Day12.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Exercise 1: Construct a function called simSeq() that takes an integer argument, and generates a random DNA string of that length."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "function simSeq()\n",
    "    some code\n",
    "    return something\n",
    "end"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "simSeq (generic function with 1 method)"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "function simSeq(arg1)\n",
    "    alp = [\"A\",\"C\",\"G\",\"T\"]\n",
    "    DNAarray = [alph[rand(1:4)] for i in 1:arg1]\n",
    "    retVal = join(DNAarray)\n",
    "    return retVal\n",
    "end"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"CTTGAACCGA\""
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "simSeq(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Exercise 2: Write a function evolveSeq() that takes a String DNA sequence argument, and a mutation probability, and mutates each base to a random {A,C,G,T} base with said probability."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"joined\""
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Hint:\n",
    "join([\"j\",\"o\",\"i\",\"n\",\"e\",\"d\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "evolveSeq (generic function with 1 method)"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "function evolveSeq(seq,mutProb)\n",
    "    alp = [\"A\",\"C\",\"G\",\"T\"]\n",
    "    arr = []\n",
    "    for i in 1:length(seq)\n",
    "        if rand()<mutProb\n",
    "            push!(arr,alp[rand(1:4)])\n",
    "            else push!(arr,seq[i])\n",
    "        end\n",
    "    end\n",
    "    return join(arr)\n",
    "end"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"THISIAADAG\""
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "evolveSeq(\"THISISADOG\",0.2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Exercise 3: Create a function hammingProportion() that takes two strings of the same length, and returns the number of differences between them divided by their length."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "hammingProportion (generic function with 1 method)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "function hammingProportion(s1,s2)\n",
    "    diffs = sum([s1[i]!=s2[i] for i in 1:length(s1)])\n",
    "    return diffs/length(s1)\n",
    "end"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "longseq = simSeq(10000);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0371"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mutlongseq = evolveSeq(longseq,0.05)\n",
    "hammingProportion(longseq,mutlongseq)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Exercise 4: Create a printFasta() function that takes an array of sequences, and an array of names, and prints them in .fasta format."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "printFasta (generic function with 1 method)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "function printFasta(seqs,names)\n",
    "    for i in 1:length(seqs)\n",
    "        println(\">\",names[i])\n",
    "        println(seqs[i])\n",
    "    end\n",
    "end"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#COMPARE CASES:\n",
    "#rate = 0.1, numseqs = 20\n",
    "#rate = 0.6, numseqs = 20\n",
    "#rate = 0.1, numseqs = 200\n",
    "#rate = 0.01, numseqs = 200\n",
    "\n",
    "founder = simSeq(500);\n",
    "current = founder;\n",
    "seqArr = String[]\n",
    "for i in 1:200\n",
    "    push!(seqArr,current)\n",
    "    current = evolveSeq(current,0.01)\n",
    "end\n",
    "namesArr = [\"seq\"*string(i) for i in 1:length(seqArr)];\n",
    "printFasta(seqArr,namesArr)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Exercise 5: Predict the output of the following code. If you can't, then run it and try and explain the output. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "using PyPlot\n",
    "founder = simSeq(5000);\n",
    "current = founder;\n",
    "seqArr = String[]\n",
    "for i in 1:1000\n",
    "    push!(seqArr,current)\n",
    "    current = evolveSeq(current,0.01)\n",
    "end\n",
    "\n",
    "plot([hammingProportion(founder,i) for i in seqArr],\".\")\n",
    "plot([1,length(seqArr)],[0.75,0.75])"
   ]
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Julia 0.5.0",
   "language": "julia",
   "name": "julia-0.5"
  },
  "language_info": {
   "file_extension": ".jl",
   "mimetype": "application/julia",
   "name": "julia",
   "version": "0.5.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}