From 92e25b997279a6ae100ed811b8f9d22110652c41 Mon Sep 17 00:00:00 2001
From: Kalin Nonchev <nonchev@thulit.cip.ifi.lmu.de>
Date: Sat, 4 Nov 2023 10:24:23 +0100
Subject: [PATCH] clean nb

---
 scripts/GettingStartedwithGnomAD_DB.ipynb | 140 ++++++----------------
 1 file changed, 35 insertions(+), 105 deletions(-)

diff --git a/scripts/GettingStartedwithGnomAD_DB.ipynb b/scripts/GettingStartedwithGnomAD_DB.ipynb
index 66229fa..2cdc5f3 100644
--- a/scripts/GettingStartedwithGnomAD_DB.ipynb
+++ b/scripts/GettingStartedwithGnomAD_DB.ipynb
@@ -2,8 +2,8 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "ac0fca47",
+   "execution_count": null,
+   "id": "d6bb7fee",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -14,7 +14,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "acdaa43f",
+   "id": "29f709fc",
    "metadata": {},
    "source": [
     "# Download SQLite preprocessed files\n",
@@ -26,44 +26,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "id": "13b2eb85",
+   "execution_count": null,
+   "id": "a4f2b492",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Starting downloading...\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "gnomad_db_wes_v4.0.sqlite3.gz?download=1: 7.31GB [12:40, 9.62MB/s]                                                                                                          \n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Starting unzipping. This can take some time...\n",
-      "Database location: test_dir/gnomad_db.sqlite3\n",
-      "Done!\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# uncomment if you actually want to download it\n",
-    "download_link = \"https://zenodo.org/records/10066310/files/gnomad_db_wes_v4.0.sqlite3.gz?download=1\"\n",
-    "output_dir = \"test_dir\" # database_location\n",
-    "gnomAD_DB.download_and_unzip(download_link, output_dir) "
+    "# download_link = \"https://zenodo.org/records/10066310/files/gnomad_db_wes_v4.0.sqlite3.gz?download=1\"\n",
+    "# output_dir = \"test_dir\" # database_location\n",
+    "# gnomAD_DB.download_and_unzip(download_link, output_dir) "
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "aab41c34",
+   "id": "fd567b25",
    "metadata": {},
    "source": [
     "# Initialize Database"
@@ -71,8 +47,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
-   "id": "dc9b3e8c",
+   "execution_count": null,
+   "id": "d31b697b",
    "metadata": {
     "tags": [
      "parameters"
@@ -86,32 +62,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
-   "id": "7f430055",
+   "execution_count": null,
+   "id": "726b2d8e",
    "metadata": {},
-   "outputs": [
-    {
-     "ename": "AssertionError",
-     "evalue": "We don't support this version: v45. Please select one fo the following ones: ['v2', 'v3', 'v4']",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mAssertionError\u001b[0m                            Traceback (most recent call last)",
-      "\u001b[0;32m/tmp/user/31932/ipykernel_1570523/790803492.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;31m# initialize database\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mdb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgnomAD_DB\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdatabase_location\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgnomad_version\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"v45\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
-      "\u001b[0;32m~/code/gnomAD_DB/gnomad_db/database.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, genodb_path, gnomad_version, parallel, cpu_count)\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;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 30\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgnomad_version\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_parse_gnomad_version\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mgnomad_version\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeys\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\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[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[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmap\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;32mlambda\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlower\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcolumns\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"base_columns\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mcolumns\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgnomad_version\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m~/code/gnomAD_DB/gnomad_db/database.py\u001b[0m in \u001b[0;36m_parse_gnomad_version\u001b[0;34m(self, gnomad_version, supported_gnomad_versions)\u001b[0m\n\u001b[1;32m    179\u001b[0m         \u001b[0mgnomad_version\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mgnomad_version\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    180\u001b[0m         \u001b[0mgnomad_version\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgnomad_version\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msplit\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;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 181\u001b[0;31m         \u001b[0;32massert\u001b[0m \u001b[0mgnomad_version\u001b[0m \u001b[0;32min\u001b[0m \u001b[0msupported_gnomad_versions\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34mf\"We don't support this version: {gnomad_version}. Please select one fo the following ones: {supported_gnomad_versions}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    182\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mgnomad_version\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    183\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mAssertionError\u001b[0m: We don't support this version: v45. Please select one fo the following ones: ['v2', 'v3', 'v4']"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# initialize database\n",
-    "db = gnomAD_DB(database_location, gnomad_version=\"v45\")"
+    "db = gnomAD_DB(database_location, gnomad_version=\"v4\")"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "a9e3006f",
+   "id": "5294a85b",
    "metadata": {},
    "source": [
     "# Insert gnomAD variants into the database from single tsv file\n",
@@ -121,7 +83,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "8def6a52",
+   "id": "0ab60f6c",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -136,7 +98,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "34dbb770",
+   "id": "28d2319d",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -146,7 +108,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "7a9243d2",
+   "id": "8a27dc55",
    "metadata": {},
    "source": [
     "# Query MAF"
@@ -155,7 +117,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "835e50b4",
+   "id": "17e08a76",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -166,7 +128,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "eb3a308d",
+   "id": "939be8c0",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -176,7 +138,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b879dad5",
+   "id": "5832ab61",
    "metadata": {},
    "source": [
     "## You can pass a dataframe with variants\n",
@@ -186,7 +148,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "36014921",
+   "id": "d07eacc3",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -196,7 +158,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a7bfea3b",
+   "id": "60403b2b",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -206,7 +168,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "0aaa8a58",
+   "id": "3d0cd436",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -216,7 +178,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "88c20646",
+   "id": "9e7b8572",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -231,7 +193,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ef74e6bd",
+   "id": "0e81620c",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -240,7 +202,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b4261ffd",
+   "id": "efeec779",
    "metadata": {},
    "source": [
     "## You can pass a single string as a variant"
@@ -248,42 +210,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "id": "084c732a",
+   "execution_count": null,
+   "id": "f6162668",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "chrom                   10\n",
-       "pos               95606780\n",
-       "ref                      A\n",
-       "alt                      C\n",
-       "filter                PASS\n",
-       "AC                     2.0\n",
-       "AN                628768.0\n",
-       "AF                0.000003\n",
-       "MQ                    60.0\n",
-       "QD                 12.1796\n",
-       "ReadPosRankSum       0.365\n",
-       "VarDP                412.0\n",
-       "AS_VQSLOD           5.5239\n",
-       "AC_grpmax              2.0\n",
-       "AN_grpmax         350092.0\n",
-       "AF_grpmax         0.000006\n",
-       "AF_eas                 0.0\n",
-       "AF_nfe            0.000006\n",
-       "AF_fin                 0.0\n",
-       "AF_afr                 0.0\n",
-       "AF_asj                 0.0\n",
-       "Name: 0, dtype: object"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "db.get_info_from_str(\"10:95606780:A>C\", \"*\")"
    ]
@@ -291,7 +221,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "e72d5071",
+   "id": "7d487510",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -300,7 +230,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b2cd63fc",
+   "id": "d85b4921",
    "metadata": {},
    "source": [
     "## You can look for the MAF scores in an interval"
@@ -309,7 +239,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "0e587bf1",
+   "id": "125170f7",
    "metadata": {},
    "outputs": [],
    "source": [