initial commit

LindoNkambule · Aug 10, 2019 · a022abf · a022abf
1 parent 448b2de
commit a022abf
Showing 1 changed file with 106 additions and 0 deletions.
diff --git a/VCFCompare.ipynb b/VCFCompare.ipynb
@@ -0,0 +1,106 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Total Truth VCF records: 4358\n",
+      "Non-reference VCF records: 4358\n",
+      "Total Query VCF records: 7494\n",
+      "Non-reference VCF records: 4495\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/anaconda3/lib/python3.6/site-packages/allel/io/vcf_read.py:1741: UserWarning: invalid INFO header: '##INFO=<ID=VDB,Number=1,Type=Float,Description=\"Variant Distance Bias for filtering splice-site artefacts in RNA-seq data (bigger is better)\",Version=\"3\">\\n'\n",
+      "  warnings.warn('invalid INFO header: %r' % header)\n"
+     ]
+    }
+   ],
+   "source": [
+    "#!/usr/local/bin python\n",
+    "import sys\n",
+    "import pandas as pd\n",
+    "import allel #pip install scikit-allel to install this module for analysis of large scale genetic variation data\n",
+    "import csv\n",
+    "\n",
+    "golden_vcf = allel.vcf_to_dataframe(\"bcftools_variants.vcf\", ['variants/CHROM', 'variants/POS', 'variants/REF', 'variants/ALT', 'QUAL'], alt_number=1) # Storing the information in the VCF file into a dataframe\n",
+    "query_vcf = allel.vcf_to_dataframe(\"freeebayes_variants.vcf\", ['variants/CHROM', 'variants/POS', 'variants/REF', 'variants/ALT', 'QUAL'], alt_number=1)\n",
+    "golden_variants_list = golden_vcf.values.tolist() #Each variant info will be saved onto a list, creating a list of list\n",
+    "query_variants_list = query_vcf.values.tolist()\n",
+    "\n",
+    "# for list in query_variants_list:\n",
+    "#     print (list[4])\n",
+    "\n",
+    "header = ['TRUTH.TOTAL', 'TP', 'FP', 'FN', 'QUERY.TOTAL', 'Recall', 'Precision']\n",
+    "list = []\n",
+    "\n",
+    "#Totals\n",
+    "Truth_Total = len(golden_variants_list)\n",
+    "print (\"Total Truth VCF records: \" + str(Truth_Total))\n",
+    "Truth_Pass_Total = len([x for x in golden_variants_list if x[4] > 2])\n",
+    "print (\"Non-reference VCF records: \" + str(Truth_Pass_Total))\n",
+    "Query_Total = len(query_variants_list)\n",
+    "print (\"Total Query VCF records: \" + str(Query_Total))\n",
+    "Query_Pass_Total = len([x for x in query_variants_list if x[4] > 0.003])\n",
+    "print (\"Non-reference VCF records: \" + str(Query_Pass_Total))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "4\n",
+      "4\n",
+      "5\n"
+     ]
+    }
+   ],
+   "source": [
+    "a = [[1, 3, 4], [2, 4, 4], [3, 4, 5]]\n",
+    "for list in a:\n",
+    "    print (list[2])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.6.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}