " <td>37.68</td>\n", + " <td>1.0</td>\n", + " <td>1.0</td>\n", + " <td>-0.5892</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>0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1041</th>\n", + " <td>TCGA-WY-A85E</td>\n", + " <td>TCGA-WY-A85E-01Z-00-DX1.AA7A4C1F-99AA-490D-B6D...</td>\n", + " <td>WY</td>\n", + " <td>1.0</td>\n", + " <td>OAST</td>\n", + " <td>48.0</td>\n", + " <td>20.80</td>\n", + " <td>1.0</td>\n", + " <td>1.0</td>\n", + " <td>-0.1087</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>0</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "<p>1042 rows × 2891 columns</p>\n", + "</div>" + ], + "text/plain": [ + " case_id slide_id site \\\n", + "0 TCGA-02-0047 TCGA-02-0047-01Z-00-DX1.4755D138-5842-4159-848... 2 \n", + "1 TCGA-06-0125 TCGA-06-0125-01Z-00-DX1.8e0915b2-8dc3-4753-806... 6 \n", + "2 TCGA-06-0125 TCGA-06-0125-01Z-00-DX2.4f9cef92-2bdb-480d-870... 6 \n", + "3 TCGA-06-0129 TCGA-06-0129-01Z-00-DX1.b7bddf7d-f39e-45e7-a78... 6 \n", + "4 TCGA-06-0129 TCGA-06-0129-01Z-00-DX2.1ea78b46-1dc7-44d8-81b... 6 \n", + "... ... ... ... \n", + "1037 TCGA-WY-A85A TCGA-WY-A85A-01Z-00-DX1.CB302B89-F89A-40FD-A7D... WY \n", + "1038 TCGA-WY-A85B TCGA-WY-A85B-01Z-00-DX1.1E4B796A-A1E3-45F9-807... WY \n", + "1039 TCGA-WY-A85C TCGA-WY-A85C-01Z-00-DX1.E0A6429A-91B3-4FFE-9FF... WY \n", + "1040 TCGA-WY-A85D TCGA-WY-A85D-01Z-00-DX1.FB8C252B-7A88-4B14-B3C... WY \n", + "1041 TCGA-WY-A85E TCGA-WY-A85E-01Z-00-DX1.AA7A4C1F-99AA-490D-B6D... WY \n", + "\n", + " is_female oncotree_code age survival_months censorship train \\\n", + "0 0.0 GBM 78.0 14.72 0.0 1.0 \n", + "1 1.0 GBM 63.0 47.57 0.0 1.0 \n", + "2 1.0 GBM 63.0 47.57 0.0 1.0 \n", + "3 0.0 GBM 30.0 33.64 0.0 1.0 \n", + "4 0.0 GBM 30.0 33.64 0.0 1.0 \n", + "... ... ... ... ... ... ... \n", + "1037 0.0 ASTR 20.0 43.36 1.0 1.0 \n", + "1038 0.0 ASTR 24.0 45.76 1.0 1.0 \n", + "1039 0.0 ASTR 36.0 46.85 1.0 1.0 \n", + "1040 0.0 OAST 60.0 37.68 1.0 1.0 \n", + "1041 1.0 OAST 48.0 20.80 1.0 1.0 \n", + "\n", + " AAK1_rnaseq ... AGAP2_cnv TSPAN31_cnv CDK4_cnv MARCH9_cnv \\\n", + "0 1.5517 ... 0 0 0 0 \n", + "1 0.5557 ... 0 0 0 0 \n", + "2 0.5557 ... 0 0 0 0 \n", + "3 0.6442 ... 2 2 2 2 \n", + "4 0.6442 ... 2 2 2 2 \n", + "... ... ... ... ... ... ... \n", + "1037 -0.3841 ... 0 0 0 0 \n", + "1038 -0.4479 ... -1 -1 -1 -1 \n", + "1039 -0.2472 ... 0 0 0 0 \n", + "1040 -0.5892 ... 0 0 0 0 \n", + "1041 -0.1087 ... 0 0 0 0 \n", + "\n", + " CYP27B1_cnv METTL1_cnv TSFM_cnv AVIL_cnv CTDSP2_cnv RN7SKP65_cnv \n", + "0 0 0 0 0 0 0 \n", + "1 0 0 0 0 0 0 \n", + "2 0 0 0 0 0 0 \n", + "3 2 2 2 2 2 2 \n", + "4 2 2 2 2 2 2 \n", + "... ... ... ... ... ... ... \n", + "1037 0 0 0 0 0 0 \n", + "1038 -1 -1 -1 -1 -1 -1 \n", + "1039 0 0 0 0 0 0 \n", + "1040 0 0 0 0 0 0 \n", + "1041 0 0 0 0 0 0 \n", + "\n", + "[1042 rows x 2891 columns]" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "_" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": {}, + "outputs": [], + "source": [ + "from scipy import stats\n", + "\n", + "slide_df = pd.read_csv(fname)\n", + "rnaseq = slide_df[slide_df.columns[slide_df.columns.str.contains('_rnaseq')]]\n", + "\n", + "top_k=2000\n", + "mad = stats.median_abs_deviation(rnaseq, axis=0)\n", + "sort_idx = np.argsort(mad)[-top_k:]\n", + "rnaseq = rnaseq[rnaseq.columns[sort_idx]]" + ] + }, + { + "cell_type": "code", + "execution_count": 45, + "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>CLASRP_rnaseq</th>\n", + " <th>NBAS_rnaseq</th>\n", + " <th>ARL2BP_rnaseq</th>\n", + " <th>TMEM199_rnaseq</th>\n", + " <th>TTC37_rnaseq</th>\n", + " <th>GTF2I_rnaseq</th>\n", + " <th>STYX_rnaseq</th>\n", + " <th>TSR3_rnaseq</th>\n", + " <th>SEC61A1_rnaseq</th>\n", + " <th>TRRAP_rnaseq</th>\n", + " <th>...</th>\n", + " <th>GET4_rnaseq</th>\n", + " <th>BRD9_rnaseq</th>\n", + " <th>NSUN2_rnaseq</th>\n", + " <th>PYCRL_rnaseq</th>\n", + " <th>HGH1_rnaseq</th>\n", + " <th>PRUNE_rnaseq</th>\n", + " <th>MAF1_rnaseq</th>\n", + " <th>CCDC127_rnaseq</th>\n", + " <th>EXOC3_rnaseq</th>\n", + " <th>PUF60_rnaseq</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>0</th>\n", + " <td>-0.5874</td>\n", + " <td>0.8371</td>\n", + " <td>0.7587</td>\n", + " <td>0.2188</td>\n", + " <td>-0.4040</td>\n", + " <td>2.3916</td>\n", + " <td>-0.7124</td>\n", + " <td>-1.0035</td>\n", + " <td>0.7356</td>\n", + " <td>-0.0249</td>\n", + " <td>...</td>\n", + " <td>-0.1915</td>\n", + " <td>0.3503</td>\n", + " <td>-1.1848</td>\n", + " <td>-1.4121</td>\n", + " <td>-0.2389</td>\n", + " <td>5.0110</td>\n", + " <td>1.4287</td>\n", + " <td>-0.3531</td>\n", + " <td>-0.8503</td>\n", + " <td>1.2995</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1</th>\n", + " <td>0.2811</td>\n", + " <td>0.2232</td>\n", + " <td>0.9000</td>\n", + " <td>3.2327</td>\n", + " <td>-0.0096</td>\n", + " <td>-0.4464</td>\n", + " <td>0.5219</td>\n", + " <td>0.3927</td>\n", + " <td>-0.3513</td>\n", + " <td>-0.7917</td>\n", + " <td>...</td>\n", + " <td>0.7627</td>\n", + " <td>-0.6092</td>\n", + " <td>0.1291</td>\n", + " <td>1.7400</td>\n", + " <td>-0.0250</td>\n", + " <td>-0.1531</td>\n", + " <td>0.5344</td>\n", + " <td>-0.0012</td>\n", + " <td>-0.9606</td>\n", + " <td>2.0233</td>\n", + " </tr>\n", + " <tr>\n", + " <th>2</th>\n", + " <td>1.5665</td>\n", + " <td>-0.4726</td>\n", + " <td>0.1693</td>\n", + " <td>0.9845</td>\n", + " <td>-0.6740</td>\n", + " <td>-0.3986</td>\n", + " <td>-0.2289</td>\n", + " <td>-0.2791</td>\n", + " <td>-0.0646</td>\n", + " <td>-0.4431</td>\n", + " <td>...</td>\n", + " <td>4.4123</td>\n", + " <td>1.4417</td>\n", + " <td>-0.5196</td>\n", + " <td>-1.3030</td>\n", + " <td>-1.1373</td>\n", + " <td>4.6041</td>\n", + " <td>-1.0135</td>\n", + " <td>1.3589</td>\n", + " <td>2.6994</td>\n", + " <td>-0.3068</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3</th>\n", + " <td>0.6169</td>\n", + " <td>-0.3266</td>\n", + " <td>-0.3082</td>\n", + " <td>-0.2220</td>\n", + " <td>0.5305</td>\n", + " <td>0.5360</td>\n", + " <td>0.2785</td>\n", + " <td>-1.0873</td>\n", + " <td>-1.0712</td>\n", + " <td>-0.3184</td>\n", + " <td>...</td>\n", + " <td>0.7665</td>\n", + " <td>-0.3344</td>\n", + " <td>0.0695</td>\n", + " <td>0.0040</td>\n", + " <td>0.2291</td>\n", + " <td>3.6034</td>\n", + " <td>0.1774</td>\n", + " <td>-0.2766</td>\n", + " <td>0.5080</td>\n", + " <td>0.6178</td>\n", + " </tr>\n", + " <tr>\n", + " <th>4</th>\n", + " <td>0.6406</td>\n", + " <td>-1.0330</td>\n", + " <td>-0.6522</td>\n", + " <td>0.1727</td>\n", + " <td>-0.7455</td>\n", + " <td>-0.6040</td>\n", + " <td>0.2553</td>\n", + " <td>1.0504</td>\n", + " <td>1.0583</td>\n", + " <td>-0.2884</td>\n", + " <td>...</td>\n", + " <td>3.3807</td>\n", + " <td>0.3364</td>\n", + " <td>-0.2792</td>\n", + " <td>4.8566</td>\n", + " <td>7.9296</td>\n", + " <td>1.6951</td>\n", + " <td>5.8943</td>\n", + " <td>1.3652</td>\n", + " <td>-0.8062</td>\n", + " <td>9.2417</td>\n", + " </tr>\n", + " <tr>\n", + " <th>...</th>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " </tr>\n", + " <tr>\n", + " <th>511</th>\n", + " <td>0.5640</td>\n", + " <td>0.1255</td>\n", + " <td>-1.3364</td>\n", + " <td>-0.8430</td>\n", + " <td>0.4406</td>\n", + " <td>-0.9735</td>\n", + " <td>-1.4547</td>\n", + " <td>-0.1983</td>\n", + " <td>-0.5259</td>\n", + " <td>-0.2029</td>\n", + " <td>...</td>\n", + " <td>3.0311</td>\n", + " <td>3.4963</td>\n", + " <td>2.5079</td>\n", + " <td>0.0556</td>\n", + " <td>0.5691</td>\n", + " <td>0.1104</td>\n", + " <td>-0.3776</td>\n", + " <td>2.6136</td>\n", + " <td>3.4259</td>\n", + " <td>-0.8442</td>\n", + " </tr>\n", + " <tr>\n", + " <th>512</th>\n", + " <td>1.2336</td>\n", + " <td>0.1902</td>\n", + " <td>-1.3500</td>\n", + " <td>-0.3472</td>\n", + " <td>0.4549</td>\n", + " <td>-0.6806</td>\n", + " <td>-1.1291</td>\n", + " <td>1.0677</td>\n", + " <td>1.1586</td>\n", + " <td>0.1959</td>\n", + " <td>...</td>\n", + " <td>0.5573</td>\n", + " <td>-0.7546</td>\n", + " <td>0.8104</td>\n", + " <td>0.1239</td>\n", + " <td>0.0985</td>\n", + " <td>2.9026</td>\n", + " <td>0.0173</td>\n", + " <td>0.3492</td>\n", + " <td>2.5703</td>\n", + " <td>1.0690</td>\n", + " </tr>\n", + " <tr>\n", + " <th>513</th>\n", + " <td>1.8148</td>\n", + " <td>-0.8502</td>\n", + " <td>-0.0628</td>\n", + " <td>-0.7776</td>\n", + " <td>0.6452</td>\n", + " <td>-0.4622</td>\n", + " <td>-1.2732</td>\n", + " <td>1.8145</td>\n", + " <td>-0.8767</td>\n", + " <td>-0.2980</td>\n", + " <td>...</td>\n", + " <td>1.4671</td>\n", + " <td>2.2343</td>\n", + " <td>2.1466</td>\n", + " <td>0.7868</td>\n", + " <td>0.6893</td>\n", + " <td>0.1571</td>\n", + " <td>0.9686</td>\n", + " <td>3.0870</td>\n", + " <td>5.6169</td>\n", + " <td>0.5300</td>\n", + " </tr>\n", + " <tr>\n", + " <th>514</th>\n", + " <td>0.0569</td>\n", + " <td>-0.4511</td>\n", + " <td>3.8784</td>\n", + " <td>0.2609</td>\n", + " <td>0.9393</td>\n", + " <td>0.5776</td>\n", + " <td>-0.9469</td>\n", + " <td>2.9500</td>\n", + " <td>-0.9261</td>\n", + " <td>2.4218</td>\n", + " <td>...</td>\n", + " <td>5.0440</td>\n", + " <td>0.0862</td>\n", + " <td>0.1431</td>\n", + " <td>-0.7761</td>\n", + " <td>-0.8430</td>\n", + " <td>0.2311</td>\n", + " <td>-0.5913</td>\n", + " <td>1.4958</td>\n", + " <td>2.1736</td>\n", + " <td>-0.5699</td>\n", + " </tr>\n", + " <tr>\n", + " <th>515</th>\n", + " <td>1.9203</td>\n", + " <td>-0.0634</td>\n", + " <td>-0.7142</td>\n", + " <td>-1.3296</td>\n", + " <td>0.3966</td>\n", + " <td>1.0089</td>\n", + " <td>-0.7931</td>\n", + " <td>0.8513</td>\n", + " <td>0.7651</td>\n", + " <td>0.2217</td>\n", + " <td>...</td>\n", + " <td>2.2952</td>\n", + " <td>0.3985</td>\n", + " <td>-0.0072</td>\n", + " <td>0.0683</td>\n", + " <td>-0.8047</td>\n", + " <td>-0.2712</td>\n", + " <td>-0.5864</td>\n", + " <td>-0.2393</td>\n", + " <td>1.8585</td>\n", + " <td>-1.0489</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "<p>516 rows × 2000 columns</p>\n", + "</div>" + ], + "text/plain": [ + " CLASRP_rnaseq NBAS_rnaseq ARL2BP_rnaseq TMEM199_rnaseq TTC37_rnaseq \\\n", + "0 -0.5874 0.8371 0.7587 0.2188 -0.4040 \n", + "1 0.2811 0.2232 0.9000 3.2327 -0.0096 \n", + "2 1.5665 -0.4726 0.1693 0.9845 -0.6740 \n", + "3 0.6169 -0.3266 -0.3082 -0.2220 0.5305 \n", + "4 0.6406 -1.0330 -0.6522 0.1727 -0.7455 \n", + ".. ... ... ... ... ... \n", + "511 0.5640 0.1255 -1.3364 -0.8430 0.4406 \n", + "512 1.2336 0.1902 -1.3500 -0.3472 0.4549 \n", + "513 1.8148 -0.8502 -0.0628 -0.7776 0.6452 \n", + "514 0.0569 -0.4511 3.8784 0.2609 0.9393 \n", + "515 1.9203 -0.0634 -0.7142 -1.3296 0.3966 \n", + "\n", + " GTF2I_rnaseq STYX_rnaseq TSR3_rnaseq SEC61A1_rnaseq TRRAP_rnaseq \\\n", + "0 2.3916 -0.7124 -1.0035 0.7356 -0.0249 \n", + "1 -0.4464 0.5219 0.3927 -0.3513 -0.7917 \n", + "2 -0.3986 -0.2289 -0.2791 -0.0646 -0.4431 \n", + "3 0.5360 0.2785 -1.0873 -1.0712 -0.3184 \n", + "4 -0.6040 0.2553 1.0504 1.0583 -0.2884 \n", + ".. ... ... ... ... ... \n", + "511 -0.9735 -1.4547 -0.1983 -0.5259 -0.2029 \n", + "512 -0.6806 -1.1291 1.0677 1.1586 0.1959 \n", + "513 -0.4622 -1.2732 1.8145 -0.8767 -0.2980 \n", + "514 0.5776 -0.9469 2.9500 -0.9261 2.4218 \n", + "515 1.0089 -0.7931 0.8513 0.7651 0.2217 \n", + "\n", + " ... GET4_rnaseq BRD9_rnaseq NSUN2_rnaseq PYCRL_rnaseq HGH1_rnaseq \\\n", + "0 ... -0.1915 0.3503 -1.1848 -1.4121 -0.2389 \n", + "1 ... 0.7627 -0.6092 0.1291 1.7400 -0.0250 \n", + "2 ... 4.4123 1.4417 -0.5196 -1.3030 -1.1373 \n", + "3 ... 0.7665 -0.3344 0.0695 0.0040 0.2291 \n", + "4 ... 3.3807 0.3364 -0.2792 4.8566 7.9296 \n", + ".. ... ... ... ... ... ... \n", + "511 ... 3.0311 3.4963 2.5079 0.0556 0.5691 \n", + "512 ... 0.5573 -0.7546 0.8104 0.1239 0.0985 \n", + "513 ... 1.4671 2.2343 2.1466 0.7868 0.6893 \n", + "514 ... 5.0440 0.0862 0.1431 -0.7761 -0.8430 \n", + "515 ... 2.2952 0.3985 -0.0072 0.0683 -0.8047 \n", + "\n", + " PRUNE_rnaseq MAF1_rnaseq CCDC127_rnaseq EXOC3_rnaseq PUF60_rnaseq \n", + "0 5.0110 1.4287 -0.3531 -0.8503 1.2995 \n", + "1 -0.1531 0.5344 -0.0012 -0.9606 2.0233 \n", + "2 4.6041 -1.0135 1.3589 2.6994 -0.3068 \n", + "3 3.6034 0.1774 -0.2766 0.5080 0.6178 \n", + "4 1.6951 5.8943 1.3652 -0.8062 9.2417 \n", + ".. ... ... ... ... ... \n", + "511 0.1104 -0.3776 2.6136 3.4259 -0.8442 \n", + "512 2.9026 0.0173 0.3492 2.5703 1.0690 \n", + "513 0.1571 0.9686 3.0870 5.6169 0.5300 \n", + "514 0.2311 -0.5913 1.4958 2.1736 -0.5699 \n", + "515 -0.2712 -0.5864 -0.2393 1.8585 -1.0489 \n", + "\n", + "[516 rows x 2000 columns]" + ] + }, + "execution_count": 45, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "rnaseq" + ] + }, + { + "cell_type": "code", + "execution_count": 51, + "metadata": {}, + "outputs": [ + { + "ename": "ModuleNotFoundError", + "evalue": "No module named 'torch'", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m<ipython-input-51-eb42ca6e4af3>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mimport\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'torch'" + ] + } + ], + "source": [ + "import torch" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Index(['UBE2Q2P2_rnaseq', 'SSX9_rnaseq', 'CXORF67_rnaseq', 'EFCAB8_rnaseq',\n", + " 'SDR16C6P_rnaseq', 'EFCAB12_rnaseq', 'A1BG_rnaseq', 'A1CF_rnaseq',\n", + " 'RBFOX1_rnaseq', 'GGACT_rnaseq',\n", + " ...\n", + " 'ZWINT_rnaseq', 'ZXDA_rnaseq', 'ZXDB_rnaseq', 'ZXDC_rnaseq',\n", + " 'ZYG11A_rnaseq', 'ZYG11B_rnaseq', 'ZYX_rnaseq', 'ZZEF1_rnaseq',\n", + " 'ZZZ3_rnaseq', 'TPTEP1_rnaseq'],\n", + " dtype='object', length=18345)" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "slide_df[slide_df.columns.str.contains('_rnaseq')]" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": {}, + "outputs": [], + "source": [ + "slide_df = pd.read_csv(fname)\n", + "slide_df = slide_df[slide_df.columns[slide_df.columns.str.contains('_rnaseq')]]" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "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>UBE2Q2P2_rnaseq</th>\n", + " <th>SSX9_rnaseq</th>\n", + " <th>CXORF67_rnaseq</th>\n", + " <th>EFCAB8_rnaseq</th>\n", + " <th>SDR16C6P_rnaseq</th>\n", + " <th>EFCAB12_rnaseq</th>\n", + " <th>A1BG_rnaseq</th>\n", + " <th>A1CF_rnaseq</th>\n", + " <th>RBFOX1_rnaseq</th>\n", + " <th>GGACT_rnaseq</th>\n", + " <th>...</th>\n", + " <th>ZWINT_rnaseq</th>\n", + " <th>ZXDA_rnaseq</th>\n", + " <th>ZXDB_rnaseq</th>\n", + " <th>ZXDC_rnaseq</th>\n", + " <th>ZYG11A_rnaseq</th>\n", + " <th>ZYG11B_rnaseq</th>\n", + " <th>ZYX_rnaseq</th>\n", + " <th>ZZEF1_rnaseq</th>\n", + " <th>ZZZ3_rnaseq</th>\n", + " <th>TPTEP1_rnaseq</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>0</th>\n", + " <td>-0.3291</td>\n", + " <td>-0.1379</td>\n", + " <td>-0.1805</td>\n", + " <td>-0.0869</td>\n", + " <td>-0.3317</td>\n", + " <td>-0.1661</td>\n", + " <td>-0.1483</td>\n", + " <td>-0.1371</td>\n", + " <td>-0.2260</td>\n", + " <td>-0.5346</td>\n", + " <td>...</td>\n", + " <td>-0.7082</td>\n", + " <td>0.6149</td>\n", + " <td>0.5725</td>\n", + " <td>0.2889</td>\n", + " <td>-0.5255</td>\n", + " <td>-0.2205</td>\n", + " <td>-0.7847</td>\n", + " <td>-0.2296</td>\n", + " <td>-0.0897</td>\n", + " <td>0.1457</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1</th>\n", + " <td>-0.8531</td>\n", + " <td>-0.1379</td>\n", + " <td>-0.1805</td>\n", + " <td>-0.2629</td>\n", + " <td>-0.3317</td>\n", + " <td>-0.2317</td>\n", + " <td>-0.5528</td>\n", + " <td>-0.1476</td>\n", + " <td>-0.2508</td>\n", + " <td>0.6921</td>\n", + " <td>...</td>\n", + " <td>0.9291</td>\n", + " <td>0.5118</td>\n", + " <td>-0.1673</td>\n", + " <td>-0.8006</td>\n", + " <td>-0.4348</td>\n", + " <td>-1.7113</td>\n", + " <td>0.7466</td>\n", + " <td>-0.1563</td>\n", + " <td>-0.9102</td>\n", + " <td>-0.5005</td>\n", + " </tr>\n", + " <tr>\n", + " <th>2</th>\n", + " <td>-0.7262</td>\n", + " <td>0.3883</td>\n", + " <td>0.4908</td>\n", + " <td>-0.0666</td>\n", + " <td>-0.3317</td>\n", + " <td>-0.3948</td>\n", + " <td>0.0021</td>\n", + " <td>-0.1476</td>\n", + " <td>-0.2508</td>\n", + " <td>-0.0800</td>\n", + " <td>...