fig updates

Author: panushri25

src/evaluation/figure_notebooks/figure_6/final_figures/format_af_caqtls-Copy1.ipynb

@@ -11,13 +11,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 146,
    "metadata": {},
    "outputs": [],
    "source": [
     "data = pd.read_csv(\"all_caqtls.scores.tsv\", sep=\"\\t\")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 147,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[['chr', 'pos', 'allele1', 'allele2', \"rsid\"]].to_csv(\"/mnt/lab_data2/anusri/enformer/eu_caqtls/afgr_all.tsv\", sep=\"\\t\", header=True, index=False)\n"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 3,

src/evaluation/figure_notebooks/figure_6/final_figures/format_cagi.ipynb

@@ -568,28 +568,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 215,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "challenge_HBG1.tsv\n",
-      "challenge_PKLR.tsv\n",
-      "challenge_MYCrs6983267.tsv\n",
-      "challenge_TERT-GBM.tsv\n",
-      "challenge_MSMB.tsv\n",
-      "challenge_F9.tsv\n",
-      "challenge_IRF6.tsv\n",
-      "challenge_HNF4A.tsv\n",
-      "challenge_IRF4.tsv\n",
-      "challenge_SORT1.tsv\n",
-      "challenge_ZFAND3.tsv\n",
-      "challenge_HBB.tsv\n",
-      "challenge_LDLR.tsv\n",
-      "challenge_TERT-HEK293T.tsv\n",
-      "challenge_GP1BB.tsv\n"
+     "ename": "NameError",
+     "evalue": "name 'dirs' 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-1-59d188bd8e8a>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0menf_dfs\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----> 2\u001b[0;31m \u001b[0;32mfor\u001b[0m \u001b[0midir\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdirs\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      3\u001b[0m     \u001b[0midir\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0midir\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[0mifile\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0modir\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0midir\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misfile\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mifile\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 'dirs' is not defined"
      ]
     }
    ],
@@ -626,6 +616,7 @@
     "            \n",
     "            enf_f = \"/mnt/lab_data2/anusri/chrombpnet/results/variant_data/CAGI/enformer_preds/alldata/\"+idir.replace(\"challenge_\",\"\").replace(\".tsv\",\"\")+\".ZigaDataLocal.csv\"\n",
     "            enf_f = pd.read_csv(enf_f, sep=\",\", header=0)\n",
+    "            print(enf_h,head(1))\n",
     "            #print(combined.drop_duplicates().shape[0], combined.shape[0])\n",
     "            #print(enf_f.head(1))\n",
     "            #assert(enf_f.shape[0] == combined.shape[0])\n",

src/evaluation/figure_notebooks/figure_6/final_figures/format_spi1_bqtls.ipynb

@@ -759,7 +759,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 56,
+   "execution_count": 73,
    "metadata": {},
    "outputs": [
     {
@@ -780,7 +780,7 @@
        "      dtype='object')"
       ]
      },
-     "execution_count": 56,
+     "execution_count": 73,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -789,6 +789,26 @@
     "snps.columns"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "4834"
+      ]
+     },
+     "execution_count": 74,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(mean_change)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 44,

src/evaluation/figure_notebooks/figure_6/final_figures_new/cagi_scoring_all.ipynb

@@ -11,7 +11,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -20,7 +20,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -232,7 +232,7 @@
        "[5 rows x 25 columns]"
       ]
      },
-     "execution_count": 33,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -243,7 +243,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -258,7 +258,7 @@
        "      dtype='object')"
       ]
      },
-     "execution_count": 34,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -269,7 +269,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [