first task

task1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import libraries up front\n",
    "import json\n",
    "\n",
    "# From Table S13 in Plaisier et al., Cell Systems 2016\n",
    "# These are Entrez IDs (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3013746/)\n",
    "input = ['430', '1052', '1053', '1385', '84699', '9586', '1871', '1874', '144455', '79733', '1960', '1997', '2002', '2004', '80712', '2114', '2115', '2120', '51513', '2551', '2623', '2624', '2625', '9421', '3232', '10320', '3659', '3662', '3670', '91464', '3726', '10661', '11278', '128209', '10365', '9314', '1316', '51176', '9935', '23269', '4602', '4774', '4790', '7025', '9480', '5468', '5914', '5916', '3516', '5971', '864', '6257', '4093', '6659', '6660', '6662', '25803', '347853', '30009', '9496', '6929', '6925', '8463', '7022', '29842', '10155', '6935', '132625', '23051', '85416', '7707', '7764', '23528', '201516']\n",
    "\n",
    "# Loading JSON file\n",
    "# https://www.safaribooksonline.com/library/view/python-cookbook-3rd/9781449357337/ch06s02.html\n",
    "# Example:\n",
    "# import json\n",
    "#\n",
    "# # Reading data back\n",
    "# with open('data.json', 'r') as f:\n",
    "#      data = json.load(f)\n",
    "\n",
    "# Reading TF regulator to TF target gene relationships into Python\n",
    "# The json library we import takes care of most of the work\n",
    "with open('tfbsDb_plus_and_minus_5000_entrez.json', 'r') as f:\n",
    "     tfbsDb = json.load(f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['SOX10_HMG_full_dimeric_16_1', 'V_AP2ALPHA_01_M00469', 'V_SIX6_01_M01345', 'Pitx1.1', 'ELF1_ETS_full_monomeric_12_1']\n"
     ]
    }
   ],
   "source": [
    "# Example set of keys in tfbsDb, they are Motif IDs (http://jaspar.genereg.net/search?q=Homo%20sapiens&collection=CORE&tax_group=vertebrates)\n",
    "print(list(tfbsDb.keys())[0:5])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['10', '100131211', '100288797', '100302736', '10057']\n"
     ]
    }
   ],
   "source": [
    "# Example set of values under a specific Motif ID, they are Entrez IDs\n",
    "print(tfbsDb[list(tfbsDb.keys())[1]][0:5])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1185\n"
     ]
    }
   ],
   "source": [
    "print(len(tfbsDb[list(tfbsDb.keys())[0]]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Motif Name', 'Gene Symbol', 'Entrez ID']\n"
     ]
    }
   ],
   "source": [
    "# Read in humanTFs file\n",
    " \n",
    "id2motif = {}\n",
    "motif2id = {}\n",
    "with open('id_conversion/humanTFs_All.csv','r') as inFile:\n",
    "    # Use the readline() function to read in a single line\n",
    "    # strip() gets rid of the newline character at the end of the line\n",
    "    # split(',') splits up the line into columns based on commas\n",
    "    header = inFile.readline().strip().split(',')\n",
    "    print (header)\n",
    "    while 1:\n",
    "        inLine = inFile.readline()\n",
    "        if not inLine:\n",
    "            break\n",
    "        split = inLine.strip().split(',') \n",
    "        \n",
    "        # TODO Fill out the id2motif dictionary (key = Entrez ID, value = Motif Name)\n",
    "        # if split[2]\n",
    "        \n",
    "        if not split[2] in id2motif:\n",
    "            id2motif[split[2]] = []\n",
    "        id2motif[split[2]].append(split[0])       \n",
    "        # TODO Fill out the motif2id dictionary (key = Motif Name, value = Entrez ID)\n",
    "        motif2id[split[0]]=split[2]\n",
    "        \n",
    "       \n",
    "     \n",
    "\n",
    "#print(len(motif2id))\n",
    "#print(len(id2motif.keys()))\n",
    "#print(id2motif)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "## To build a TF regulator to TF target gene network (constrained to TFs within the input list).\n",
    "## This will require mapping from:\n",
    "##     1. Input list of potential TF regulator Entrez Gene IDs (input) \n",
    "##     2. List of Motif IDs for an Entrez Gene ID in the input list (either id2motif or motif2id)\n",
    "##     3. TF target genes that are Entrez Gene IDs that are the values under a specific Motif ID in tfbsDb\n",
    "##     4. Restrict TF target genes to only those in the input list\n",
    "##     5. Add new entry to tfNetwor dictionary that has as the key the TF regulator and the values all the TF target genes\n",
    "tfNetwork = {}\n",
    "\n",
    "for eachTfReg in input:    # for loop that assigns each iteration to eachTfReg\n",
    "    if eachTfReg in id2motif:\n",
    "        for eachMotif in id2motif[eachTfReg]:    # loop function that checks motif2id in id2motif[eachTfReg]\n",
    "            if eachMotif in tfbsDb:\n",
    "                targets = tfbsDb[eachMotif]          # assign targets from id2motif[eachTfReg]/eachTfreg\n",
    "        \n",
    "                for eachTarget in targets:\n",
    "                    if not eachTfReg in tfNetwork:\n",
    "                        tfNetwork[eachTfReg] = []\n",
    "            \n",
    "                    if eachTarget in input and not eachTarget in tfNetwork[eachTfReg]:\n",
    "                        tfNetwork[eachTfReg].append(eachTarget)\n",
    "    \n",
    "#print (tfNetwork)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "12\n",
      "['84699', '9421', '3726', '128209', '10365', '1316', '5971', '4093', '347853', '8463', '23051', '85416']\n"
     ]
    }
   ],
   "source": [
    "l1 = []\n",
    "for eachTfReg in input:\n",
    "    if not eachTfReg in tfNetwork:\n",
    "        #print (eachTfReg)\n",
    "        l1.append(eachTfReg)\n",
    " \n",
    "print(len(l1))\n",
    "print(l1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "#sorted(id2motif.keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Ascl2.1',\n",
       " 'Ascl2.2',\n",
       " 'Ascl2_bHLH_DBD_dimeric_10_1',\n",
       " 'V_ASCL2_03_M02737',\n",
       " 'V_ASCL2_04_M02841']"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#motif2id['430']\n",
    "id2motif['430']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'430'"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "motif2id['Ascl2.1']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "74\n"
     ]
    }
   ],
   "source": [
    "print (len(input))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['142', '190', '196', '257', '326']\n"
     ]
    }
   ],
   "source": [
    "print (list(id2motif.keys())[0:5])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'142' in tfbsDb['Ascl2.1']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "#print(tfbsDb.keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "#for each in input:\n",
    "  #  print (each)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "62"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(tfNetwork)"
   ]
  },
  {
   "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": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}