</td>\n", + " <td>0.2957</td>\n", + " <td>-0.4399</td>\n", + " <td>-0.2751</td>\n", + " <td>-0.4668</td>\n", + " <td>0.1222</td>\n", + " <td>0.3555</td>\n", + " <td>1.4078</td>\n", + " <td>-0.1592</td>\n", + " <td>-0.2276</td>\n", + " <td>-0.3931</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3</th>\n", + " <td>-1.0590</td>\n", + " <td>-0.1379</td>\n", + " <td>-0.1805</td>\n", + " <td>-0.0959</td>\n", + " <td>-0.3317</td>\n", + " <td>-0.3372</td>\n", + " <td>-0.1061</td>\n", + " <td>-0.1476</td>\n", + " <td>-0.2508</td>\n", + " <td>-0.5641</td>\n", + " <td>...</td>\n", + " <td>-0.9962</td>\n", + " <td>1.4844</td>\n", + " <td>0.9748</td>\n", + " <td>0.7481</td>\n", + " <td>-0.7049</td>\n", + " <td>-0.2617</td>\n", + " <td>-0.2934</td>\n", + " <td>1.1243</td>\n", + " <td>0.0823</td>\n", + " <td>0.8831</td>\n", + " </tr>\n", + " <tr>\n", + " <th>4</th>\n", + " <td>-0.7257</td>\n", + " <td>-0.1379</td>\n", + " <td>-0.1805</td>\n", + " <td>-0.1756</td>\n", + " <td>-0.3317</td>\n", + " <td>-0.3778</td>\n", + " <td>0.1119</td>\n", + " <td>-0.1476</td>\n", + " <td>1.2515</td>\n", + " <td>-1.0113</td>\n", + " <td>...</td>\n", + " <td>1.7870</td>\n", + " <td>-0.0462</td>\n", + " <td>1.8418</td>\n", + " <td>-0.9922</td>\n", + " <td>-0.7090</td>\n", + " <td>-1.0285</td>\n", + " <td>0.6567</td>\n", + " <td>-1.0377</td>\n", + " <td>-1.1277</td>\n", + " <td>-0.5026</td>\n", + " </tr>\n", + " <tr>\n", + " <th>...</th>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " </tr>\n", + " <tr>\n", + " <th>511</th>\n", + " <td>0.5308</td>\n", + " <td>-0.1379</td>\n", + " <td>-0.1805</td>\n", + " <td>-0.2629</td>\n", + " <td>-0.3317</td>\n", + " <td>-0.2827</td>\n", + " <td>-0.6045</td>\n", + " <td>-0.1476</td>\n", + " <td>-0.2508</td>\n", + " <td>-0.2014</td>\n", + " <td>...</td>\n", + " <td>-0.5331</td>\n", + " <td>-0.4205</td>\n", + " <td>-0.3773</td>\n", + " <td>0.0551</td>\n", + " <td>-0.5660</td>\n", + " <td>-0.5123</td>\n", + " <td>0.1254</td>\n", + " <td>0.2124</td>\n", + " <td>-0.6375</td>\n", + " <td>1.4712</td>\n", + " </tr>\n", + " <tr>\n", + " <th>512</th>\n", + " <td>-0.5021</td>\n", + " <td>-0.1379</td>\n", + " <td>-0.0120</td>\n", + " <td>1.7408</td>\n", + " <td>-0.3317</td>\n", + " <td>-0.2152</td>\n", + " <td>0.7495</td>\n", + " <td>1.8708</td>\n", + " <td>-0.1178</td>\n", + " <td>-1.3502</td>\n", + " <td>...</td>\n", + " <td>-0.3624</td>\n", + " <td>0.0588</td>\n", + " <td>-0.1157</td>\n", + " <td>1.2831</td>\n", + " <td>-0.0555</td>\n", + " <td>-0.3620</td>\n", + " <td>-0.4242</td>\n", + " <td>1.6937</td>\n", + " <td>-0.4990</td>\n", + " <td>2.2944</td>\n", + " </tr>\n", + " <tr>\n", + " <th>513</th>\n", + " <td>5.2714</td>\n", + " <td>-0.1379</td>\n", + " <td>-0.1805</td>\n", + " <td>0.1753</td>\n", + " <td>-0.3317</td>\n", + " <td>-0.2325</td>\n", + " <td>0.5863</td>\n", + " <td>-0.1476</td>\n", + " <td>-0.0185</td>\n", + " <td>-0.3172</td>\n", + " <td>...</td>\n", + " <td>-0.9598</td>\n", + " <td>-1.5823</td>\n", + " <td>-1.3015</td>\n", + " <td>0.4371</td>\n", + " <td>-0.6739</td>\n", + " <td>-1.4417</td>\n", + " <td>-0.9613</td>\n", + " <td>0.4167</td>\n", + " <td>-1.4631</td>\n", + " <td>-0.5035</td>\n", + " </tr>\n", + " <tr>\n", + " <th>514</th>\n", + " <td>0.6290</td>\n", + " <td>-0.1379</td>\n", + " <td>0.1131</td>\n", + " <td>-0.0667</td>\n", + " <td>1.5316</td>\n", + " <td>-0.3634</td>\n", + " <td>0.3730</td>\n", + " <td>-0.1476</td>\n", + " <td>-0.2361</td>\n", + " <td>-1.7106</td>\n", + " <td>...</td>\n", + " <td>-0.5337</td>\n", + " <td>4.2234</td>\n", + " <td>0.9716</td>\n", + " <td>0.6699</td>\n", + " <td>-0.8134</td>\n", + " <td>-0.2453</td>\n", + " <td>0.2731</td>\n", + " <td>0.6346</td>\n", + " <td>-1.1963</td>\n", + " <td>0.1686</td>\n", + " </tr>\n", + " <tr>\n", + " <th>515</th>\n", + " <td>-0.6140</td>\n", + " <td>-0.1379</td>\n", + " <td>0.0493</td>\n", + " <td>0.3641</td>\n", + " <td>-0.3317</td>\n", + " <td>-0.0722</td>\n", + " <td>-0.1809</td>\n", + " <td>-0.1263</td>\n", + " <td>-0.2508</td>\n", + " <td>0.1358</td>\n", + " <td>...</td>\n", + " <td>-1.0456</td>\n", + " <td>0.5245</td>\n", + " <td>-0.1738</td>\n", + " <td>2.4043</td>\n", + " <td>-0.7251</td>\n", + " <td>-1.0053</td>\n", + " <td>0.7014</td>\n", + " <td>0.7755</td>\n", + " <td>-1.0308</td>\n", + " <td>0.6609</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "<p>516 rows × 18345 columns</p>\n", + "</div>" + ], + "text/plain": [ + " UBE2Q2P2_rnaseq SSX9_rnaseq CXORF67_rnaseq EFCAB8_rnaseq \\\n", + "0 -0.3291 -0.1379 -0.1805 -0.0869 \n", + "1 -0.8531 -0.1379 -0.1805 -0.2629 \n", + "2 -0.7262 0.3883 0.4908 -0.0666 \n", + "3 -1.0590 -0.1379 -0.1805 -0.0959 \n", + "4 -0.7257 -0.1379 -0.1805 -0.1756 \n", + ".. ... ... ... ... \n", + "511 0.5308 -0.1379 -0.1805 -0.2629 \n", + "512 -0.5021 -0.1379 -0.0120 1.7408 \n", + "513 5.2714 -0.1379 -0.1805 0.1753 \n", + "514 0.6290 -0.1379 0.1131 -0.0667 \n", + "515 -0.6140 -0.1379 0.0493 0.3641 \n", + "\n", + " SDR16C6P_rnaseq EFCAB12_rnaseq A1BG_rnaseq A1CF_rnaseq RBFOX1_rnaseq \\\n", + "0 -0.3317 -0.1661 -0.1483 -0.1371 -0.2260 \n", + "1 -0.3317 -0.2317 -0.5528 -0.1476 -0.2508 \n", + "2 -0.3317 -0.3948 0.0021 -0.1476 -0.2508 \n", + "3 -0.3317 -0.3372 -0.1061 -0.1476 -0.2508 \n", + "4 -0.3317 -0.3778 0.1119 -0.1476 1.2515 \n", + ".. ... ... ... ... ... \n", + "511 -0.3317 -0.2827 -0.6045 -0.1476 -0.2508 \n", + "512 -0.3317 -0.2152 0.7495 1.8708 -0.1178 \n", + "513 -0.3317 -0.2325 0.5863 -0.1476 -0.0185 \n", + "514 1.5316 -0.3634 0.3730 -0.1476 -0.2361 \n", + "515 -0.3317 -0.0722 -0.1809 -0.1263 -0.2508 \n", + "\n", + " GGACT_rnaseq ... ZWINT_rnaseq ZXDA_rnaseq ZXDB_rnaseq ZXDC_rnaseq \\\n", + "0 -0.5346 ... -0.7082 0.6149 0.5725 0.2889 \n", + "1 0.6921 ... 0.9291 0.5118 -0.1673 -0.8006 \n", + "2 -0.0800 ... 0.2957 -0.4399 -0.2751 -0.4668 \n", + "3 -0.5641 ... -0.9962 1.4844 0.9748 0.7481 \n", + "4 -1.0113 ... 1.7870 -0.0462 1.8418 -0.9922 \n", + ".. ... ... ... ... ... ... \n", + "511 -0.2014 ... -0.5331 -0.4205 -0.3773 0.0551 \n", + "512 -1.3502 ... -0.3624 0.0588 -0.1157 1.2831 \n", + "513 -0.3172 ... -0.9598 -1.5823 -1.3015 0.4371 \n", + "514 -1.7106 ... -0.5337 4.2234 0.9716 0.6699 \n", + "515 0.1358 ... -1.0456 0.5245 -0.1738 2.4043 \n", + "\n", + " ZYG11A_rnaseq ZYG11B_rnaseq ZYX_rnaseq ZZEF1_rnaseq ZZZ3_rnaseq \\\n", + "0 -0.5255 -0.2205 -0.7847 -0.2296 -0.0897 \n", + "1 -0.4348 -1.7113 0.7466 -0.1563 -0.9102 \n", + "2 0.1222 0.3555 1.4078 -0.1592 -0.2276 \n", + "3 -0.7049 -0.2617 -0.2934 1.1243 0.0823 \n", + "4 -0.7090 -1.0285 0.6567 -1.0377 -1.1277 \n", + ".. ... ... ... ... ... \n", + "511 -0.5660 -0.5123 0.1254 0.2124 -0.6375 \n", + "512 -0.0555 -0.3620 -0.4242 1.6937 -0.4990 \n", + "513 -0.6739 -1.4417 -0.9613 0.4167 -1.4631 \n", + "514 -0.8134 -0.2453 0.2731 0.6346 -1.1963 \n", + "515 -0.7251 -1.0053 0.7014 0.7755 -1.0308 \n", + "\n", + " TPTEP1_rnaseq \n", + "0 0.1457 \n", + "1 -0.5005 \n", + "2 -0.3931 \n", + "3 0.8831 \n", + "4 -0.5026 \n", + ".. ... \n", + "511 1.4712 \n", + "512 2.2944 \n", + "513 -0.5035 \n", + "514 0.1686 \n", + "515 0.6609 \n", + "\n", + "[516 rows x 18345 columns]" + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "slide_df" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "<ipython-input-18-1ae2fdcf544f>:14: DeprecationWarning: The default dtype for empty Series will be 'object' instead of 'float64' in a future version. Specify a dtype explicitly to silence this warning.\n", + " return pd.Series(list(set(s1) & set(s2)))\n", + "/home/mahmoodlab/anaconda3/lib/python3.8/site-packages/IPython/core/interactiveshell.py:3071: DtypeWarning: Columns (2) have mixed types.Specify dtype option on import or set low_memory=False.\n", + " has_raised = await self.run_ast_nodes(code_ast.body, cell_name,\n", + "/home/mahmoodlab/anaconda3/lib/python3.8/site-packages/IPython/core/interactiveshell.py:3071: DtypeWarning: Columns (4) have mixed types.Specify dtype option on import or set low_memory=False.\n", + " has_raised = await self.run_ast_nodes(code_ast.body, cell_name,\n" + ] + } + ], + "source": [ + "### Snippet for creating genomic signatures\n", + "for fname in os.listdir('./'):\n", + " if fname.endswith('.csv.zip'):\n", + " slide_df = pd.read_csv(fname)\n", + " \n", + " signatures = pd.read_csv('./signatures.csv')\n", + " omic_from_signatures = []\n", + " for col in signatures.columns:\n", + " omic = signatures[col].dropna().unique()\n", + " omic_from_signatures.append(omic)\n", + "\n", + " omic_from_signatures = np.concatenate(omic_from_signatures)\n", + "\n", + " def series_intersection(s1, s2):\n", + " return pd.Series(list(set(s1) & set(s2)))\n", + "\n", + " rnaseq_overlap = np.concatenate([omic_from_signatures+mode for mode in ['_rnaseq']])\n", + " rnaseq_overlap = sorted(series_intersection(rnaseq_overlap, slide_df.columns))\n", + " genomics_mut_cnv = list(slide_df.columns[slide_df.columns.str.contains('_mut|_cnv')])\n", + " \n", + " slide_df[list(slide_df.columns[:9]) + rnaseq_overlap + genomics_mut_cnv].to_csv('../dataset_csv_mutsigdb/%s' % fname)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": {}, + "outputs": [], + "source": [ + "omic_from_signatures = []\n", + "for col in signatures.columns:\n", + " omic = signatures[col].dropna().unique()\n", + " omic_from_signatures.append(omic)\n", + "\n", + "omic_from_signatures = np.concatenate(omic_from_signatures)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Tumor Suppressor Genes Embedding Size: 84\n", + "Oncogenes Embedding Size: 314\n", + "Protein Kinases Embedding Size: 498\n", + "Cell Differentiation Markers Embedding Size: 415\n", + "Transcription Factors Embedding Size: 1396\n", + "Cytokines and Growth Factors Embedding Size: 428\n" + ] + } + ], + "source": [ + "\n", + "def series_intersection(s1, s2):\n", + " return pd.Series(list(set(s1) & set(s2)))\n", + "\n", + "sig_names = []\n", + "for col in signatures.columns:\n", + " sig = signatures[col].dropna().unique()\n", + " sig = np.concatenate([sig+mode for mode in ['_mut', '_cnv', '_rnaseq']])\n", + " sig = sorted(series_intersection(sig, genomic_features.columns))\n", + " sig_names.append(sig)\n", + " print('%s Embedding Size: %d' % (col, len(sig)))\n", + "sig_sizes = [len(sig) for sig in sig_names]" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['IFNA10_cnv',\n", + " 'IFNA13_cnv',\n", + " 'IFNA14_cnv',\n", + " 'IFNA16_cnv',\n", + " 'IFNA17_cnv',\n", + " 'IFNA1_cnv',\n", + " 'IFNA21_cnv',\n", + " 'IFNA2_cnv',\n", + " 'IFNA4_cnv',\n", + " 'IFNA5_cnv',\n", + " 'IFNA6_cnv',\n", + " 'IFNA7_cnv',\n", + " 'IFNA8_cnv',\n", + " 'IFNB1_cnv',\n", + " 'IFNE_cnv',\n", + " 'IFNW1_cnv',\n", + " 'PDGFRA_cnv']" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sig" + ] + }, + { + "cell_type": "code", + "execution_count": 434, + "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>NDUFS5_cnv</th>\n", + " <th>MACF1_cnv</th>\n", + " <th>RNA5SP44_cnv</th>\n", + " <th>KIAA0754_cnv</th>\n", + " <th>BMP8A_cnv</th>\n", + " <th>PABPC4_cnv</th>\n", + " <th>SNORA55_cnv</th>\n", + " <th>HEYL_cnv</th>\n", + " <th>HPCAL4_cnv</th>\n", + " <th>NT5C1A_cnv</th>\n", + " <th>...</th>\n", + " <th>ZWINT_rnaseq</th>\n", + " <th>ZXDA_rnaseq</th>\n", + " <th>ZXDB_rnaseq</th>\n", + " <th>ZXDC_rnaseq</th>\n", + " <th>ZYG11A_rnaseq</th>\n", + " <th>ZYG11B_rnaseq</th>\n", + " <th>ZYX_rnaseq</th>\n", + " <th>ZZEF1_rnaseq</th>\n", + " <th>ZZZ3_rnaseq</th>\n", + " <th>TPTEP1_rnaseq</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>0</th>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>...</td>\n", + " <td>-0.8388</td>\n", + " <td>4.1375</td>\n", + " <td>3.9664</td>\n", + " <td>1.8437</td>\n", + " <td>-0.3959</td>\n", + " <td>-0.2561</td>\n", + " <td>-0.2866</td>\n", + " <td>1.8770</td>\n", + " <td>-0.3179</td>\n", + " <td>-0.3633</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1</th>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>...</td>\n", + " <td>-0.1083</td>\n", + " <td>0.3393</td>\n", + " <td>0.2769</td>\n", + " <td>1.7320</td>\n", + " <td>-0.0975</td>\n", + " <td>2.6955</td>\n", + " <td>-0.6741</td>\n", + " <td>1.0323</td>\n", + " <td>1.2766</td>\n", + " <td>-0.3982</td>\n", + " </tr>\n", + " <tr>\n", + " <th>2</th>\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>0</td>\n", + " <td>...</td>\n", + " <td>-0.4155</td>\n", + " <td>1.6846</td>\n", + " <td>0.7711</td>\n", + " <td>-0.3061</td>\n", + " <td>-0.5016</td>\n", + " <td>2.8548</td>\n", + " <td>-0.6171</td>\n", + " <td>-0.8608</td>\n", + " <td>-0.0486</td>\n", + " <td>-0.3962</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3</th>\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>0</td>\n", + " <td>...</td>\n", + " <td>-0.8143</td>\n", + " <td>0.8344</td>\n", + " <td>1.5075</td>\n", + " <td>3.6068</td>\n", + " <td>-0.5004</td>\n", + " <td>-0.0747</td>\n", + " <td>-0.2185</td>\n", + " <td>-0.4379</td>\n", + " <td>1.6913</td>\n", + " <td>1.7748</td>\n", + " </tr>\n", + " <tr>\n", + " <th>4</th>\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>0</td>\n", + " <td>...</td>\n", + " <td>0.0983</td>\n", + " <td>-0.7908</td>\n", + " <td>-0.0053</td>\n", + " <td>-0.0643</td>\n", + " <td>-0.3706</td>\n", + " <td>0.3870</td>\n", + " <td>-0.5589</td>\n", + " <td>-0.5979</td>\n", + " <td>0.0047</td>\n", + " <td>-0.3548</td>\n", + " </tr>\n", + " <tr>\n", + " <th>...</th>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " </tr>\n", + " <tr>\n", + " <th>368</th>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>...</td>\n", + " <td>-0.0291</td>\n", + " <td>-0.1058</td>\n", + " <td>-0.6721</td>\n", + " <td>0.2802</td>\n", + " <td>1.9504</td>\n", + " <td>-0.8784</td>\n", + " <td>0.9506</td>\n", + " <td>0.0607</td>\n", + " <td>1.1883</td>\n", + " <td>-0.3521</td>\n", + " </tr>\n", + " <tr>\n", + " <th>369</th>\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>0</td>\n", + " <td>...</td>\n", + " <td>0.0497</td>\n", + " <td>0.3673</td>\n", + " <td>-0.2208</td>\n", + " <td>0.3034</td>\n", + " <td>3.2580</td>\n", + " <td>-0.2089</td>\n", + " <td>1.6053</td>\n", + " <td>-0.8746</td>\n", + " <td>-0.4491</td>\n", + " <td>-0.3450</td>\n", + " </tr>\n", + " <tr>\n", + " <th>370</th>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>...</td>\n", + " <td>0.3822</td>\n", + " <td>-0.7003</td>\n", + " <td>-0.7661</td>\n", + " <td>-1.7035</td>\n", + " <td>-0.5423</td>\n", + " <td>-0.3488</td>\n", + " <td>1.3713</td>\n", + " <td>-0.4365</td>\n", + " <td>2.3456</td>\n", + " <td>-0.3866</td>\n", + " </tr>\n", + " <tr>\n", + " <th>371</th>\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>0</td>\n", + " <td>...</td>\n", + " <td>-0.6853</td>\n", + " <td>-1.0240</td>\n", + " <td>-1.2890</td>\n", + " <td>-1.5666</td>\n", + " <td>-0.1270</td>\n", + " <td>-1.4662</td>\n", + " <td>0.3981</td>\n", + " <td>-0.5976</td>\n", + " <td>-1.3822</td>\n", + " <td>-0.4157</td>\n", + " </tr>\n", + " <tr>\n", + " <th>372</th>\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>0</td>\n", + " <td>...</td>\n", + " <td>0.0517</td>\n", + " <td>-0.3570</td>\n", + " <td>-0.4843</td>\n", + " <td>-0.3792</td>\n", + " <td>-0.1964</td>\n", + " <td>0.4200</td>\n", + " <td>3.2547</td>\n", + " <td>-0.1232</td>\n", + " <td>3.4519</td>\n", + " <td>-0.1962</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "<p>373 rows × 20395 columns</p>\n", + "</div>" + ], + "text/plain": [ + " NDUFS5_cnv MACF1_cnv RNA5SP44_cnv KIAA0754_cnv BMP8A_cnv PABPC4_cnv \\\n", + "0 -1 -1 -1 -1 -1 -1 \n", + "1 2 2 2 2 2 2 \n", + "2 0 0 0 0 0 0 \n", + "3 0 0 0 0 0 0 \n", + "4 0 0 0 0 0 0 \n", + ".. ... ... ... ... ... ... \n", + "368 2 2 2 2 2 2 \n", + "369 0 0 0 0 0 0 \n", + "370 1 1 1 1 1 1 \n", + "371 0 0 0 0 0 0 \n", + "372 0 0 0 0 0 0 \n", + "\n", + " SNORA55_cnv HEYL_cnv HPCAL4_cnv NT5C1A_cnv ... ZWINT_rnaseq \\\n", + "0 -1 -1 -1 -1 ... -0.8388 \n", + "1 2 2 2 2 ... -0.1083 \n", + "2 0 0 0 0 ... -0.4155 \n", + "3 0 0 0 0 ... -0.8143 \n", + "4 0 0 0 0 ... 