replace_headers_in_fasta_improved_version.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# old code"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"new_fileB.txt\") as new_headers_fh:\n",
    "    new_headers = new_headers_fh.readlines()\n",
    "     \n",
    "with open(\"file1.fasta\") as genome_fasta:\n",
    "    gf_lines = genome_fasta.readlines()\n",
    "    \n",
    "counter = 0\n",
    "new_lines_for_new_fasta = []\n",
    "        \n",
    "for gf_line in gf_lines:\n",
    "    if gf_line.startswith(\">\"):\n",
    "        old_header = gf_line\n",
    "        new_header_line = gf_line.replace(old_header, new_headers[counter])\n",
    "        counter += 1\n",
    "        new_lines_for_new_fasta.append(new_header_line)\n",
    "    else:\n",
    "        new_lines_for_new_fasta.append(gf_line)\n",
    "    \n",
    "with open(\"fasta_replaced_headers.fa\", 'a') as replaced_headers_fh:\n",
    "    for new_line in new_lines_for_new_fasta:\n",
    "        replaced_headers_fh.write(new_line)\n",
    "    \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# improved code"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"new_fileB.txt\") as new_headers_fh:\n",
    "    new_headers = new_headers_fh.readlines()\n",
    "     \n",
    "with open(\"file1.fasta\") as genome_fasta:\n",
    "    gf_lines = genome_fasta.readlines()\n",
    "    \n",
    "# remove the counter\n",
    "new_lines_for_new_fasta = []\n",
    "        \n",
    "for gf_line in gf_lines:\n",
    "    if gf_line.startswith(\">\"):\n",
    "        new_lines_for_new_fasta.append(new_headers[0])\n",
    "        new_headers.remove(new_headers[0])\n",
    "    else:\n",
    "        new_lines_for_new_fasta.append(gf_line)\n",
    "    \n",
    "with open(\"fasta_replaced_headers.fa\", 'wt') as replaced_headers_fh: # changed a to wt\n",
    "    for new_line in new_lines_for_new_fasta:\n",
    "        replaced_headers_fh.write(new_line)\n",
    "    \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# enumerate"
   ]
  },
  {
   "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": "3.7.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}