overlap graphs

overlap_graphs_jl.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Overlap graphs\n",
    "==============="
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "using FastaIO\n",
    "\n",
    "dat = readfasta(\"/home/scott/Dropbox/rosalind/rosalind_grph.txt\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "overlap (generic function with 1 method)"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "function overlap(x::AbstractString, y::AbstractString, k::Int)\n",
    "    x[end-(k-1):end] == y[1:k]\n",
    "end"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "154x2 Array{Any,2}:\n",
       " \"Rosalind_4684\"  \"Rosalind_2924\"\n",
       " \"Rosalind_5744\"  \"Rosalind_4684\"\n",
       " \"Rosalind_6212\"  \"Rosalind_4684\"\n",
       " \"Rosalind_5078\"  \"Rosalind_4684\"\n",
       " \"Rosalind_3280\"  \"Rosalind_4684\"\n",
       " \"Rosalind_8941\"  \"Rosalind_0064\"\n",
       " \"Rosalind_8941\"  \"Rosalind_7021\"\n",
       " \"Rosalind_8941\"  \"Rosalind_9890\"\n",
       " \"Rosalind_3053\"  \"Rosalind_8941\"\n",
       " \"Rosalind_5527\"  \"Rosalind_8941\"\n",
       " \"Rosalind_2924\"  \"Rosalind_7411\"\n",
       " \"Rosalind_6407\"  \"Rosalind_2924\"\n",
       " \"Rosalind_2924\"  \"Rosalind_5188\"\n",
       " ⋮                               \n",
       " \"Rosalind_7735\"  \"Rosalind_7153\"\n",
       " \"Rosalind_9378\"  \"Rosalind_7153\"\n",
       " \"Rosalind_0139\"  \"Rosalind_8451\"\n",
       " \"Rosalind_6755\"  \"Rosalind_8700\"\n",
       " \"Rosalind_5459\"  \"Rosalind_5078\"\n",
       " \"Rosalind_8700\"  \"Rosalind_5710\"\n",
       " \"Rosalind_7621\"  \"Rosalind_5136\"\n",
       " \"Rosalind_7621\"  \"Rosalind_3280\"\n",
       " \"Rosalind_5188\"  \"Rosalind_5710\"\n",
       " \"Rosalind_0139\"  \"Rosalind_4494\"\n",
       " \"Rosalind_2574\"  \"Rosalind_0388\"\n",
       " \"Rosalind_5709\"  \"Rosalind_5459\""
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "function adj(data, k)\n",
    "    \n",
    "    out = []\n",
    "    \n",
    "    for x in combinations(data, 2)\n",
    "        \n",
    "        str_x = x[1][2]\n",
    "        str_y = x[2][2]\n",
    "        \n",
    "        if overlap(str_x, str_y, k)\n",
    "            push!(out, x[1][1], x[2][1])\n",
    "        end\n",
    "        \n",
    "        if overlap(str_y, str_x, k)\n",
    "            push!(out, x[2][1], x[1][1])\n",
    "        end  \n",
    "    end\n",
    "    \n",
    "    # eurgh\n",
    "    out = transpose(reshape(out, 2, Int(length(out)/2)))\n",
    "    return out\n",
    "end\n",
    "\n",
    "adj(dat, 3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Check that reshaping the array preserves the order"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "10x2 Array{Int32,2}:\n",
       "  1   2\n",
       "  3   4\n",
       "  5   6\n",
       "  7   8\n",
       "  9  10\n",
       " 11  12\n",
       " 13  14\n",
       " 15  16\n",
       " 17  18\n",
       " 19  20"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test = Array(1:20)\n",
    "transpose(reshape(test, 2, 10))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Julia 0.4.2",
   "language": "julia",
   "name": "julia-0.4"
  },
  "language_info": {
   "file_extension": ".jl",
   "mimetype": "application/julia",
   "name": "julia",
   "version": "0.4.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}

overlap_graphs_py.ipynb