0.0983 \n", + ".. ... ... ... ... ... ... \n", + "368 2 2 2 2 ... -0.0291 \n", + "369 0 0 0 0 ... 0.0497 \n", + "370 1 1 1 1 ... 0.3822 \n", + "371 0 0 0 0 ... -0.6853 \n", + "372 0 0 0 0 ... 0.0517 \n", + "\n", + " ZXDA_rnaseq ZXDB_rnaseq ZXDC_rnaseq ZYG11A_rnaseq ZYG11B_rnaseq \\\n", + "0 4.1375 3.9664 1.8437 -0.3959 -0.2561 \n", + "1 0.3393 0.2769 1.7320 -0.0975 2.6955 \n", + "2 1.6846 0.7711 -0.3061 -0.5016 2.8548 \n", + "3 0.8344 1.5075 3.6068 -0.5004 -0.0747 \n", + "4 -0.7908 -0.0053 -0.0643 -0.3706 0.3870 \n", + ".. ... ... ... ... ... \n", + "368 -0.1058 -0.6721 0.2802 1.9504 -0.8784 \n", + "369 0.3673 -0.2208 0.3034 3.2580 -0.2089 \n", + "370 -0.7003 -0.7661 -1.7035 -0.5423 -0.3488 \n", + "371 -1.0240 -1.2890 -1.5666 -0.1270 -1.4662 \n", + "372 -0.3570 -0.4843 -0.3792 -0.1964 0.4200 \n", + "\n", + " ZYX_rnaseq ZZEF1_rnaseq ZZZ3_rnaseq TPTEP1_rnaseq \n", + "0 -0.2866 1.8770 -0.3179 -0.3633 \n", + "1 -0.6741 1.0323 1.2766 -0.3982 \n", + "2 -0.6171 -0.8608 -0.0486 -0.3962 \n", + "3 -0.2185 -0.4379 1.6913 1.7748 \n", + "4 -0.5589 -0.5979 0.0047 -0.3548 \n", + ".. ... ... ... ... \n", + "368 0.9506 0.0607 1.1883 -0.3521 \n", + "369 1.6053 -0.8746 -0.4491 -0.3450 \n", + "370 1.3713 -0.4365 2.3456 -0.3866 \n", + "371 0.3981 -0.5976 -1.3822 -0.4157 \n", + "372 3.2547 -0.1232 3.4519 -0.1962 \n", + "\n", + "[373 rows x 20395 columns]" + ] + }, + "execution_count": 434, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "genomic_features" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "import torch\n", + "import torch.nn as nn\n", + "import torch.nn.functional as F\n", + "import pdb\n", + "import numpy as np\n", + "\n", + "class MIL_Sum_FC_surv(nn.Module):\n", + " def __init__(self, size_arg = \"small\", dropout=0.25, n_classes=4):\n", + " super(MIL_Sum_FC_surv, self).__init__()\n", + "\n", + " self.size_dict = {\"small\": [1024, 512, 256], \"big\": [1024, 512, 384]}\n", + " size = self.size_dict[size_arg]\n", + " self.phi = nn.Sequential(*[nn.Linear(size[0], size[1]), nn.ReLU(), nn.Dropout(dropout)])\n", + " self.rho = nn.Sequential(*[nn.Linear(size[1], size[2]), nn.ReLU(), nn.Dropout(dropout)])\n", + " self.classifier = nn.Linear(size[2], n_classes)\n", + "\n", + " def relocate(self):\n", + " device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n", + " if torch.cuda.device_count() >= 1:\n", + " device_ids = list(range(torch.cuda.device_count()))\n", + " self.phi = nn.DataParallel(self.phi, device_ids=device_ids).to('cuda:0')\n", + "\n", + " self.rho = self.rho.to(device)\n", + " self.classifier = self.classifier.to(device)\n", + "\n", + " def forward(self, **kwargs):\n", + " h = kwargs['x_path']\n", + "\n", + " h = self.phi(h).sum(axis=0)\n", + " h = self.rho(h)\n", + " logits = self.classifier(h).unsqueeze(0)\n", + " Y_hat = torch.topk(logits, 1, dim = 1)[1]\n", + " hazards = torch.sigmoid(logits)\n", + " S = torch.cumprod(1 - hazards, dim=1)\n", + " \n", + " return hazards, S, Y_hat, None, None\n", + "\n", + "from os.path import join\n", + "from collections import OrderedDict\n", + "\n", + "import torch\n", + "import torch.nn as nn\n", + "import torch.nn.functional as F\n", + "import pdb\n", + "import numpy as np\n", + "\n", + "\"\"\"\n", + "A Modified Implementation of Deep Attention MIL\n", + "\"\"\"\n", + "\n", + "\n", + "\"\"\"\n", + "Attention Network without Gating (2 fc layers)\n", + "args:\n", + " L: input feature dimension\n", + " D: hidden layer dimension\n", + " dropout: whether to use dropout (p = 0.25)\n", + " n_classes: number of classes (experimental usage for multiclass MIL)\n", + "\"\"\"\n", + "class Attn_Net(nn.Module):\n", + "\n", + " def __init__(self, L = 1024, D = 256, dropout = False, n_classes = 1):\n", + " super(Attn_Net, self).__init__()\n", + " self.module = [\n", + " nn.Linear(L, D),\n", + " nn.Tanh()]\n", + "\n", + " if dropout:\n", + " self.module.append(nn.Dropout(0.25))\n", + "\n", + " self.module.append(nn.Linear(D, n_classes))\n", + " \n", + " self.module = nn.Sequential(*self.module)\n", + " \n", + " def forward(self, x):\n", + " return self.module(x), x # N x n_classes\n", + "\n", + "\"\"\"\n", + "Attention Network with Sigmoid Gating (3 fc layers)\n", + "args:\n", + " L: input feature dimension\n", + " D: hidden layer dimension\n", + " dropout: whether to use dropout (p = 0.25)\n", + " n_classes: number of classes (experimental usage for multiclass MIL)\n", + "\"\"\"\n", + "class Attn_Net_Gated(nn.Module):\n", + "\n", + " def __init__(self, L = 1024, D = 256, dropout = False, n_classes = 1):\n", + " super(Attn_Net_Gated, self).__init__()\n", + " self.attention_a = [\n", + " nn.Linear(L, D),\n", + " nn.Tanh()]\n", + " \n", + " self.attention_b = [nn.Linear(L, D),\n", + " nn.Sigmoid()]\n", + " if dropout:\n", + " self.attention_a.append(nn.Dropout(0.25))\n", + " self.attention_b.append(nn.Dropout(0.25))\n", + "\n", + " self.attention_a = nn.Sequential(*self.attention_a)\n", + " self.attention_b = nn.Sequential(*self.attention_b)\n", + " \n", + " self.attention_c = nn.Linear(D, n_classes)\n", + "\n", + " def forward(self, x):\n", + " a = self.attention_a(x)\n", + " b = self.attention_b(x)\n", + " A = a.mul(b)\n", + " A = self.attention_c(A) # N x n_classes\n", + " return A, x\n", + " \n", + "class MIL_Cluster_FC_surv(nn.Module):\n", + " def __init__(self, num_clusters=10, size_arg = \"small\", dropout=0.25, n_classes=4):\n", + " super(MIL_Cluster_FC_surv, self).__init__()\n", + " self.size_dict = {\"small\": [1024, 512, 256], \"big\": [1024, 512, 384]}\n", + " self.num_clusters = num_clusters\n", + " \n", + " ### Phenotype Learning\n", + " size = self.size_dict[size_arg]\n", + " phis = []\n", + " for phenotype_i in range(num_clusters):\n", + " phi = [nn.Linear(size[0], size[1]), nn.ReLU(), nn.Dropout(dropout),\n", + " nn.Linear(size[1], size[1]), nn.ReLU(), nn.Dropout(dropout)]\n", + " phis.append(nn.Sequential(*phi))\n", + " self.phis = nn.ModuleList(phis)\n", + " self.pool1d = nn.AdaptiveAvgPool1d(1)\n", + " \n", + " \n", + " ### WSI Attention MIL Construction\n", + " fc = [nn.Linear(size[1], size[1]), nn.ReLU()]\n", + " fc.append(nn.Dropout(0.25))\n", + " attention_net = Attn_Net_Gated(L=size[1], D=size[2], dropout=dropout, n_classes=1)\n", + " fc.append(attention_net)\n", + " self.attention_net = nn.Sequential(*fc)\n", + "\n", + " \n", + " self.rho = nn.Sequential(*[nn.Linear(size[1], size[2]), nn.ReLU(), nn.Dropout(dropout)])\n", + " self.classifier = nn.Linear(size[2], n_classes)\n", + "\n", + " def relocate(self):\n", + " device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n", + " if torch.cuda.device_count() >= 1:\n", + " device_ids = list(range(torch.cuda.device_count()))\n", + " self.phis = nn.DataParallel(self.phi, device_ids=device_ids).to('cuda:0')\n", + "\n", + " self.rho = self.rho.to(device)\n", + " self.classifier = self.classifier.to(device)\n", + "\n", + " def forward(self, **kwargs):\n", + " x_path = kwargs['x_path']\n", + " ### Phenotyping\n", + " h_phenotypes = []\n", + " from sklearn.cluster import KMeans\n", + " kmeans = KMeans(n_clusters=self.num_clusters, random_state=2021).fit(X)\n", + " #cluster_ids_x, cluster_centers = kmeans(X=x_path, num_clusters=self.num_clusters, distance='euclidean', device=torch.device('cpu'))\n", + " cluster_ids_x = KMeans(n_clusters=10, random_state=2021, max_iter=20).fit_predict(x_path)\n", + " for i in range(self.num_clusters):\n", + " h_phenotypes_i = self.phis[i](x_path[cluster_ids_x==i])\n", + " h_phenotypes.append(self.pool1d(h_phenotypes_i.T.unsqueeze(0)).squeeze(2))\n", + " h_phenotypes = torch.stack(h_phenotypes, dim=1).squeeze(0)\n", + "\n", + "\n", + " ### Attention MIL\n", + " A, h = self.attention_net(h_phenotypes) \n", + " A = torch.transpose(A, 1, 0)\n", + " if 'attention_only' in kwargs.keys():\n", + " if kwargs['attention_only']:\n", + " return A\n", + " A_raw = A \n", + " A = F.softmax(A, dim=1) \n", + " h = torch.mm(A, h_phenotypes)\n", + "\n", + " \n", + " h = self.rho(h)\n", + " logits = self.classifier(h).unsqueeze(0)\n", + " Y_hat = torch.topk(logits, 1, dim = 1)[1]\n", + " hazards = torch.sigmoid(logits)\n", + " S = torch.cumprod(1 - hazards, dim=1)\n", + " \n", + " return hazards, S, Y_hat, None, None" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [], + "source": [ + "x_path = torch.randint(10, size=(500, 1024)).type(torch.cuda.FloatTensor)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [], + "source": [ + "from sklearn.cluster import KMeans\n", + "kmeans = KMeans(n_clusters=10, random_state=2021, max_iter=20).fit_predict(x_path.cpu())" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([5, 5, 3, 5, 8, 4, 8, 7, 5, 4, 9, 1, 9, 1, 6, 1, 1, 0, 5, 0, 4, 3,\n", + " 0, 6, 3, 1, 0, 7, 9, 8, 0, 5, 5, 3, 0, 1, 5, 1, 0, 6, 6, 4, 1, 5,\n", + " 3, 0, 1, 0, 8, 5, 1, 8, 1, 0, 5, 0, 2, 5, 6, 5, 0, 0, 5, 1, 2, 7,\n", + " 4, 6, 5, 3, 0, 7, 9, 1, 3, 4, 4, 5, 7, 9, 9, 5, 0, 1, 9, 1, 2, 0,\n", + " 6, 3, 1, 1, 2, 4, 0, 5, 1, 1, 1, 0, 0, 9, 8, 1, 5, 5, 0, 9, 2, 3,\n", + " 7, 0, 1, 6, 7, 5, 3, 5, 0, 1, 6, 1, 6, 2, 8, 7, 6, 1, 6, 2, 5, 0,\n", + " 1, 6, 0, 9, 2, 1, 0, 1, 7, 7, 6, 1, 6, 0, 3, 4, 1, 3, 2, 4, 4, 5,\n", + " 4, 1, 1, 9, 6, 0, 3, 6, 4, 8, 7, 9, 6, 5, 5, 9, 0, 6, 0, 1, 9, 2,\n", + " 3, 5, 1, 9, 6, 1, 0, 6, 6, 0, 0, 6, 7, 1, 6, 1, 1, 1, 4, 0, 2, 1,\n", + " 9, 5, 7, 5, 9, 0, 1, 0, 6, 2, 2, 1, 1, 5, 3, 5, 3, 6, 5, 6, 9, 5,\n", + " 2, 2, 2, 6, 0, 0, 0, 5, 2, 6, 6, 0, 2, 5, 1, 9, 2, 4, 4, 0, 4, 7,\n", + " 4, 1, 1, 3, 6, 0, 1, 2, 4, 0, 8, 1, 8, 5, 5, 7, 4, 1, 6, 1, 0, 8,\n", + " 6, 1, 1, 4, 8, 7, 5, 2, 3, 0, 2, 9, 5, 6, 4, 3, 6, 5, 5, 4, 6, 6,\n", + " 0, 1, 5, 1, 1, 1, 1, 9, 5, 7, 3, 0, 2, 4, 0, 5, 4, 0, 5, 0, 6, 0,\n", + " 3, 1, 4, 6, 3, 7, 1, 6, 7, 0, 1, 4, 6, 1, 6, 0, 6, 0, 5, 9, 1, 1,\n", + " 3, 1, 5, 6, 1, 6, 6, 8, 2, 0, 7, 9, 9, 6, 0, 6, 2, 6, 8, 0, 8, 5,\n", + " 1, 3, 1, 9, 2, 3, 5, 8, 2, 5, 6, 6, 5, 2, 9, 0, 1, 8, 5, 9, 5, 1,\n", + " 0, 1, 0, 8, 6, 1, 7, 2, 8, 3, 1, 6, 2, 2, 1, 6, 0, 2, 6, 1, 1, 4,\n", + " 5, 6, 4, 0, 5, 0, 9, 0, 4, 8, 0, 7, 6, 5, 5, 0, 4, 1, 1, 2, 2, 0,\n", + " 0, 6, 4, 0, 7, 7, 2, 3, 1, 4, 7, 9, 4, 7, 2, 4, 5, 6, 4, 5, 7, 9,\n", + " 8, 0, 6, 2, 0, 6, 6, 3, 5, 4, 4, 0, 1, 0, 5, 3, 1, 6, 0, 7, 4, 1,\n", + " 6, 3, 6, 0, 4, 1, 5, 7, 3, 1, 4, 8, 0, 7, 0, 6, 1, 1, 0, 1, 5, 1,\n", + " 2, 3, 2, 3, 8, 8, 4, 6, 5, 6, 1, 0, 7, 6, 4, 4], dtype=int32)" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "kmeans" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(tensor([[0.9992, 0.0000, 0.0000, 1.0000]], grad_fn=<SigmoidBackward>),\n", + " tensor([[0.0008, 0.0008, 0.0008, 0.0000]], grad_fn=<CumprodBackward>),\n", + " tensor([[3]]),\n", + " None,\n", + " None)" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "x_path = torch.randint(10, size=(500, 1024)).type(torch.FloatTensor)\n", + "model = MIL_Sum_FC_surv()\n", + "model.forward(x_path=x_path)" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(tensor([[4.2595e-07, 1.0000e+00, 0.0000e+00, 7.2488e-12]],\n", + " grad_fn=<SigmoidBackward>),\n", + " tensor([[1.0000, 0.0000, 0.0000, 0.0000]], grad_fn=<CumprodBackward>),\n", + " tensor([[1]]),\n", + " None,\n", + " None)" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "x_path = torch.randint(10, size=(500, 1024)).type(torch.FloatTensor)\n", + "self = MIL_Cluster_FC_surv()\n", + "model.forward(x_path=x_path)" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [], + "source": [ + "import os\n", + "fname = os.path.join('/media/ssd1/pan-cancer/tcga_gbm_20x_features/h5_files/TCGA-02-0001-01Z-00-DX1.83fce43e-42ac-4dcd-b156-2908e75f2e47.h5')" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [], + "source": [ + "import h5py\n", + "h5 = h5py.File(fname, \"r\")\n", + "coords = np.array(h5['coords'])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "fm" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([43121, 29428])" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "np.array(h5['coords'])[0]" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([43121, 29940])" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "np.array(h5['coords'])[1]" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "512" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "np.array(h5['coords'])[1][1] - np.array(h5['coords'])[0][1]" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "512" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "np.array(h5['coords'])[2][1] - np.array(h5['coords'])[1][1]" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": {}, + "outputs": [], + "source": [ + "import nmslib\n", + "class Hnsw:\n", + "\n", + " def __init__(self, space='cosinesimil', index_params=None,\n", + " query_params=None, print_progress=True):\n", + " self.space = space\n", + " self.index_params = index_params\n", + " self.query_params = query_params\n", + " self.print_progress = print_progress\n", + "\n", + " def fit(self, X):\n", + " index_params = self.index_params\n", + " if index_params is None:\n", + " index_params = {'M': 16, 'post': 0, 'efConstruction': 400}\n", + "\n", + " query_params = self.query_params\n", + " if query_params is None:\n", + " query_params = {'ef': 90}\n", + "\n", + " # this is the actual nmslib part, hopefully the syntax should\n", + " # be pretty readable, the documentation also has a more verbiage\n", + " # introduction: https://nmslib.github.io/nmslib/quickstart.html\n", + " index = nmslib.init(space=self.space, method='hnsw')\n", + " index.addDataPointBatch(X)\n", + " index.createIndex(index_params, print_progress=self.print_progress)\n", + " index.setQueryTimeParams(query_params)\n", + "\n", + " self.index_ = index\n", + " self.index_params_ = index_params\n", + " self.query_params_ = query_params\n", + " return self\n", + "\n", + " def query(self, vector, topn):\n", + " # the knnQuery returns indices and corresponding distance\n", + " # we will throw the distance away for now\n", + " indices, _ = self.index_.knnQuery(vector, k=topn)\n", + " return indices" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "x" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([85, 87, 88, 73, 75, 76, 63, 29], dtype=int32)" + ] + }, + "execution_count": 54, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "model = Hnsw(space='l2')\n", + "model.fit(coords)\n", + "model.query(coords, topn=8)" + ] + }, + { + "cell_type": "code", + "execution_count": 59, + "metadata": {}, + "outputs": [], + "source": [ + "import networkx as nx\n", + "G = nx.Graph()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([43121, 29428])" + ] + }, + "execution_count": 56, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "for" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "130" + ] + }, + "execution_count": 52, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "temp[3]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "model" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([ 7440, 13280])" + ] + }, + "execution_count": 29, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "coords[100]" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": {}, + "outputs": [], + "source": [ + "indices = model.query(coords[100], topn =10)" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[ 7440, 13280],\n", + " [ 7440, 13792],\n", + " [ 7952, 13280],\n", + " [ 6928, 13792],\n", + " [ 7952, 12768],\n", + " [ 7952, 13792],\n", + " [ 7440, 14304],\n", + " [ 8464, 13280],\n", + " [ 6928, 14304],\n", + " [ 8464, 