puzzle club 3: Calculating GC content

GC_Julia.ipynb

GC_python.ipynb

GC_R.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Computing GC content\n",
    "---------------------\n",
    "\n",
    "Return string with the greatest proportion of GC"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Rosalind_0409\n",
      "52.4144869215292"
     ]
    }
   ],
   "source": [
    "data <- seqinr::read.fasta(\"~/Downloads/rosalind_gc.txt\")\n",
    "\n",
    "cg_content <- function(x){\n",
    "  out <- table(x)\n",
    "  c <- out[[2]]\n",
    "  g <- out[[3]]\n",
    "  content <- ((c + g) / length(x)) * 100\n",
    "}\n",
    "\n",
    "gc_list <- lapply(data, cg_content)\n",
    "out <- which.max(lapply(data, cg_content))\n",
    "cat(paste(names(out), max(unlist(gc_list)), sep = '\\n'))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "-------------------------------------\n",
    "\n",
    "## Without using `table()`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Rosalind_0409\n",
      "52.4144869215292"
     ]
    }
   ],
   "source": [
    "data <- seqinr::read.fasta(\"~/Downloads/rosalind_gc.txt\")\n",
    "\n",
    "col_data <- lapply(data, function(x){paste(x, collapse = \"\")})\n",
    "\n",
    "cg_content <- function(x){\n",
    "    chars <- strsplit(x, NULL)[[1]]\n",
    "    c <- summary(factor(chars))[[2]]\n",
    "    g <- summary(factor(chars))[[3]]\n",
    "    out <- ((c + g) / length(chars)) * 100\n",
    "}\n",
    "\n",
    "out <- lapply(col_data, cg_content)\n",
    "cat(paste(names(which.max(out)), max(unlist(out)), sep = '\\n'))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "R",
   "language": "R",
   "name": "ir"
  },
  "language_info": {
   "codemirror_mode": "r",
   "file_extension": ".r",
   "mimetype": "text/x-r-source",
   "name": "R",
   "pygments_lexer": "r",
   "version": "3.2.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}