13792]])" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "coords[indices]" + ] + }, + { + "cell_type": "code", + "execution_count": 84, + "metadata": {}, + "outputs": [], + "source": [ + "def do_KmeansPCA(X=None, y=None, scaler=None, n_clusters=4, n_components=5):\n", + " import pandas as pd\n", + " import seaborn as sns\n", + " from sklearn.datasets import make_blobs\n", + " from sklearn import decomposition\n", + " from sklearn.decomposition import PCA, TruncatedSVD\n", + " from sklearn.preprocessing import StandardScaler, Normalizer\n", + " from sklearn.pipeline import make_pipeline\n", + " from sklearn.cluster import KMeans\n", + " ### Initialize Scaler\n", + " if scaler is None: \n", + " scaler = StandardScaler()\n", + " ### Get Random Data\n", + " X, y = make_blobs(n_features=10, n_samples=100, centers=4, random_state=4, cluster_std=7)\n", + " ### Scale Data\n", + " X = scaler.fit_transform(X)\n", + " ### Perform K-Means Clustering\n", + " cls = KMeans(n_clusters=n_clusters, init='k-means++', n_jobs=-1, n_init=1)\n", + " y_pred = cls.fit_predict(X)\n", + " ### Perform PCA\n", + " pca = PCA(n_components=n_components)\n", + " pc = pca.fit_transform(X)\n", + " ### Plot Results\n", + " columns = ['PC%d'%c for c in range(1, n_components+1)]\n", + " pc_df = pd.DataFrame(data=pc, columns=columns)\n", + " pc_df['y_pred'] = y_pred\n", + " pc_df['y'] = y\n", + " df = pd.DataFrame({'Variance Explained':pca.explained_variance_ratio_, 'Principal Components': columns})\n", + " sns.barplot(x='Principal Components',y=\"Variance Explained\", data=df, color=\"c\")\n", + " sns.lmplot( x=\"PC1\", y=\"PC2\", data=pc_df, fit_reg=False, \n", + " hue='y', legend=True, scatter_kws={\"s\": 80})\n", + " sns.lmplot( x=\"PC1\", y=\"PC2\", data=pc_df, fit_reg=False, \n", + " hue='y', legend=True, scatter_kws={\"s\": 80})" + ] + }, + { + "cell_type": "code", + "execution_count": 85, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "<Figure size 432x288 with 1 Axes>" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "<Figure size 402.375x360 with 1 Axes>" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "<Figure size 402.375x360 with 1 Axes>" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "do_KmeansPCA()" + ] + }, + { + "cell_type": "code", + "execution_count": 76, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(tensor([[1.0000, 0.0000, 1.0000, 0.9998]], grad_fn=<SigmoidBackward>),\n", + " tensor([[0., 0., 0., 0.]], grad_fn=<CumprodBackward>),\n", + " tensor([[2]]),\n", + " None,\n", + " None)" + ] + }, + "execution_count": 76, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "model.forward(x_path=x_path)" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "metadata": {}, + "outputs": [ + { + "ename": "SyntaxError", + "evalue": "invalid syntax (<ipython-input-69-c543913fa78f>, line 1)", + "output_type": "error", + "traceback": [ + "\u001b[0;36m File \u001b[0;32m\"<ipython-input-69-c543913fa78f>\"\u001b[0;36m, line \u001b[0;32m1\u001b[0m\n\u001b[0;31m import ..models\u001b[0m\n\u001b[0m ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m invalid syntax\n" + ] + } + ], + "source": [ + "import ..models" + ] + }, + { + "cell_type": "code", + "execution_count": 63, + "metadata": {}, + "outputs": [], + "source": [ + "x_path = torch.randint(10, size=(500, 1024)).type(torch.FloatTensor)" + ] + }, + { + "cell_type": "code", + "execution_count": 65, + "metadata": {}, + "outputs": [ + { + "ename": "NameError", + "evalue": "name 'MultiheadAttention' is not defined", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m<ipython-input-65-f85a99af33ee>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mself\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mMM_CoAttn_Transformer_Surv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0momic_sizes\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msig_sizes\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[0;32m<ipython-input-62-9e5f322e30a0>\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, omic_sizes, n_classes, model_size_wsi, model_size_omic, dropout)\u001b[0m\n\u001b[1;32m 28\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 29\u001b[0m \u001b[0;31m### Multihead Attention\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 30\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcoattn\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mMultiheadAttention\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0membed_dim\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m256\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnum_heads\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 31\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 32\u001b[0m \u001b[0;31m### Transformer\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mNameError\u001b[0m: name 'MultiheadAttention' is not defined" + ] + } + ], + "source": [ + "self = MM_CoAttn_Transformer_Surv(omic_sizes=sig_sizes)" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": {}, + "outputs": [ + { + "ename": "NameError", + "evalue": "name 'sig_size' is not defined", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m<ipython-input-52-097a03ed0c40>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mself\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mMM_CoAttn_Surv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msig_sizes\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msig_sizes\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mx_path\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrandint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m500\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1024\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mFloatTensor\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0msig_feats\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrandint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msize\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mFloatTensor\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0msize\u001b[0m \u001b[0;32min\u001b[0m \u001b[0msig_sizes\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0mx_path\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mattention_net\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx_path\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0munsqueeze\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m<ipython-input-43-4469ba9e1eea>\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, sig_sizes, n_classes, model_size_wsi, model_size_omic, dropout)\u001b[0m\n\u001b[1;32m 19\u001b[0m \u001b[0mhidden\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize_dict_omic\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mmodel_size_omic\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 20\u001b[0m \u001b[0msig_networks\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 21\u001b[0;31m \u001b[0;32mfor\u001b[0m \u001b[0minput_dim\u001b[0m \u001b[0;32min\u001b[0m \u001b[0msig_size\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 22\u001b[0m \u001b[0mfc_omic\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mSNN_Block\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdim1\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minput_dim\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdim2\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mhidden\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 23\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_\u001b[0m \u001b[0;32min\u001b[0m \u001b[0menumerate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mhidden\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mNameError\u001b[0m: name 'sig_size' is not defined" + ] + } + ], + "source": [ + "self = MM_CoAttn_Surv(sig_sizes=sig_sizes)\n", + "x_path = torch.randint(10, size=(500, 1024)).type(torch.FloatTensor)\n", + "sig_feats = [torch.randint(10, size=(size,)).type(torch.FloatTensor) for size in sig_sizes]\n", + "\n", + "x_path = self.attention_net(x_path).unsqueeze(1)\n", + "x_omic = torch.stack([self.sig_networks[idx].forward(sig_feat) for idx, sig_feat in enumerate(sig_feats)]).unsqueeze(1)\n", + "\n", + "out, attention_weights = self.coattn(x_omic, x_path, x_path)\n", + "out = self.transformer(out)\n", + "out = self.conv(out.squeeze(1).T.unsqueeze(0))\n", + "#out = self.classifier(out.squeeze(0).squeeze(1))" + ] + }, + { + "cell_type": "code", + "execution_count": 471, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "torch.Size([1, 256, 1])" + ] + }, + "execution_count": 471, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "out.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 472, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "tensor([[[ 0.5998, 1.9873, -1.1435, ..., -0.0048, 0.2963, 1.1112]],\n", + "\n", + " [[-0.4201, -0.1456, 0.2057, ..., -0.2175, 0.4188, 0.4702]],\n", + "\n", + " [[ 1.0294, 3.1634, 0.4595, ..., 1.2059, 0.5845, 1.4114]],\n", + "\n", + " [[-1.1435, -1.1435, -1.1435, ..., 0.1951, -0.4378, 0.2051]],\n", + "\n", + " [[ 0.9948, 1.1596, 2.1419, ..., -0.1225, 1.3597, -0.3037]],\n", + "\n", + " [[ 0.4019, -1.1435, -0.1522, ..., -0.2058, 0.0351, -1.1435]]],\n", + " grad_fn=<UnsqueezeBackward0>)" + ] + }, + "execution_count": 472, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "x_omic" + ] + }, + { + "cell_type": "code", + "execution_count": 474, + "metadata": {}, + "outputs": [], + "source": [ + "self = MM_CoAttn_Surv(sig_sizes=sig_sizes)\n", + "x_path = torch.randint(10, size=(500, 1024)).type(torch.FloatTensor)\n", + "sig_feats = [torch.randint(10, size=(size,)).type(torch.FloatTensor) for size in sig_sizes]\n", + "\n", + "x_path = self.attention_net(x_path).unsqueeze(1)\n", + "x_omic = torch.stack([self.sig_networks[idx].forward(sig_feat) for idx, sig_feat in enumerate(sig_feats)]).unsqueeze(1)\n", + "out, attention_weights = self.coattn(x_omic, x_path, x_path)\n", + "\n", + "out = self.transformer(out)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 491, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "torch.Size([1536])" + ] + }, + "execution_count": 491, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "torch.cat([self.sig_networks[idx].forward(sig_feat) for idx, sig_feat in enumerate(sig_feats)]).shape" + ] + }, + { + "cell_type": "code", + "execution_count": 484, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "torch.Size([6, 1, 512])" + ] + }, + "execution_count": 484, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "torch.cat([out, out], axis=2).shape" + ] + }, + { + "cell_type": "code", + "execution_count": 455, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "torch.Size([6, 1, 256])" + ] + }, + "execution_count": 455, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "out.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 452, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "torch.Size([6, 1, 256])" + ] + }, + "execution_count": 452, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "out.shape" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 423, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "torch.Size([1, 8, 6, 500])" + ] + }, + "execution_count": 423, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "attention_weights.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 415, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "tensor([[[0.0018, 0.0020, 0.0012, ..., 0.0016, 0.0025, 0.0031],\n", + " [0.0026, 0.0015, 0.0016, ..., 0.0021, 0.0021, 0.0016],\n", + " [0.0019, 0.0014, 0.0011, ..., 0.0020, 0.0013, 0.0025],\n", + " [0.0016, 0.0013, 0.0023, ..., 0.0009, 0.0015, 0.0027],\n", + " [0.0015, 0.0013, 0.0023, ..., 0.0026, 0.0019, 0.0026],\n", + " [0.0013, 0.0019, 0.0025, ..., 0.0022, 0.0020, 0.0021]]],\n", + " grad_fn=<DivBackward0>)" + ] + }, + "execution_count": 415, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "attention_weights_0" + ] + }, + { + "cell_type": "code", + "execution_count": 416, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "tensor([[[0.0018, 0.0020, 0.0012, ..., 0.0016, 0.0025, 0.0031],\n", + " [0.0026, 0.0015, 0.0016, ..., 0.0021, 0.0021, 0.0016],\n", + " [0.0019, 0.0014, 0.0011, ..., 0.0020, 0.0013, 0.0025],\n", + " [0.0016, 0.0013, 0.0023, ..., 0.0009, 0.0015, 0.0027],\n", + " [0.0015, 0.0013, 0.0023, ..., 0.0026, 0.0019, 0.0026],\n", + " [0.0013, 0.0019, 0.0025, ..., 0.0022, 0.0020, 0.0021]]],\n", + " grad_fn=<DivBackward0>)" + ] + }, + "execution_count": 416, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "softmax(attention_weights_1, dim=-1).sum(axis=1) / 8" + ] + }, + { + "cell_type": "code", + "execution_count": 411, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "torch.Size([1, 1, 6, 500])" + ] + }, + "execution_count": 411, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "softmax(attention_weights_1, dim=-1).shape" + ] + }, + { + "cell_type": "code", + "execution_count": 339, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "tensor(1.0000, grad_fn=<SumBackward0>)" + ] + }, + "execution_count": 339, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "attention_weights_0[0][0].sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 396, + "metadata": {}, + "outputs": [], + "source": [ + "test = softmax(attention_weights_2, dim=-1)" + ] + }, + { + "cell_type": "code", + "execution_count": 402, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "tensor([0.0024, 0.0030, 0.0019, 0.0018, 0.0038, 0.0015, 0.0020, 0.0016, 0.0015,\n", + " 0.0019, 0.0015, 0.0035, 0.0026, 0.0017, 0.0014, 0.0013, 0.0023, 0.0020,\n", + " 0.0017, 0.0010], grad_fn=<SliceBackward>)" + ] + }, + "execution_count": 402, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "attention_weights_0[0][0][:20]" + ] + }, + { + "cell_type": "code", + "execution_count": 404, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "tensor([0.0028, 0.0033, 0.0019, 0.0013, 0.0042, 0.0016, 0.0024, 0.0018, 0.0019,\n", + " 0.0024, 0.0016, 0.0033, 0.0022, 0.0014, 0.0016, 0.0013, 0.0023, 0.0021,\n", + " 0.0013, 0.0013], grad_fn=<SliceBackward>)" + ] + }, + "execution_count": 404, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "test[0][0][:20]" + ] + }, + { + "cell_type": "code", + "execution_count": 366, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "tensor([[[False, False, False, ..., False, False, False],\n", + " [False, False, False, ..., False, False, False],\n", + " [False, False, False, ..., False, False, False],\n", + " [False, False, False, ..., False, False, False],\n", + " [False, False, False, ..., False, False, False],\n", + " [False, False, False, ..., False, False, False]]])" + ] + }, + "execution_count": 366, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "torch.eq(attention_weights_0, test)" + ] + }, + { + "cell_type": "code", + "execution_count": 320, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "torch.Size([1, 8, 6, 500])" + ] + }, + "execution_count": 320, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "attention_weights_1.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 318, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "torch.Size([1, 6, 500])" + ] + }, + "execution_count": 318, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "attention_weights_2.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 282, + "metadata": {}, + "outputs": [], + "source": [ + "out = self.classifier(out.squeeze(0).squeeze(1))" + ] + }, + { + "cell_type": "code", + "execution_count": 284, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "tensor([ 0.2832, 0.1548, -0.0972, -0.2801], grad_fn=<AddBackward0>)" + ] + }, + "execution_count": 284, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "out" + ] + }, + { + "cell_type": "code", + "execution_count": 269, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "tensor([[0.0018, 0.0019, 0.0019, ..., 0.0019, 0.0022, 0.0018],\n", + " [0.0020, 0.0020, 0.0021, ..., 0.0021, 0.0020, 0.0020],\n", + " [0.0019, 0.0022, 0.0021, ..., 0.0019, 0.0019, 0.0020],\n", + " [0.0021, 0.0022, 0.0019, ..., 0.0018, 0.0020, 0.0021],\n", + " [0.0019, 0.0019, 0.0020, ..., 0.0020, 0.0018, 0.0019],\n", + " [0.0021, 0.0021, 0.0019, ..., 0.0019, 0.0021, 0.0021]],\n", + " grad_fn=<SelectBackward>)" + ] + }, + "execution_count": 269, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "attention_weights[0]" + ] + }, + { + "cell_type": "code", + "execution_count": 241, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(tensor([[[-0.0504, 0.0757, -0.0366, ..., -0.0275, -0.0294, 0.1300]],\n", + " \n", + " [[-0.0500, 0.0762, -0.0352, ..., -0.0253, -0.0289, 0.1311]],\n", + " \n", + " [[-0.0497, 0.0772, -0.0321, ..., -0.0246, -0.0288, 0.1301]],\n", + " \n", + " [[-0.0491, 0.0794, -0.0337, ..., -0.0260, -0.0278, 0.1281]],\n", + " \n", + " [[-0.0483, 0.0781, -0.0343, ..., -0.0246, -0.0301, 0.1321]],\n", + " \n", + " [[-0.0499, 0.0768, -0.0305, ..., -0.0257, -0.0280, 0.1321]]],\n", + " grad_fn=<AddBackward0>),\n", + " tensor([[[0.0019, 0.0019, 0.0019, ..., 0.0020, 0.0021, 0.0021],\n", + " [0.0017, 0.0020, 0.0020, ..., 0.0019, 0.0019, 0.0018],\n", + " [0.0019, 0.0018, 0.0019, ..., 0.0019, 0.0019, 0.0021],\n", + " [0.0020, 0.0020, 0.0019, ..., 0.0020, 0.0021, 0.0019],\n", + " [0.0017, 0.0023, 0.0021, ..., 0.0019, 0.0020, 0.0020],\n", + " [0.0021, 0.0021, 0.0020, ..., 0.0021, 0.0021, 0.0020]]],\n", + " grad_fn=<DivBackward0>))" + ] + }, + "execution_count": 241, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "self.coattn(x_omic, x_path, x_path)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "h" + ] + }, + { + "cell_type": "code", + "execution_count": 208, + "metadata": {}, + "outputs": [], + "source": [ + "sig_feats = [torch.randn(size) for size in sig_sizes]\n", + "x_omic = torch.stack([self.sig_networks[idx].forward(sig_feat) for idx, sig_feat in enumerate(sig_feats)])\n" + ] + }, + { + "cell_type": "code", + "execution_count": 204, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 206, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "torch.Size([6, 256])" + ] + }, + "execution_count": 206, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "x_omic.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 166, + "metadata": {}, + "outputs": [ + { + "ename": "NameError", + "evalue": "name 'sig1' is not defined", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m<ipython-input-166-aea4cb4c555c>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0msig1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msig2\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msig3\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msig4\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msig5\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msig6\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[0;31mNameError\u001b[0m: name 'sig1' is not defined" + ] + } + ], + "source": [ + "sig1, sig2, sig3, sig4, sig5, sig6 = torch.randn()" + ] + }, + { + "cell_type": "code", + "execution_count": 158, + "metadata": {}, + "outputs": [], + "source": [ + "src = torch.rand(6, 1, 256)\n", + "out = transformer(src)\n", + "out = out.squeeze(1).T.unsqueeze(0)" + ] + }, + { + "cell_type": "code", + "execution_count": 163, + "metadata": {}, + "outputs": [], + "source": [ + "conv = nn.Conv1d(in_channels=256, out_channels=256, kernel_size=4, stride=4)" + ] + }, + { + "cell_type": "code", + "execution_count": 164, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "torch.Size([1, 256, 6])" + ] + }, + "execution_count": 164, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "out.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 165, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "torch.Size([1, 256, 1])" + ] + }, + "execution_count": 165, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "conv(out).shape" + ] + }, + { + "cell_type": "code", + "execution_count": 112, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "torch.Size([1536])" + ] + }, + "execution_count": 112, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "x.reshape(-1).shape" + ] + }, + { + "cell_type": "code", + "execution_count": 106, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "3072" + ] + }, + "execution_count": 106, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "256 * 12" + ] + }, + { + "cell_type": "code", + "execution_count": 88, + "metadata": {}, + "outputs": [], + "source": [ + "net = Attn_Net_Gated()\n", + "wsi_feats = torch.randn(500, 1, 256)\n", + "sig_feats = torch.randn(6, 1, 256)" + ] + }, + { + "cell_type": "code", + "execution_count": 89, + "metadata": {}, + "outputs": [], + "source": [ + "multihead_attn = nn.MultiheadAttention(embed_dim=256, num_heads=8)" + ] + }, + { + "cell_type": "code", + "execution_count": 90, + "metadata": {}, + "outputs": [], + "source": [ + "out, coattn_weights = multihead_attn(sig_feats, wsi_feats, wsi_feats)" + ] + }, + { + "cell_type": "code", + "execution_count": 96, + "metadata": {}, + "outputs": [], + "source": [ + "cotton = DenseCoAttn(dim1=256, dim2=256, num_attn=8, num_none=3, dropout=0.3b)" + ] + }, + { + "cell_type": "code", + "execution_count": 100, + "metadata": {}, + "outputs": [], + "source": [ + "from math import sqrt\n", + "wsi_feats = torch.randn(1, 500, 256)\n", + "sig_feats = torch.randn(1, 6, 256)\n", + "_ = cotton(wsi_feats, sig_feats)" + ] + }, + { + "cell_type": "code", + "execution_count": 103, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "torch.Size([1, 6, 256])" + ] + }, + "execution_count": 103, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "_[0].shape" + ] + }, + { + "cell_type": "code", + "execution_count": 104, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "torch.Size([1, 500, 256])" + ] + }, + "execution_count": 104, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "_[1].shape" + ] + }, + { + "cell_type": "code", + "execution_count": 94, + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "import torch\n", + "import torch.nn as nn\n", + "import torch.nn.functional as F\n", + "\n", + "\n", + "def qkv_attention(query, key, value, mask=None, dropout=None):\n", + "\td_k = query.size(-1)\n", + "\tscores = torch.matmul(query, key.transpose(-2,-1)) / sqrt(d_k)\n", + "\tif mask is not None:\n", + "\t\tscores.data.masked_fill_(mask.eq(0), -65504.0)\n", + "\t\n", + "\tp_attn = F.softmax(scores, dim=-1)\n", + "\tif dropout is not None:\n", + "\t\tp_attn = dropout(p_attn)\n", + "\n", + "\treturn torch.matmul(p_attn, value), p_attn\n", + "\n", + "\n", + "class DenseCoAttn(nn.Module):\n", + "\n", + "\tdef __init__(self, dim1, dim2, num_attn, num_none, dropout, is_multi_head=False):\n", + "\t\tsuper(DenseCoAttn, self).__init__()\n", + "\t\tdim = min(dim1, dim2)\n", + "\t\tself.linears = nn.ModuleList([nn.Linear(dim1, dim, bias=False),\n", + "\t\t\t\t\t\t\t\t\t nn.Linear(dim2, dim, bias=False)])\n", + "\t\tself.nones = nn.ParameterList([nn.Parameter(nn.init.xavier_uniform_(torch.empty(num_none, dim1))),\n", + "\t\t\t\t\t\t\t\t\t nn.Parameter(nn.init.xavier_uniform_(torch.empty(num_none, dim2)))])\n", + "\t\tself.d_k = dim // num_attn\n", + "\t\tself.h = num_attn\n", + "\t\tself.num_none = num_none\n", + "\t\tself.is_multi_head = is_multi_head\n", + "\t\tself.attn = None\n", + "\t\tself.dropouts = nn.ModuleList([nn.Dropout(p=dropout) for _ in range(2)])\n", + "\n", + "\tdef forward(self, value1, value2, mask1=None, mask2=None):\n", + "\t\tbatch = value1.size(0)\n", + "\t\tdim1, dim2 = value1.size(-1), value2.size(-1)\n", + "\t\tvalue1 = torch.cat([self.nones[0].unsqueeze(0).expand(batch, self.num_none, dim1), value1], dim=1)\n", + "\t\tvalue2 = torch.cat([self.nones[1].unsqueeze(0).expand(batch, self.num_none, dim2), value2], dim=1)\n", + "\t\tnone_mask = value1.new_ones((batch, self.num_none))\n", + "\n", + "\t\tif mask1 is not None:\n", + "\t\t\tmask1 = torch.cat([none_mask, mask1], dim=1)\n", + "\t\t\tmask1 = mask1.unsqueeze(1).unsqueeze(2)\n", + "\t\tif mask2 is not None:\n", + "\t\t\tmask2 = torch.cat([none_mask, mask2], dim=1)\n", + "\t\t\tmask2 = mask2.unsqueeze(1).unsqueeze(2)\n", + "\n", + "\t\tquery1, query2 = [l(x).view(batch, -1, self.h, self.d_k).transpose(1, 2) \n", + "\t\t\tfor l, x in zip(self.linears, (value1, value2))]\n", + "\n", + "\t\tif self.is_multi_head:\n", + "\t\t\tweighted1, attn1 = qkv_attention(query2, query1, query1, mask=mask1, dropout=self.dropouts[0])\n", + "\t\t\tweighted1 = weighted1.transpose(1, 2).contiguous()[:, self.num_none:, :]\n", + "\t\t\tweighted2, attn2 = qkv_attention(query1, query2, query2, mask=mask2, dropout=self.dropouts[1])\n", + "\t\t\tweighted2 = weighted2.transpose(1, 2).contiguous()[:, self.num_none:, :]\n", + "\t\telse:\n", + "\t\t\tweighted1, attn1 = qkv_attention(query2, query1, value1.unsqueeze(1), mask=mask1, \n", + "\t\t\t\tdropout=self.dropouts[0])\n", + "\t\t\tweighted1 = weighted1.mean(dim=1)[:, self.num_none:, :]\n", + "\t\t\tweighted2, attn2 = qkv_attention(query1, query2, value2.unsqueeze(1), mask=mask2, \n", + "\t\t\t\tdropout=self.dropouts[1])\n", + "\t\t\tweighted2 = weighted2.mean(dim=1)[:, self.num_none:, :]\n", + "\t\tself.attn = [attn1[:,:,self.num_none:,self.num_none:], attn2[:,:,self.num_none:,self.num_none:]]\n", + "\n", + "\t\treturn weighted1, weighted2\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 417, + "metadata": {}, + "outputs": [], + "source": [ + "from torch.nn.functional import *\n", + "\n", + "def multi_head_attention_forward(\n", + " query: Tensor,\n", + " key: Tensor,\n", + " value: Tensor,\n", + " embed_dim_to_check: int,\n", + " num_heads: int,\n", + " in_proj_weight: Tensor,\n", + " in_proj_bias: Tensor,\n", + " bias_k: Optional[Tensor],\n", + " bias_v: Optional[Tensor],\n", + " add_zero_attn: bool,\n", + " dropout_p: float,\n", + " out_proj_weight: Tensor,\n", + " out_proj_bias: Tensor,\n", + " training: bool = True,\n", + " key_padding_mask: Optional[Tensor] = None,\n", + " need_weights: bool = True,\n", + " need_raw: bool = True,\n", + " attn_mask: Optional[Tensor] = None,\n", + " use_separate_proj_weight: bool = False,\n", + " q_proj_weight: Optional[Tensor] = None,\n", + " k_proj_weight: Optional[Tensor] = None,\n", + " v_proj_weight: Optional[Tensor] = None,\n", + " static_k: Optional[Tensor] = None,\n", + " static_v: Optional[Tensor] = None,\n", + ") -> Tuple[Tensor, Optional[Tensor]]:\n", + " r\"\"\"\n", + " Args:\n", + " query, key, value: map a query and a set of key-value pairs to an output.\n", + " See \"Attention Is All You Need\" for more details.\n", + " embed_dim_to_check: total dimension of the model.\n", + " num_heads: parallel attention heads.\n", + " in_proj_weight, in_proj_bias: input projection weight and bias.\n", + " bias_k, bias_v: bias of the key and value sequences to be added at dim=0.\n", + " add_zero_attn: add a new batch of zeros to the key and\n", + " value sequences at dim=1.\n", + " dropout_p: probability of an element to be zeroed.\n", + " out_proj_weight, out_proj_bias: the output projection weight and bias.\n", + " training: apply dropout if is ``True``.\n", + " key_padding_mask: if provided, specified padding elements in the key will\n", + " be ignored by the attention. This is an binary mask. When the value is True,\n", + " the corresponding value on the attention layer will be filled with -inf.\n", + " need_weights: output attn_output_weights.\n", + " attn_mask: 2D or 3D mask that prevents attention to certain positions. A 2D mask will be broadcasted for all\n", + " the batches while a 3D mask allows to specify a different mask for the entries of each batch.\n", + " use_separate_proj_weight: the function accept the proj. weights for query, key,\n", + " and value in different forms. If false, in_proj_weight will be used, which is\n", + " a combination of q_proj_weight, k_proj_weight, v_proj_weight.\n", + " q_proj_weight, k_proj_weight, v_proj_weight, in_proj_bias: input projection weight and bias.\n", + " static_k, static_v: static key and value used for attention operators.\n", + " Shape:\n", + " Inputs:\n", + " - query: :math:`(L, N, E)` where L is the target sequence length, N is the batch size, E is\n", + " the embedding dimension.\n", + " - key: :math:`(S, N, E)`, where S is the source sequence length, N is the batch size, E is\n", + " the embedding dimension.\n", + " - value: :math:`(S, N, E)` where S is the source sequence length, N is the batch size, E is\n", + " the embedding dimension.\n", + " - key_padding_mask: :math:`(N, S)` where N is the batch size, S is the source sequence length.\n", + " If a ByteTensor is provided, the non-zero positions will be ignored while the zero positions\n", + " will be unchanged. If a BoolTensor is provided, the positions with the\n", + " value of ``True`` will be ignored while the position with the value of ``False`` will be unchanged.\n", + " - attn_mask: 2D mask :math:`(L, S)` where L is the target sequence length, S is the source sequence length.\n", + " 3D mask :math:`(N*num_heads, L, S)` where N is the batch size, L is the target sequence length,\n", + " S is the source sequence length. attn_mask ensures that position i is allowed to attend the unmasked\n", + " positions. If a ByteTensor is provided, the non-zero positions are not allowed to attend\n", + " while the zero positions will be unchanged. If a BoolTensor is provided, positions with ``True``\n", + " are not allowed to attend while ``False`` values will be unchanged. If a FloatTensor\n", + " is provided, it will be added to the attention weight.\n", + " - static_k: :math:`(N*num_heads, S, E/num_heads)`, where S is the source sequence length,\n", + " N is the batch size, E is the embedding dimension. E/num_heads is the head dimension.\n", + " - static_v: :math:`(N*num_heads, S, E/num_heads)`, where S is the source sequence length,\n", + " N is the batch size, E is the embedding dimension. E/num_heads is the head dimension.\n", + " Outputs:\n", + " - attn_output: :math:`(L, N, E)` where L is the target sequence length, N is the batch size,\n", + " E is the embedding dimension.\n", + " - attn_output_weights: :math:`(N, L, S)` where N is the batch size,\n", + " L is the target sequence length, S is the source sequence length.\n", + " \"\"\"\n", + " tens_ops = (query, key, value, in_proj_weight, in_proj_bias, bias_k, bias_v, out_proj_weight, out_proj_bias)\n", + " if has_torch_function(tens_ops):\n", + " return handle_torch_function(\n", + " multi_head_attention_forward,\n", + " tens_ops,\n", + " query,\n", + " key,\n", + " value,\n", + " embed_dim_to_check,\n", + " num_heads,\n", + " in_proj_weight,\n", + " in_proj_bias,\n", + " bias_k,\n", + " bias_v,\n", + " add_zero_attn,\n", + " dropout_p,\n", + " out_proj_weight,\n", + " out_proj_bias,\n", + " training=training,\n", + " key_padding_mask=key_padding_mask,\n", + " need_weights=need_weights,\n", + " need_raw=need_raw,\n", + " attn_mask=attn_mask,\n", + " use_separate_proj_weight=use_separate_proj_weight,\n", + " q_proj_weight=q_proj_weight,\n", + " k_proj_weight=k_proj_weight,\n", + " v_proj_weight=v_proj_weight,\n", + " static_k=static_k,\n", + " static_v=static_v,\n", + " )\n", + " tgt_len, bsz, embed_dim = query.size()\n", + " assert embed_dim == embed_dim_to_check\n", + " # allow MHA to have different sizes for the feature dimension\n", + " assert key.size(0) == value.size(0) and key.size(1) == value.size(1)\n", + "\n", + " head_dim = embed_dim // num_heads\n", + " assert head_dim * num_heads == embed_dim, \"embed_dim must be divisible by num_heads\"\n", + " scaling = float(head_dim) ** -0.5\n", + "\n", + " if not use_separate_proj_weight:\n", + " if (query is key or torch.equal(query, key)) and (key is value or torch.equal(key, value)):\n", + " # self-attention\n", + " q, k, v = linear(query, in_proj_weight, in_proj_bias).chunk(3, dim=-1)\n", + "\n", + " elif key is value or torch.equal(key, value):\n", + " # encoder-decoder attention\n", + " # This is inline in_proj function with in_proj_weight and in_proj_bias\n", + " _b = in_proj_bias\n", + " _start = 0\n", + " _end = embed_dim\n", + " _w = in_proj_weight[_start:_end, :]\n", + " if _b is not None:\n", + " _b = _b[_start:_end]\n", + " q = linear(query, _w, _b)\n", + "\n", + " if key is None:\n", + " assert value is None\n", + " k = None\n", + " v = None\n", + " else:\n", + "\n", + " # This is inline in_proj function with in_proj_weight and in_proj_bias\n", + " _b = in_proj_bias\n", + " _start = embed_dim\n", + " _end = None\n", + " _w = in_proj_weight[_start:, :]\n", + " if _b is not None:\n", + " _b = _b[_start:]\n", + " k, v = linear(key, _w, _b).chunk(2, dim=-1)\n", + "\n", + " else:\n", + " # This is inline in_proj function with in_proj_weight and in_proj_bias\n", + " _b = in_proj_bias\n", + " _start = 0\n", + " _end = embed_dim\n", + " _w = in_proj_weight[_start:_end, :]\n", + " if _b is not None:\n", + " _b = _b[_start:_end]\n", + " q = linear(query, _w, _b)\n", + "\n", + " # This is inline in_proj function with in_proj_weight and in_proj_bias\n", + " _b = in_proj_bias\n", + " _start = embed_dim\n", + " _end = embed_dim * 2\n", + " _w = in_proj_weight[_start:_end, :]\n", + " if _b is not None:\n", + " _b = _b[_start:_end]\n", + " k = linear(key, _w, _b)\n", + "\n", + " # This is inline in_proj function with in_proj_weight and in_proj_bias\n", + " _b = in_proj_bias\n", + " _start = embed_dim * 2\n", + " _end = None\n", + " _w = in_proj_weight[_start:, :]\n", + " if _b is not None:\n", + " _b = _b[_start:]\n", + " v = linear(value, _w, _b)\n", + " else:\n", + " q_proj_weight_non_opt = torch.jit._unwrap_optional(q_proj_weight)\n", + " len1, len2 = q_proj_weight_non_opt.size()\n", + " assert len1 == embed_dim and len2 == query.size(-1)\n", + "\n", + " k_proj_weight_non_opt = torch.jit._unwrap_optional(k_proj_weight)\n", + " len1, len2 = k_proj_weight_non_opt.size()\n", + " assert len1 == embed_dim and len2 == key.size(-1)\n", + "\n", + " v_proj_weight_non_opt = torch.jit._unwrap_optional(v_proj_weight)\n", + " len1, len2 = v_proj_weight_non_opt.size()\n", + " assert len1 == embed_dim and len2 == value.size(-1)\n", + "\n", + " if in_proj_bias is not None:\n", + " q = linear(query, q_proj_weight_non_opt, in_proj_bias[0:embed_dim])\n", + " k = linear(key, k_proj_weight_non_opt, in_proj_bias[embed_dim : (embed_dim * 2)])\n", + " v = linear(value, v_proj_weight_non_opt, in_proj_bias[(embed_dim * 2) :])\n", + " else:\n", + " q = linear(query, q_proj_weight_non_opt, in_proj_bias)\n", + " k = linear(key, k_proj_weight_non_opt, in_proj_bias)\n", + " v = linear(value, v_proj_weight_non_opt, in_proj_bias)\n", + " q = q * scaling\n", + "\n", + " if attn_mask is not None:\n", + " assert (\n", + " attn_mask.dtype == torch.float32\n", + " or attn_mask.dtype == torch.float64\n", + " or attn_mask.dtype == torch.float16\n", + " or attn_mask.dtype == torch.uint8\n", + " or attn_mask.dtype == torch.bool\n", + " ), \"Only float, byte, and bool types are supported for attn_mask, not {}\".format(attn_mask.dtype)\n", + " if attn_mask.dtype == torch.uint8:\n", + " warnings.warn(\"Byte tensor for attn_mask in nn.MultiheadAttention is deprecated. Use bool tensor instead.\")\n", + " attn_mask = attn_mask.to(torch.bool)\n", + "\n", + " if attn_mask.dim() == 2:\n", + " attn_mask = attn_mask.unsqueeze(0)\n", + " if list(attn_mask.size()) != [1, query.size(0), key.size(0)]:\n", + " raise RuntimeError(\"The size of the 2D attn_mask is not correct.\")\n", + " elif attn_mask.dim() == 3:\n", + " if list(attn_mask.size()) != [bsz * num_heads, query.size(0), key.size(0)]:\n", + " raise RuntimeError(\"The size of the 3D attn_mask is not correct.\")\n", + " else:\n", + " raise RuntimeError(\"attn_mask's dimension {} is not supported\".format(attn_mask.dim()))\n", + " # attn_mask's dim is 3 now.\n", + "\n", + " # convert ByteTensor key_padding_mask to bool\n", + " if key_padding_mask is not None and key_padding_mask.dtype == torch.uint8:\n", + " warnings.warn(\n", + " \"Byte tensor for key_padding_mask in nn.MultiheadAttention is deprecated. Use bool tensor instead.\"\n", + " )\n", + " key_padding_mask = key_padding_mask.to(torch.bool)\n", + "\n", + " if bias_k is not None and bias_v is not None:\n", + " if static_k is None and static_v is None:\n", + " k = torch.cat([k, bias_k.repeat(1, bsz, 1)])\n", + " v = torch.cat([v, bias_v.repeat(1, bsz, 1)])\n", + " if attn_mask is not None:\n", + " attn_mask = pad(attn_mask, (0, 1))\n", + " if key_padding_mask is not None:\n", + " key_padding_mask = pad(key_padding_mask, (0, 1))\n", + " else:\n", + " assert static_k is None, \"bias cannot be added to static key.\"\n", + " assert static_v is None, \"bias cannot be added to static value.\"\n", + " else:\n", + " assert bias_k is None\n", + " assert bias_v is None\n", + "\n", + " q = q.contiguous().view(tgt_len, bsz * num_heads, head_dim).transpose(0, 1)\n", + " if k is not None:\n", + " k = k.contiguous().view(-1, bsz * num_heads, head_dim).transpose(0, 1)\n", + " if v is not None:\n", + " v = v.contiguous().view(-1, bsz * num_heads, head_dim).transpose(0, 1)\n", + "\n", + " if static_k is not None:\n", + " assert static_k.size(0) == bsz * num_heads\n", + " assert static_k.size(2) == head_dim\n", + " k = static_k\n", + "\n", + " if static_v is not None:\n", + " assert static_v.size(0) == bsz * num_heads\n", + " assert static_v.size(2) == head_dim\n", + " v = static_v\n", + "\n", + " src_len = k.size(1)\n", + "\n", + " if key_padding_mask is not None:\n", + " assert key_padding_mask.size(0) == bsz\n", + " assert key_padding_mask.size(1) == src_len\n", + "\n", + " if add_zero_attn:\n", + " src_len += 1\n", + " k = torch.cat([k, torch.zeros((k.size(0), 1) + k.size()[2:], dtype=k.dtype, device=k.device)], dim=1)\n", + " v = torch.cat([v, torch.zeros((v.size(0), 1) + v.size()[2:], dtype=v.dtype, device=v.device)], dim=1)\n", + " if attn_mask is not None:\n", + " attn_mask = pad(attn_mask, (0, 1))\n", + " if key_padding_mask is not None:\n", + " key_padding_mask = pad(key_padding_mask, (0, 1))\n", + "\n", + " attn_output_weights = torch.bmm(q, k.transpose(1, 2))\n", + " assert list(attn_output_weights.size()) == [bsz * num_heads, tgt_len, src_len]\n", + "\n", + " if attn_mask is not None:\n", + " if attn_mask.dtype == torch.bool:\n", + " attn_output_weights.masked_fill_(attn_mask, float(\"-inf\"))\n", + " else:\n", + " attn_output_weights += attn_mask\n", + "\n", + " if key_padding_mask is not None:\n", + " attn_output_weights = attn_output_weights.view(bsz, num_heads, tgt_len, src_len)\n", + " attn_output_weights = attn_output_weights.masked_fill(\n", + " key_padding_mask.unsqueeze(1).unsqueeze(2),\n", + " float(\"-inf\"),\n", + " )\n", + " attn_output_weights = attn_output_weights.view(bsz * num_heads, tgt_len, src_len)\n", + " \n", + " attn_output_weights_raw = attn_output_weights\n", + " attn_output_weights = softmax(attn_output_weights, dim=-1)\n", + " attn_output_weights = dropout(attn_output_weights, p=dropout_p, training=training)\n", + "\n", + " attn_output = torch.bmm(attn_output_weights, v)\n", + " assert list(attn_output.size()) == [bsz * num_heads, tgt_len, head_dim]\n", + " attn_output = attn_output.transpose(0, 1).contiguous().view(tgt_len, bsz, embed_dim)\n", + " attn_output = linear(attn_output, out_proj_weight, out_proj_bias)\n", + " \n", + " if need_weights:\n", + " if need_raw:\n", + " \n", + " attn_output_weights_raw = attn_output_weights_raw.view(bsz, num_heads, tgt_len, src_len)\n", + " return attn_output,attn_output_weights_raw\n", + " \n", + " #attn_output_weights = attn_output_weights.view(bsz, num_heads, tgt_len, src_len)\n", + " #return attn_output, attn_output_weights.sum(dim=1) / num_heads, attn_output_weights_raw, attn_output_weights_raw.sum(dim=1) / num_heads\n", + " else:\n", + " # average attention weights over heads\n", + " attn_output_weights = attn_output_weights.view(bsz, num_heads, tgt_len, src_len)\n", + " return attn_output, attn_output_weights.sum(dim=1) / num_heads\n", + " else:\n", + " return attn_output, None\n" + ] + }, + { + "cell_type": "code", + "execution_count": 418, + "metadata": {}, + "outputs": [], + "source": [ + "import torch\n", + "from torch import Tensor\n", + "from torch.nn.modules.linear import _LinearWithBias\n", + "from torch.nn.init import xavier_uniform_\n", + "from torch.nn.init import constant_\n", + "from torch.nn.init import xavier_normal_\n", + "from torch.nn.parameter import Parameter\n", + "from torch.nn import Module\n", + "\n", + "class MultiheadAttention(Module):\n", + " r\"\"\"Allows the model to jointly attend to information\n", + " from different representation subspaces.\n", + " See reference: Attention Is All You Need\n", + "\n", + " .. math::\n", + " \\text{MultiHead}(Q, K, V) = \\text{Concat}(head_1,\\dots,head_h)W^O\n", + " \\text{where} head_i = \\text{Attention}(QW_i^Q, KW_i^K, VW_i^V)\n", + "\n", + " Args:\n", + " embed_dim: total dimension of the model.\n", + " num_heads: parallel attention heads.\n", + " dropout: a Dropout layer on attn_output_weights. Default: 0.0.\n", + " bias: add bias as module parameter. Default: True.\n", + " add_bias_kv: add bias to the key and value sequences at dim=0.\n", + " add_zero_attn: add a new batch of zeros to the key and\n", + " value sequences at dim=1.\n", + " kdim: total number of features in key. Default: None.\n", + " vdim: total number of features in value. Default: None.\n", + "\n", + " Note: if kdim and vdim are None, they will be set to embed_dim such that\n", + " query, key, and value have the same number of features.\n", + "\n", + " Examples::\n", + "\n", + " >>> multihead_attn = nn.MultiheadAttention(embed_dim, num_heads)\n", + " >>> attn_output, attn_output_weights = multihead_attn(query, key, value)\n", + " \"\"\"\n", + " bias_k: Optional[torch.Tensor]\n", + " bias_v: Optional[torch.Tensor]\n", + "\n", + " def __init__(self, embed_dim, num_heads, dropout=0., bias=True, add_bias_kv=False, add_zero_attn=False, kdim=None, vdim=None):\n", + " super(MultiheadAttention, self).__init__()\n", + " self.embed_dim = embed_dim\n", + " self.kdim = kdim if kdim is not None else embed_dim\n", + " self.vdim = vdim if vdim is not None else embed_dim\n", + " self._qkv_same_embed_dim = self.kdim == embed_dim and self.vdim == embed_dim\n", + "\n", + " self.num_heads = num_heads\n", + " self.dropout = dropout\n", + " self.head_dim = embed_dim // num_heads\n", + " assert self.head_dim * num_heads == self.embed_dim, \"embed_dim must be divisible by num_heads\"\n", + "\n", + " if self._qkv_same_embed_dim is False:\n", + " self.q_proj_weight = Parameter(torch.Tensor(embed_dim, embed_dim))\n", + " self.k_proj_weight = Parameter(torch.Tensor(embed_dim, self.kdim))\n", + " self.v_proj_weight = Parameter(torch.Tensor(embed_dim, self.vdim))\n", + " self.register_parameter('in_proj_weight', None)\n", + " else:\n", + " self.in_proj_weight = Parameter(torch.empty(3 * embed_dim, embed_dim))\n", + " self.register_parameter('q_proj_weight', None)\n", + " self.register_parameter('k_proj_weight', None)\n", + " self.register_parameter('v_proj_weight', None)\n", + "\n", + " if bias:\n", + " self.in_proj_bias = Parameter(torch.empty(3 * embed_dim))\n", + " else:\n", + " self.register_parameter('in_proj_bias', None)\n", + " self.out_proj = _LinearWithBias(embed_dim, embed_dim)\n", + "\n", + " if add_bias_kv:\n", + " self.bias_k = Parameter(torch.empty(1, 1, embed_dim))\n", + " self.bias_v = Parameter(torch.empty(1, 1, embed_dim))\n", + " else:\n", + " self.bias_k = self.bias_v = None\n", + "\n", + " self.add_zero_attn = add_zero_attn\n", + "\n", + " self._reset_parameters()\n", + "\n", + " def _reset_parameters(self):\n", + " if self._qkv_same_embed_dim:\n", + " xavier_uniform_(self.in_proj_weight)\n", + " else:\n", + " xavier_uniform_(self.q_proj_weight)\n", + " xavier_uniform_(self.k_proj_weight)\n", + " xavier_uniform_(self.v_proj_weight)\n", + "\n", + " if self.in_proj_bias is not None:\n", + " constant_(self.in_proj_bias, 0.)\n", + " constant_(self.out_proj.bias, 0.)\n", + " if self.bias_k is not None:\n", + " xavier_normal_(self.bias_k)\n", + " if self.bias_v is not None:\n", + " xavier_normal_(self.bias_v)\n", + "\n", + " def __setstate__(self, state):\n", + " # Support loading old MultiheadAttention checkpoints generated by v1.1.0\n", + " if '_qkv_same_embed_dim' not in state:\n", + " state['_qkv_same_embed_dim'] = True\n", + "\n", + " super(MultiheadAttention, self).__setstate__(state)\n", + "\n", + " def forward(self, query, key, value, key_padding_mask=None,\n", + " need_weights=True, need_raw=True, attn_mask=None):\n", + " # type: (Tensor, Tensor, Tensor, Optional[Tensor], bool, Optional[Tensor]) -> Tuple[Tensor, Optional[Tensor]]\n", + " r\"\"\"\n", + " Args:\n", + " query, key, value: map a query and a set of key-value pairs to an output.\n", + " See \"Attention Is All You Need\" for more details.\n", + " key_padding_mask: if provided, specified padding elements in the key will\n", + " be ignored by the attention. When given a binary mask and a value is True,\n", + " the corresponding value on the attention layer will be ignored. When given\n", + " a byte mask and a value is non-zero, the corresponding value on the attention\n", + " layer will be ignored\n", + " need_weights: output attn_output_weights.\n", + " attn_mask: 2D or 3D mask that prevents attention to certain positions. A 2D mask will be broadcasted for all\n", + " the batches while a 3D mask allows to specify a different mask for the entries of each batch.\n", + "\n", + " Shape:\n", + " - Inputs:\n", + " - query: :math:`(L, N, E)` where L is the target sequence length, N is the batch size, E is\n", + " the embedding dimension.\n", + " - key: :math:`(S, N, E)`, where S is the source sequence length, N is the batch size, E is\n", + " the embedding dimension.\n", + " - value: :math:`(S, N, E)` where S is the source sequence length, N is the batch size, E is\n", + " the embedding dimension.\n", + " - key_padding_mask: :math:`(N, S)` where N is the batch size, S is the source sequence length.\n", + " If a ByteTensor is provided, the non-zero positions will be ignored while the position\n", + " with the zero positions will be unchanged. If a BoolTensor is provided, the positions with the\n", + " value of ``True`` will be ignored while the position with the value of ``False`` will be unchanged.\n", + " - attn_mask: 2D mask :math:`(L, S)` where L is the target sequence length, S is the source sequence length.\n", + " 3D mask :math:`(N*num_heads, L, S)` where N is the batch size, L is the target sequence length,\n", + " S is the source sequence length. attn_mask ensure that position i is allowed to attend the unmasked\n", + " positions. If a ByteTensor is provided, the non-zero positions are not allowed to attend\n", + " while the zero positions will be unchanged. If a BoolTensor is provided, positions with ``True``\n", + " is not allowed to attend while ``False`` values will be unchanged. If a FloatTensor\n", + " is provided, it will be added to the attention weight.\n", + "\n", + " - Outputs:\n", + " - attn_output: :math:`(L, N, E)` where L is the target sequence length, N is the batch size,\n", + " E is the embedding dimension.\n", + " - attn_output_weights: :math:`(N, L, S)` where N is the batch size,\n", + " L is the target sequence length, S is the source sequence length.\n", + " \"\"\"\n", + " if not self._qkv_same_embed_dim:\n", + " return multi_head_attention_forward(\n", + " query, key, value, self.embed_dim, self.num_heads,\n", + " self.in_proj_weight, self.in_proj_bias,\n", + " self.bias_k, self.bias_v, self.add_zero_attn,\n", + " self.dropout, self.out_proj.weight, self.out_proj.bias,\n", + " training=self.training,\n", + " key_padding_mask=key_padding_mask, need_weights=need_weights, need_raw=need_raw,\n", + " attn_mask=attn_mask, use_separate_proj_weight=True,\n", + " q_proj_weight=self.q_proj_weight, k_proj_weight=self.k_proj_weight,\n", + " v_proj_weight=self.v_proj_weight)\n", + " else:\n", + " return multi_head_attention_forward(\n", + " query, key, value, self.embed_dim, self.num_heads,\n", + " self.in_proj_weight, self.in_proj_bias,\n", + " self.bias_k, self.bias_v, self.add_zero_attn,\n", + " self.dropout, self.out_proj.weight, self.out_proj.bias,\n", + " training=self.training,\n", + " key_padding_mask=key_padding_mask, need_weights=need_weights, need_raw=need_raw,\n", + " attn_mask=attn_mask)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 104, + "metadata": {}, + "outputs": [ + { + "ename": "ModuleNotFoundError", + "evalue": "No module named 'torch'", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m<ipython-input-104-6bb47b25d46a>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmath\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0;32mimport\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 4\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mtorch\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mnn\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'torch'" + ] + } + ], + "source": [ + "import math\n", + "\n", + "import torch\n", + "from torch import nn\n", + "\n", + "############\n", + "# Omic Model\n", + "############\n", + "def init_max_weights(module):\n", + " for m in module.modules():\n", + " if type(m) == nn.Linear:\n", + " stdv = 1. / math.sqrt(m.weight.size(1))\n", + " m.weight.data.normal_(0, stdv)\n", + " m.bias.data.zero_()\n", + "\n", + "def SNN_Block(dim1, dim2, dropout=0.25):\n", + " return nn.Sequential(\n", + " nn.Linear(dim1, dim2),\n", + " nn.ELU(),\n", + " nn.AlphaDropout(p=dropout, inplace=False))\n", + "\n", + "class MaxNet(nn.Module):\n", + " def __init__(self, input_dim: int, meta_dim: int=0, model_size_omic: str='small', n_classes: int=4):\n", + " super(MaxNet, self).__init__()\n", + " self.meta_dim = meta_dim\n", + " self.n_classes = n_classes\n", + " self.size_dict_omic = {'small': [256, 256, 256, 256], 'big': [1024, 1024, 1024, 256]}\n", + " \n", + " ### Constructing Genomic SNN\n", + " hidden = self.size_dict_omic[model_size_omic]\n", + " fc_omic = [SNN_Block(dim1=input_dim, dim2=hidden[0])]\n", + " for i, _ in enumerate(hidden[1:]):\n", + " fc_omic.append(SNN_Block(dim1=hidden[i], dim2=hidden[i+1], dropout=0.25))\n", + " self.fc_omic = nn.Sequential(*fc_omic)\n", + " self.classifier = nn.Linear(hidden[-1]+self.meta_dim, n_classes)\n", + " init_max_weights(self)\n", + "\n", + " def forward(self, **kwargs):\n", + " x = kwargs['x_omic']\n", + " meta = kwargs['meta']\n", + " features = self.fc_omic(x)\n", + "\n", + " if self.meta_dim: \n", + " axis_dim = 1 if len(meta.shape) > 1 else 0\n", + " features = torch.cat((features, meta), axis_dim)\n", + "\n", + " logits = self.classifier(features).unsqueeze(0)\n", + " Y_hat = torch.topk(logits, 1, dim=1)[1]\n", + " hazards = torch.sigmoid(logits)\n", + " S = torch.cumprod(1 - hazards, dim=1)\n", + " return hazards, S, Y_hat, None, None\n", + "\n", + " def relocate(self):\n", + " device=torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n", + "\n", + " if torch.cuda.device_count() > 1:\n", + " device_ids = list(range(torch.cuda.device_count()))\n", + " self.fc_omic = nn.DataParallel(self.fc_omic, device_ids=device_ids).to('cuda:0')\n", + " else:\n", + " self.fc_omic = self.fc_omic.to(device)\n", + "\n", + "\n", + " self.classifier = self.classifier.to(device)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 88, + "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>CXCL14_rnaseq</th>\n", + " <th>FGF1_rnaseq</th>\n", + " <th>IFNA8_cnv</th>\n", + " <th>ADM_rnaseq</th>\n", + " <th>LTBP2_rnaseq</th>\n", + " <th>CCL28_rnaseq</th>\n", + " <th>IFNA7_rnaseq</th>\n", + " <th>GH2_rnaseq</th>\n", + " <th>AIMP1_rnaseq</th>\n", + " <th>DEFB1_rnaseq</th>\n", + " <th>...</th>\n", + " <th>NPPB_rnaseq</th>\n", + " <th>CCL27_rnaseq</th>\n", + " <th>FASLG_rnaseq</th>\n", + " <th>FGF20_cnv</th>\n", + " <th>FAM3C_rnaseq</th>\n", + " <th>IL18_rnaseq</th>\n", + " <th>GDF10_rnaseq</th>\n", + " <th>MYDGF_rnaseq</th>\n", + " <th>IL10_rnaseq</th>\n", + " <th>IFNW1_rnaseq</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>0</th>\n", + " <td>-0.1170</td>\n", + " <td>-0.2221</td>\n", + " <td>1</td>\n", + " <td>-0.5126</td>\n", + " <td>-0.3289</td>\n", + " <td>-0.7331</td>\n", + " <td>-0.1244</td>\n", + " <td>-0.1693</td>\n", + " <td>0.5942</td>\n", + " <td>-0.4707</td>\n", + " <td>...</td>\n", + " <td>-0.2276</td>\n", + " <td>1.2033</td>\n", + " <td>0.9826</td>\n", + " <td>-1</td>\n", + " <td>-0.6161</td>\n", + " <td>-0.5643</td>\n", + " <td>-0.2165</td>\n", + " <td>-0.2836</td>\n", + " <td>0.9991</td>\n", + " <td>-0.3899</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1</th>\n", + " <td>-0.2330</td>\n", + " <td>-0.4343</td>\n", + " <td>-1</td>\n", + " <td>-0.2381</td>\n", + " <td>-0.4799</td>\n", + " <td>-0.0520</td>\n", + " <td>-0.1244</td>\n", + " <td>-0.1693</td>\n", + " <td>1.1854</td>\n", + " <td>-0.4820</td>\n", + " <td>...</td>\n", + " <td>-0.2276</td>\n", + " <td>-0.2946</td>\n", + " <td>-0.5443</td>\n", + " <td>-1</td>\n", + " <td>-0.3499</td>\n", + " <td>-0.7958</td>\n", + " <td>-0.3140</td>\n", + " <td>-0.3359</td>\n", + " <td>-0.4865</td>\n", + " <td>-0.3899</td>\n", + " </tr>\n", + " <tr>\n", + " <th>2</th>\n", + " <td>-0.1384</td>\n", + " <td>-0.1597</td>\n", + " <td>-1</td>\n", + " <td>-0.1521</td>\n", + " <td>-0.3348</td>\n", + " <td>-0.5310</td>\n", + " <td>-0.1244</td>\n", + " <td>-0.1693</td>\n", + " <td>0.3889</td>\n", + " <td>-0.3607</td>\n", + " <td>...</td>\n", + " <td>3.4177</td>\n", + " <td>-0.2946</td>\n", + " <td>-0.5320</td>\n", + " <td>0</td>\n", + " <td>0.4581</td>\n", + " <td>-0.6179</td>\n", + " <td>-0.2107</td>\n", + " <td>0.2751</td>\n", + " <td>-0.5108</td>\n", + " <td>1.0629</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3</th>\n", + " <td>-0.1624</td>\n", + " <td>-0.3463</td>\n", + " <td>-1</td>\n", + " <td>0.0272</td>\n", + " <td>-0.7623</td>\n", + " <td>0.8196</td>\n", + " <td>-0.1244</td>\n", + " <td>-0.1693</td>\n", + " <td>-0.0416</td>\n", + " <td>0.1661</td>\n", + " <td>...</td>\n", + " <td>-0.2276</td>\n", + " <td>-0.1020</td>\n", + " <td>-0.4682</td>\n", + " <td>-1</td>\n", + " <td>-0.4391</td>\n", + " <td>-0.7275</td>\n", + " <td>-0.2876</td>\n", + " <td>-0.4696</td>\n", + " <td>-0.6248</td>\n", + " <td>-0.3899</td>\n", + " </tr>\n", + " <tr>\n", + " <th>4</th>\n", + " <td>-0.2346</td>\n", + " <td>-0.4090</td>\n", + " <td>-1</td>\n", + " <td>-0.2078</td>\n", + " <td>0.5702</td>\n", + " <td>-0.4219</td>\n", + " <td>-0.1244</td>\n", + " <td>0.5257</td>\n", + " <td>-0.9790</td>\n", + " <td>0.3938</td>\n", + " <td>...</td>\n", + " <td>-0.2276</td>\n", + " <td>-0.1035</td>\n", + " <td>-0.4688</td>\n", + " <td>-1</td>\n", + " <td>1.2596</td>\n", + " <td>-0.5807</td>\n", + " <td>0.4108</td>\n", + " <td>0.1801</td>\n", + " <td>-0.6086</td>\n", + " <td>-0.3899</td>\n", + " </tr>\n", + " <tr>\n", + " <th>...</th>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " </tr>\n", + " <tr>\n", + " <th>368</th>\n", + " <td>-0.2417</td>\n", + " <td>10.1423</td>\n", + " <td>-1</td>\n", + " <td>-0.5456</td>\n", + " <td>0.8742</td>\n", + " <td>-0.1822</td>\n", + " <td>-0.1244</td>\n", + " <td>-0.1693</td>\n", + " <td>-1.2395</td>\n", + " <td>-0.5125</td>\n", + " <td>...</td>\n", + " <td>-0.2276</td>\n", + " <td>-0.2946</td>\n", + " <td>0.0777</td>\n", + " <td>0</td>\n", + " <td>-0.8242</td>\n", + " <td>-0.6727</td>\n", + " <td>0.1938</td>\n", + " <td>0.9210</td>\n", + " <td>0.4479</td>\n", + " <td>-0.3899</td>\n", + " </tr>\n", + " <tr>\n", + " <th>369</th>\n", + " <td>-0.2412</td>\n", + " <td>1.3253</td>\n", + " <td>1</td>\n", + " <td>-0.5680</td>\n", + " <td>1.0719</td>\n", + " <td>-0.1707</td>\n", + " <td>-0.1244</td>\n", + " <td>-0.1693</td>\n", + " <td>-1.6694</td>\n", + " <td>-0.4528</td>\n", + " <td>...</td>\n", + " <td>0.5679</td>\n", + " <td>-0.2661</td>\n", + " <td>1.0215</td>\n", + " <td>-2</td>\n", + " <td>-0.5327</td>\n", + " <td>0.3335</td>\n", + " <td>-0.1730</td>\n", + " <td>0.0147</td>\n", + " <td>0.6012</td>\n", + " <td>2.2526</td>\n", + " </tr>\n", + " <tr>\n", + " <th>370</th>\n", + " <td>-0.2396</td>\n", + " <td>0.0435</td>\n", + " <td>0</td>\n", + " <td>-0.3610</td>\n", + " <td>3.1965</td>\n", + " <td>1.3670</td>\n", + " <td>-0.1244</td>\n", + " <td>-0.1693</td>\n", + " <td>0.4439</td>\n", + " <td>-0.5099</td>\n", + " <td>...</td>\n", + " <td>-0.2276</td>\n", + " <td>-0.2289</td>\n", + " <td>0.0521</td>\n", + " <td>-1</td>\n", + " <td>1.0317</td>\n", + " <td>-0.1473</td>\n", + " <td>-0.1517</td>\n", + " <td>0.9384</td>\n", + " <td>-0.3165</td>\n", + " <td>0.6239</td>\n", + " </tr>\n", + " <tr>\n", + " <th>371</th>\n", + " <td>-0.2393</td>\n", + " <td>-0.4475</td>\n", + " <td>0</td>\n", + " <td>0.4772</td>\n", + " <td>2.9612</td>\n", + " <td>-0.7799</td>\n", + " <td>-0.1244</td>\n", + " <td>-0.1693</td>\n", + " <td>0.5778</td>\n", + " <td>1.7607</td>\n", + " <td>...</td>\n", + " <td>-0.2276</td>\n", + " <td>9.4098</td>\n", + " <td>-0.5443</td>\n", + " <td>0</td>\n", + " <td>0.2992</td>\n", + " <td>-0.5451</td>\n", + " <td>-0.2456</td>\n", + " <td>0.8898</td>\n", + " <td>-0.5781</td>\n", + " <td>-0.3899</td>\n", + " </tr>\n", + " <tr>\n", + " <th>372</th>\n", + " <td>-0.1936</td>\n", + " <td>-0.2281</td>\n", + " <td>0</td>\n", + " <td>-0.4124</td>\n", + " <td>-0.1873</td>\n", + " <td>-0.1200</td>\n", + " <td>-0.1244</td>\n", + " <td>-0.0326</td>\n", + " <td>-0.8786</td>\n", + " <td>-0.3912</td>\n", + " <td>...</td>\n", + " <td>-0.2276</td>\n", + " <td>-0.2570</td>\n", + " <td>-0.3810</td>\n", + " <td>-1</td>\n", + " <td>-0.6399</td>\n", + " <td>-0.9128</td>\n", + " <td>0.3367</td>\n", + " <td>-0.4686</td>\n", + " <td>0.8995</td>\n", + " <td>1.3522</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "<p>373 rows × 347 columns</p>\n", + "</div>" + ], + "text/plain": [ + " CXCL14_rnaseq FGF1_rnaseq IFNA8_cnv ADM_rnaseq LTBP2_rnaseq \\\n", + "0 -0.1170 -0.2221 1 -0.5126 -0.3289 \n", + "1 -0.2330 -0.4343 -1 -0.2381 -0.4799 \n", + "2 -0.1384 -0.1597 -1 -0.1521 -0.3348 \n", + "3 -0.1624 -0.3463 -1 0.0272 -0.7623 \n", + "4 -0.2346 -0.4090 -1 -0.2078 0.5702 \n", + ".. ... ... ... ... ... \n", + "368 -0.2417 10.1423 -1 -0.5456 0.8742 \n", + "369 -0.2412 1.3253 1 -0.5680 1.0719 \n", + "370 -0.2396 0.0435 0 -0.3610 3.1965 \n", + "371 -0.2393 -0.4475 0 0.4772 2.9612 \n", + "372 -0.1936 -0.2281 0 -0.4124 -0.1873 \n", + "\n", + " CCL28_rnaseq IFNA7_rnaseq GH2_rnaseq AIMP1_rnaseq DEFB1_rnaseq ... \\\n", + "0 -0.7331 -0.1244 -0.1693 0.5942 -0.4707 ... \n", + "1 -0.0520 -0.1244 -0.1693 1.1854 -0.4820 ... \n", + "2 -0.5310 -0.1244 -0.1693 0.3889 -0.3607 ... \n", + "3 0.8196 -0.1244 -0.1693 -0.0416 0.1661 ... \n", + "4 -0.4219 -0.1244 0.5257 -0.9790 0.3938 ... \n", + ".. ... ... ... ... ... ... \n", + "368 -0.1822 -0.1244 -0.1693 -1.2395 -0.5125 ... \n", + "369 -0.1707 -0.1244 -0.1693 -1.6694 -0.4528 ... \n", + "370 1.3670 -0.1244 -0.1693 0.4439 -0.5099 ... \n", + "371 -0.7799 -0.1244 -0.1693 0.5778 1.7607 ... \n", + "372 -0.1200 -0.1244 -0.0326 -0.8786 -0.3912 ... \n", + "\n", + " NPPB_rnaseq CCL27_rnaseq FASLG_rnaseq FGF20_cnv FAM3C_rnaseq \\\n", + "0 -0.2276 1.2033 0.9826 -1 -0.6161 \n", + "1 -0.2276 -0.2946 -0.5443 -1 -0.3499 \n", + "2 3.4177 -0.2946 -0.5320 0 0.4581 \n", + "3 -0.2276 -0.1020 -0.4682 -1 -0.4391 \n", + "4 -0.2276 -0.1035 -0.4688 -1 1.2596 \n", + ".. ... ... ... ... ... \n", + "368 -0.2276 -0.2946 0.0777 0 -0.8242 \n", + "369 0.5679 -0.2661 1.0215 -2 -0.5327 \n", + "370 -0.2276 -0.2289 0.0521 -1 1.0317 \n", + "371 -0.2276 9.4098 -0.5443 0 0.2992 \n", + "372 -0.2276 -0.2570 -0.3810 -1 -0.6399 \n", + "\n", + " IL18_rnaseq GDF10_rnaseq MYDGF_rnaseq IL10_rnaseq IFNW1_rnaseq \n", + "0 -0.5643 -0.2165 -0.2836 0.9991 -0.3899 \n", + "1 -0.7958 -0.3140 -0.3359 -0.4865 -0.3899 \n", + "2 -0.6179 -0.2107 0.2751 -0.5108 1.0629 \n", + "3 -0.7275 -0.2876 -0.4696 -0.6248 -0.3899 \n", + "4 -0.5807 0.4108 0.1801 -0.6086 -0.3899 \n", + ".. ... ... ... ... ... \n", + "368 -0.6727 0.1938 0.9210 0.4479 -0.3899 \n", + "369 0.3335 -0.1730 0.0147 0.6012 2.2526 \n", + "370 -0.1473 -0.1517 0.9384 -0.3165 0.6239 \n", + "371 -0.5451 -0.2456 0.8898 -0.5781 -0.3899 \n", + "372 -0.9128 0.3367 -0.4686 0.8995 1.3522 \n", + "\n", + "[373 rows x 347 columns]" + ] + }, + "execution_count": 88, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "genomic_features[series_intersecdef series_intersection(s1, s2):\n", + " return pd.Series(list(set(s1) & set(s2)))\n", + "tion(sig, genomic_features.columns)]" + ] + }, + { + "cell_type": "code", + "execution_count": 84, + "metadata": {}, + "outputs": [], + "source": [ + "def series_intersection(s1, s2):\n", + " return pd.Series(list(set(s1) & set(s2)))\n" + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "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>NDUFS5_cnv</th>\n", + " <th>MACF1_cnv</th>\n", + " <th>RNA5SP44_cnv</th>\n", + " <th>KIAA0754_cnv</th>\n", + " <th>BMP8A_cnv</th>\n", + " <th>PABPC4_cnv</th>\n", + " <th>SNORA55_cnv</th>\n", + " <th>HEYL_cnv</th>\n", + " <th>HPCAL4_cnv</th>\n", + " <th>NT5C1A_cnv</th>\n", + " <th>...</th>\n", + " <th>ZWINT_rnaseq</th>\n", + " <th>ZXDA_rnaseq</th>\n", + " <th>ZXDB_rnaseq</th>\n", + " <th>ZXDC_rnaseq</th>\n", + " <th>ZYG11A_rnaseq</th>\n", + " <th>ZYG11B_rnaseq</th>\n", + " <th>ZYX_rnaseq</th>\n", + " <th>ZZEF1_rnaseq</th>\n", + " <th>ZZZ3_rnaseq</th>\n", + " <th>TPTEP1_rnaseq</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>0</th>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>-1</td>\n", + " <td>...</td>\n", + " <td>-0.8388</td>\n", + " <td>4.1375</td>\n", + " <td>3.9664</td>\n", + " <td>1.8437</td>\n", + " <td>-0.3959</td>\n", + " <td>-0.2561</td>\n", + " <td>-0.2866</td>\n", + " <td>1.8770</td>\n", + " <td>-0.3179</td>\n", + " <td>-0.3633</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1</th>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>...</td>\n", + " <td>-0.1083</td>\n", + " <td>0.3393</td>\n", + " <td>0.2769</td>\n", + " <td>1.7320</td>\n", + " <td>-0.0975</td>\n", + " <td>2.6955</td>\n", + " <td>-0.6741</td>\n", + " <td>1.0323</td>\n", + " <td>1.2766</td>\n", + " <td>-0.3982</td>\n", + " </tr>\n", + " <tr>\n", + " <th>2</th>\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>0</td>\n", + " <td>...</td>\n", + " <td>-0.4155</td>\n", + " <td>1.6846</td>\n", + " <td>0.7711</td>\n", + " <td>-0.3061</td>\n", + " <td>-0.5016</td>\n", + " <td>2.8548</td>\n", + " <td>-0.6171</td>\n", + " <td>-0.8608</td>\n", + " <td>-0.0486</td>\n", + " <td>-0.3962</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3</th>\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>0</td>\n", + " <td>...</td>\n", + " <td>-0.8143</td>\n", + " <td>0.8344</td>\n", + " <td>1.5075</td>\n", + " <td>3.6068</td>\n", + " <td>-0.5004</td>\n", + " <td>-0.0747</td>\n", + " <td>-0.2185</td>\n", + " <td>-0.4379</td>\n", + " <td>1.6913</td>\n", + " <td>1.7748</td>\n", + " </tr>\n", + " <tr>\n", + " <th>4</th>\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>0</td>\n", + " <td>...</td>\n", + " <td>0.0983</td>\n", + " <td>-0.7908</td>\n", + " <td>-0.0053</td>\n", + " <td>-0.0643</td>\n", + " <td>-0.3706</td>\n", + " <td>0.3870</td>\n", + " <td>-0.5589</td>\n", + " <td>-0.5979</td>\n", + " <td>0.0047</td>\n", + " <td>-0.3548</td>\n", + " </tr>\n", + " <tr>\n", + " <th>...</th>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " </tr>\n", + " <tr>\n", + " <th>368</th>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>2</td>\n", + " <td>...</td>\n", + " <td>-0.0291</td>\n", + " <td>-0.1058</td>\n", + " <td>-0.6721</td>\n", + " <td>0.2802</td>\n", + " <td>1.9504</td>\n", + " <td>-0.8784</td>\n", + " <td>0.9506</td>\n", + " <td>0.0607</td>\n", + " <td>1.1883</td>\n", + " <td>-0.3521</td>\n", + " </tr>\n", + " <tr>\n", + " <th>369</th>\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>0</td>\n", + " <td>...</td>\n", + " <td>0.0497</td>\n", + " <td>0.3673</td>\n", + " <td>-0.2208</td>\n", + " <td>0.3034</td>\n", + " <td>3.2580</td>\n", + " <td>-0.2089</td>\n", + " <td>1.6053</td>\n", + " <td>-0.8746</td>\n", + " <td>-0.4491</td>\n", + " <td>-0.3450</td>\n", + " </tr>\n", + " <tr>\n", + " <th>370</th>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>...</td>\n", + " <td>0.3822</td>\n", + " <td>-0.7003</td>\n", + " <td>-0.7661</td>\n", + " <td>-1.7035</td>\n", + " <td>-0.5423</td>\n", + " <td>-0.3488</td>\n", + " <td>1.3713</td>\n", + " <td>-0.4365</td>\n", + " <td>2.3456</td>\n", + " <td>-0.3866</td>\n", + " </tr>\n", + " <tr>\n", + " <th>371</th>\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>0</td>\n", + " <td>...</td>\n", + " <td>-0.6853</td>\n", + " <td>-1.0240</td>\n", + " <td>-1.2890</td>\n", + " <td>-1.5666</td>\n", + " <td>-0.1270</td>\n", + " <td>-1.4662</td>\n", + " <td>0.3981</td>\n", + " <td>-0.5976</td>\n", + " <td>-1.3822</td>\n", + " <td>-0.4157</td>\n", + " </tr>\n", + " <tr>\n", + " <th>372</th>\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>0</td>\n", + " <td>...</td>\n", + " <td>0.0517</td>\n", + " <td>-0.3570</td>\n", + " <td>-0.4843</td>\n", + " <td>-0.3792</td>\n", + " <td>-0.1964</td>\n", + " <td>0.4200</td>\n", + " <td>3.2547</td>\n", + " <td>-0.1232</td>\n", + " <td>3.4519</td>\n", + " <td>-0.1962</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "<p>373 rows × 20395 columns</p>\n", + "</div>" + ], + "text/plain": [ + " NDUFS5_cnv MACF1_cnv RNA5SP44_cnv KIAA0754_cnv BMP8A_cnv PABPC4_cnv \\\n", + "0 -1 -1 -1 -1 -1 -1 \n", + "1 2 2 2 2 2 2 \n", + "2 0 0 0 0 0 0 \n", + "3 0 0 0 0 0 0 \n", + "4 0 0 0 0 0 0 \n", + ".. ... ... ... ... ... ... \n", + "368 2 2 2 2 2 2 \n", + "369 0 0 0 0 0 0 \n", + "370 1 1 1 1 1 1 \n", + "371 0 0 0 0 0 0 \n", + "372 0 0 0 0 0 0 \n", + "\n", + " SNORA55_cnv HEYL_cnv HPCAL4_cnv NT5C1A_cnv ... ZWINT_rnaseq \\\n", + "0 -1 -1 -1 -1 ... -0.8388 \n", + "1 2 2 2 2 ... -0.1083 \n", + "2 0 0 0 0 ... -0.4155 \n", + "3 0 0 0 0 ... -0.8143 \n", + "4 0 0 0 0 ... 0.0983 \n", + ".. ... ... ... ... ... ... \n", + "368 2 2 2 2 ... -0.0291 \n", + "369 0 0 0 0 ... 0.0497 \n", + "370 1 1 1 1 ... 0.3822 \n", + "371 0 0 0 0 ... -0.6853 \n", + "372 0 0 0 0 ... 0.0517 \n", + "\n", + " ZXDA_rnaseq ZXDB_rnaseq ZXDC_rnaseq ZYG11A_rnaseq ZYG11B_rnaseq \\\n", + "0 4.1375 3.9664 1.8437 -0.3959 -0.2561 \n", + "1 0.3393 0.2769 1.7320 -0.0975 2.6955 \n", + "2 1.6846 0.7711 -0.3061 -0.5016 2.8548 \n", + "3 0.8344 1.5075 3.6068 -0.5004 -0.0747 \n", + "4 -0.7908 -0.0053 -0.0643 -0.3706 0.3870 \n", + ".. ... ... ... ... ... \n", + "368 -0.1058 -0.6721 0.2802 1.9504 -0.8784 \n", + "369 0.3673 -0.2208 0.3034 3.2580 -0.2089 \n", + "370 -0.7003 -0.7661 -1.7035 -0.5423 -0.3488 \n", + "371 -1.0240 -1.2890 -1.5666 -0.1270 -1.4662 \n", + "372 -0.3570 -0.4843 -0.3792 -0.1964 0.4200 \n", + "\n", + " ZYX_rnaseq ZZEF1_rnaseq ZZZ3_rnaseq TPTEP1_rnaseq \n", + "0 -0.2866 1.8770 -0.3179 -0.3633 \n", + "1 -0.6741 1.0323 1.2766 -0.3982 \n", + "2 -0.6171 -0.8608 -0.0486 -0.3962 \n", + "3 -0.2185 -0.4379 1.6913 1.7748 \n", + "4 -0.5589 -0.5979 0.0047 -0.3548 \n", + ".. ... ... ... ... \n", + "368 0.9506 0.0607 1.1883 -0.3521 \n", + "369 1.6053 -0.8746 -0.4491 -0.3450 \n", + "370 1.3713 -0.4365 2.3456 -0.3866 \n", + "371 0.3981 -0.5976 -1.3822 -0.4157 \n", + "372 3.2547 -0.1232 3.4519 -0.1962 \n", + "\n", + "[373 rows x 20395 columns]" + ] + }, + "execution_count": 68, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "genomic_features" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [], + "source": [ + "if 'case_id' not in slide_data:\n", + " slide_data.index = slide_data.index.str[:12]\n", + " slide_data['case_id'] = slide_data.index\n", + " slide_data = slide_data.reset_index(drop=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [], + "source": [ + "new_cols = list(slide_data.columns[-2:]) + list(slide_data.columns[:-2])\n", + "slide_data = slide_data[new_cols]" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "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>ZZZ3_rnaseq</th>\n", + " <th>TPTEP1_rnaseq</th>\n", + " <th>slide_id</th>\n", + " <th>site</th>\n", + " <th>is_female</th>\n", + " <th>oncotree_code</th>\n", + " <th>age</th>\n", + " <th>survival_months</th>\n", + " <th>censorship</th>\n", + " <th>train</th>\n", + " <th>...</th>\n", + " <th>ZW10_rnaseq</th>\n", + " <th>ZWILCH_rnaseq</th>\n", + " <th>ZWINT_rnaseq</th>\n", + " <th>ZXDA_rnaseq</th>\n", + " <th>ZXDB_rnaseq</th>\n", + " <th>ZXDC_rnaseq</th>\n", + " <th>ZYG11A_rnaseq</th>\n", + " <th>ZYG11B_rnaseq</th>\n", + " <th>ZYX_rnaseq</th>\n", + " <th>ZZEF1_rnaseq</th>\n", + " </tr>\n", + " <tr>\n", + " <th>case_id</th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " <th></th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>TCGA-2F-A9KO</th>\n", + " <td>-0.3179</td>\n", + " <td>-0.3633</td>\n", + " <td>TCGA-2F-A9KO-01Z-00-DX1.195576CF-B739-4BD9-B15...</td>\n", + " <td>2F</td>\n", + " <td>0</td>\n", + " <td>BLCA</td>\n", + " <td>63</td>\n", + " <td>24.11</td>\n", + " <td>0</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-0.7172</td>\n", + " <td>0.7409</td>\n", + " <td>-0.8388</td>\n", + " <td>4.1375</td>\n", + " <td>3.9664</td>\n", + " <td>1.8437</td>\n", + " <td>-0.3959</td>\n", + " <td>-0.2561</td>\n", + " <td>-0.2866</td>\n", + " <td>1.8770</td>\n", + " </tr>\n", + " <tr>\n", + " <th>TCGA-2F-A9KP</th>\n", + " <td>1.2766</td>\n", + " <td>-0.3982</td>\n", + " <td>TCGA-2F-A9KP-01Z-00-DX1.3CDF534E-958F-4467-AA7...</td>\n", + " <td>2F</td>\n", + " <td>0</td>\n", + " <td>BLCA</td>\n", + " <td>66</td>\n", + " <td>11.96</td>\n", + " <td>0</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>0.6373</td>\n", + " <td>0.8559</td>\n", + " <td>-0.1083</td>\n", + " <td>0.3393</td>\n", + " <td>0.2769</td>\n", + " <td>1.7320</td>\n", + " <td>-0.0975</td>\n", + " <td>2.6955</td>\n", + " <td>-0.6741</td>\n", + " <td>1.0323</td>\n", + " </tr>\n", + " <tr>\n", + " <th>TCGA-2F-A9KP</th>\n", + " <td>1.2766</td>\n", + " <td>-0.3982</td>\n", + " <td>TCGA-2F-A9KP-01Z-00-DX2.718C82A3-252B-498E-BFB...</td>\n", + " <td>2F</td>\n", + " <td>0</td>\n", + " <td>BLCA</td>\n", + " <td>66</td>\n", + " <td>11.96</td>\n", + " <td>0</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>0.6373</td>\n", + " <td>0.8559</td>\n", + " <td>-0.1083</td>\n", + " <td>0.3393</td>\n", + " <td>0.2769</td>\n", + " <td>1.7320</td>\n", + " <td>-0.0975</td>\n", + " <td>2.6955</td>\n", + " <td>-0.6741</td>\n", + " <td>1.0323</td>\n", + " </tr>\n", + " <tr>\n", + " <th>TCGA-2F-A9KQ</th>\n", + " <td>-0.0486</td>\n", + " <td>-0.3962</td>\n", + " <td>TCGA-2F-A9KQ-01Z-00-DX1.1C8CB2DD-5CC6-4E99-A0F...</td>\n", + " <td>2F</td>\n", + " <td>0</td>\n", + " <td>BLCA</td>\n", + " <td>69</td>\n", + " <td>94.81</td>\n", + " <td>1</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-0.5676</td>\n", + " <td>-0.0621</td>\n", + " <td>-0.4155</td>\n", + " <td>1.6846</td>\n", + " <td>0.7711</td>\n", + " <td>-0.3061</td>\n", + " <td>-0.5016</td>\n", + " <td>2.8548</td>\n", + " <td>-0.6171</td>\n", + " <td>-0.8608</td>\n", + " </tr>\n", + " <tr>\n", + " <th>TCGA-2F-A9KR</th>\n", + " <td>1.6913</td>\n", + " <td>1.7748</td>\n", + " <td>TCGA-2F-A9KR-01Z-00-DX1.D6A4BD2D-18F3-4FA6-827...</td>\n", + " <td>2F</td>\n", + " <td>1</td>\n", + " <td>BLCA</td>\n", + " <td>59</td>\n", + " <td>104.57</td>\n", + " <td>0</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-1.3825</td>\n", + " <td>0.3550</td>\n", + " <td>-0.8143</td>\n", + " <td>0.8344</td>\n", + " <td>1.5075</td>\n", + " <td>3.6068</td>\n", + " <td>-0.5004</td>\n", + " <td>-0.0747</td>\n", + " <td>-0.2185</td>\n", + " <td>-0.4379</td>\n", + " </tr>\n", + " <tr>\n", + " <th>...</th>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " <td>...</td>\n", + " </tr>\n", + " <tr>\n", + " <th>TCGA-ZF-AA54</th>\n", + " <td>1.1883</td>\n", + " <td>-0.3521</td>\n", + " <td>TCGA-ZF-AA54-01Z-00-DX1.9118BB51-333A-4257-A79...</td>\n", + " <td>ZF</td>\n", + " <td>0</td>\n", + " <td>BLCA</td>\n", + " <td>71</td>\n", + " <td>19.38</td>\n", + " <td>0</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-0.0898</td>\n", + " <td>2.1092</td>\n", + " <td>-0.0291</td>\n", + " <td>-0.1058</td>\n", + " <td>-0.6721</td>\n", + " <td>0.2802</td>\n", + " <td>1.9504</td>\n", + " <td>-0.8784</td>\n", + " <td>0.9506</td>\n", + " <td>0.0607</td>\n", + " </tr>\n", + " <tr>\n", + " <th>TCGA-ZF-AA58</th>\n", + " <td>-0.4491</td>\n", + " <td>-0.3450</td>\n", + " <td>TCGA-ZF-AA58-01Z-00-DX1.85C3611E-11FA-4AAE-B88...</td>\n", + " <td>ZF</td>\n", + " <td>1</td>\n", + " <td>BLCA</td>\n", + " <td>61</td>\n", + " <td>54.17</td>\n", + " <td>1</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-0.2075</td>\n", + " <td>-0.0617</td>\n", + " <td>0.0497</td>\n", + " <td>0.3673</td>\n", + " <td>-0.2208</td>\n", + " <td>0.3034</td>\n", + " <td>3.2580</td>\n", + " <td>-0.2089</td>\n", + " <td>1.6053</td>\n", + " <td>-0.8746</td>\n", + " </tr>\n", + " <tr>\n", + " <th>TCGA-ZF-AA5H</th>\n", + " <td>2.3456</td>\n", + " <td>-0.3866</td>\n", + " <td>TCGA-ZF-AA5H-01Z-00-DX1.2B5DF00E-E0FD-4C58-A82...</td>\n", + " <td>ZF</td>\n", + " <td>1</td>\n", + " <td>BLCA</td>\n", + " <td>60</td>\n", + " <td>29.47</td>\n", + " <td>1</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-1.4118</td>\n", + " <td>-0.1236</td>\n", + " <td>0.3822</td>\n", + " <td>-0.7003</td>\n", + " <td>-0.7661</td>\n", + " <td>-1.7035</td>\n", + " <td>-0.5423</td>\n", + " <td>-0.3488</td>\n", + " <td>1.3713</td>\n", + " <td>-0.4365</td>\n", + " </tr>\n", + " <tr>\n", + " <th>TCGA-ZF-AA5N</th>\n", + " <td>-1.3822</td>\n", + " <td>-0.4157</td>\n", + " <td>TCGA-ZF-AA5N-01Z-00-DX1.A207E3EE-CC7D-4267-A77...</td>\n", + " <td>ZF</td>\n", + " <td>1</td>\n", + " <td>BLCA</td>\n", + " <td>62</td>\n", + " <td>5.52</td>\n", + " <td>0</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-0.1733</td>\n", + " <td>-0.2397</td>\n", + " <td>-0.6853</td>\n", + " <td>-1.0240</td>\n", + " <td>-1.2890</td>\n", + " <td>-1.5666</td>\n", + " <td>-0.1270</td>\n", + " <td>-1.4662</td>\n", + " <td>0.3981</td>\n", + " <td>-0.5976</td>\n", + " </tr>\n", + " <tr>\n", + " <th>TCGA-ZF-AA5P</th>\n", + " <td>3.4519</td>\n", + " <td>-0.1962</td>\n", + " <td>TCGA-ZF-AA5P-01Z-00-DX1.B91697A2-A186-4E67-A81...</td>\n", + " <td>ZF</td>\n", + " <td>0</td>\n", + " <td>BLCA</td>\n", + " <td>65</td>\n", + " <td>12.22</td>\n", + " <td>1</td>\n", + " <td>1.0</td>\n", + " <td>...</td>\n", + " <td>-1.1056</td>\n", + " <td>-0.6634</td>\n", + " <td>0.0517</td>\n", + " <td>-0.3570</td>\n", + " <td>-0.4843</td>\n", + " <td>-0.3792</td>\n", + " <td>-0.1964</td>\n", + " <td>0.4200</td>\n", + " <td>3.2547</td>\n", + " <td>-0.1232</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "<p>437 rows × 20403 columns</p>\n", + "</div>" + ], + "text/plain": [ + " ZZZ3_rnaseq TPTEP1_rnaseq \\\n", + "case_id \n", + "TCGA-2F-A9KO -0.3179 -0.3633 \n", + "TCGA-2F-A9KP 1.2766 -0.3982 \n", + "TCGA-2F-A9KP 1.2766 -0.3982 \n", + "TCGA-2F-A9KQ -0.0486 -0.3962 \n", + "TCGA-2F-A9KR 1.6913 1.7748 \n", + "... ... ... \n", + "TCGA-ZF-AA54 1.1883 -0.3521 \n", + "TCGA-ZF-AA58 -0.4491 -0.3450 \n", + "TCGA-ZF-AA5H 2.3456 -0.3866 \n", + "TCGA-ZF-AA5N -1.3822 -0.4157 \n", + "TCGA-ZF-AA5P 3.4519 -0.1962 \n", + "\n", + " slide_id site \\\n", + "case_id \n", + "TCGA-2F-A9KO TCGA-2F-A9KO-01Z-00-DX1.195576CF-B739-4BD9-B15... 2F \n", + "TCGA-2F-A9KP TCGA-2F-A9KP-01Z-00-DX1.3CDF534E-958F-4467-AA7... 2F \n", + "TCGA-2F-A9KP TCGA-2F-A9KP-01Z-00-DX2.718C82A3-252B-498E-BFB... 2F \n", + "TCGA-2F-A9KQ TCGA-2F-A9KQ-01Z-00-DX1.1C8CB2DD-5CC6-4E99-A0F... 2F \n", + "TCGA-2F-A9KR TCGA-2F-A9KR-01Z-00-DX1.D6A4BD2D-18F3-4FA6-827... 2F \n", + "... ... ... \n", + "TCGA-ZF-AA54 TCGA-ZF-AA54-01Z-00-DX1.9118BB51-333A-4257-A79... ZF \n", + "TCGA-ZF-AA58 TCGA-ZF-AA58-01Z-00-DX1.85C3611E-11FA-4AAE-B88... ZF \n", + "TCGA-ZF-AA5H TCGA-ZF-AA5H-01Z-00-DX1.2B5DF00E-E0FD-4C58-A82... ZF \n", + "TCGA-ZF-AA5N TCGA-ZF-AA5N-01Z-00-DX1.A207E3EE-CC7D-4267-A77... ZF \n", + "TCGA-ZF-AA5P TCGA-ZF-AA5P-01Z-00-DX1.B91697A2-A186-4E67-A81... ZF \n", + "\n", + " is_female oncotree_code age survival_months censorship \\\n", + "case_id \n", + "TCGA-2F-A9KO 0 BLCA 63 24.11 0 \n", + "TCGA-2F-A9KP 0 BLCA 66 11.96 0 \n", + "TCGA-2F-A9KP 0 BLCA 66 11.96 0 \n", + "TCGA-2F-A9KQ 0 BLCA 69 94.81 1 \n", + "TCGA-2F-A9KR 1 BLCA 59 104.57 0 \n", + "... ... ... ... ... ... \n", + "TCGA-ZF-AA54 0 BLCA 71 19.38 0 \n", + "TCGA-ZF-AA58 1 BLCA 61 54.17 1 \n", + "TCGA-ZF-AA5H 1 BLCA 60 29.47 1 \n", + "TCGA-ZF-AA5N 1 BLCA 62 5.52 0 \n", + "TCGA-ZF-AA5P 0 BLCA 65 12.22 1 \n", + "\n", + " train ... ZW10_rnaseq ZWILCH_rnaseq ZWINT_rnaseq \\\n", + "case_id ... \n", + "TCGA-2F-A9KO 1.0 ... -0.7172 0.7409 -0.8388 \n", + "TCGA-2F-A9KP 1.0 ... 0.6373 0.8559 -0.1083 \n", + "TCGA-2F-A9KP 1.0 ... 0.6373 0.8559 -0.1083 \n", + "TCGA-2F-A9KQ 1.0 ... -0.5676 -0.0621 -0.4155 \n", + "TCGA-2F-A9KR 1.0 ... -1.3825 0.3550 -0.8143 \n", + "... ... ... ... ... ... \n", + "TCGA-ZF-AA54 1.0 ... -0.0898 2.1092 -0.0291 \n", + "TCGA-ZF-AA58 1.0 ... -0.2075 -0.0617 0.0497 \n", + "TCGA-ZF-AA5H 1.0 ... -1.4118 -0.1236 0.3822 \n", + "TCGA-ZF-AA5N 1.0 ... -0.1733 -0.2397 -0.6853 \n", + "TCGA-ZF-AA5P 1.0 ... -1.1056 -0.6634 0.0517 \n", + "\n", + " ZXDA_rnaseq ZXDB_rnaseq ZXDC_rnaseq ZYG11A_rnaseq \\\n", + "case_id \n", + "TCGA-2F-A9KO 4.1375 3.9664 1.8437 -0.3959 \n", + "TCGA-2F-A9KP 0.3393 0.2769 1.7320 -0.0975 \n", + "TCGA-2F-A9KP 0.3393 0.2769 1.7320 -0.0975 \n", + "TCGA-2F-A9KQ 1.6846 0.7711 -0.3061 -0.5016 \n", + "TCGA-2F-A9KR 0.8344 1.5075 3.6068 -0.5004 \n", + "... ... ... ... ... \n", + "TCGA-ZF-AA54 -0.1058 -0.6721 0.2802 1.9504 \n", + "TCGA-ZF-AA58 0.3673 -0.2208 0.3034 3.2580 \n", + "TCGA-ZF-AA5H -0.7003 -0.7661 -1.7035 -0.5423 \n", + "TCGA-ZF-AA5N -1.0240 -1.2890 -1.5666 -0.1270 \n", + "TCGA-ZF-AA5P -0.3570 -0.4843 -0.3792 -0.1964 \n", + "\n", + " ZYG11B_rnaseq ZYX_rnaseq ZZEF1_rnaseq \n", + "case_id \n", + "TCGA-2F-A9KO -0.2561 -0.2866 1.8770 \n", + "TCGA-2F-A9KP 2.6955 -0.6741 1.0323 \n", + "TCGA-2F-A9KP 2.6955 -0.6741 1.0323 \n", + "TCGA-2F-A9KQ 2.8548 -0.6171 -0.8608 \n", + "TCGA-2F-A9KR -0.0747 -0.2185 -0.4379 \n", + "... ... ... ... \n", + "TCGA-ZF-AA54 -0.8784 0.9506 0.0607 \n", + "TCGA-ZF-AA58 -0.2089 1.6053 -0.8746 \n", + "TCGA-ZF-AA5H -0.3488 1.3713 -0.4365 \n", + "TCGA-ZF-AA5N -1.4662 0.3981 -0.5976 \n", + "TCGA-ZF-AA5P 0.4200 3.2547 -0.1232 \n", + "\n", + "[437 rows x 20403 columns]" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "slide_data" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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": "3.7.7" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +}