comparison clsi_profile_type2_linux.ipynb @ 5:3c27e5c2a8e9 draft

"planemo upload for repository https://github.com/rakesh4osdd/asist/tree/master commit d4b81c15919b4b87d215eaf1b792c8f251665647"

4:2a5861818faf

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 115,
   "id": "9aa0a6f7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ASIST module2 | map AST result to the CLSI breakporints with combination antibiotics\n",

    "import sys"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "id": "9af8387e",
   "metadata": {},
   "outputs": [],
   "source": [
    "#print(pd.__version__, re.__version__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "id": "73d0783c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# compare two MIC value strings\n",

    "#check_mic('65','32-64','i')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "id": "4d2ab1b1",
   "metadata": {},
   "outputs": [],
   "source": [
    "# compare MIC value in pandas list\n",

    "#sus_res_int(mic)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "id": "0e22ef0d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'# for input argument\\ninput_user = sys.argv[1]\\ninput_clsi = sys.argv[2]\\noutput_table = sys.argv[3]'"
      ]
     },
     "execution_count": 119,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# for input argument\n",
    "input_user = sys.argv[1]\n",

    "output_table = sys.argv[3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "21d5fe63",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"#input_user='~/Jupyterlab_notebook/ASIST_module/strain_profiles_16k.csv.csv'\\ninput_user='test-data/input2.csv'\\ninput_clsi='test-data/clsi.csv'\\noutput_profile='test-data/input2_profile.csv'\\noutput_table='test-data/input2_table.csv'\\n#output_table='/home/rakesh/Jupyterlab_notebook/ASIST_module/strain_profiles_16k_table.csv'\""
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"\"\"#input_user='~/Jupyterlab_notebook/ASIST_module/strain_profiles_16k.csv.csv'\n",
    "input_user='test-data/input2.csv'\n",
    "input_clsi='test-data/clsi.csv'\n",
    "output_profile='test-data/input2_profile.csv'\n",
    "output_table='test-data/input2_table.csv'\n",
    "#output_table='/home/rakesh/Jupyterlab_notebook/ASIST_module/strain_profiles_16k_table.csv'\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 146,
   "id": "1e64b025",
   "metadata": {},
   "outputs": [],
   "source": [
    "# read user AST data with selected 3 columns\n",

    "#strain_mic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 147,
   "id": "0d30ddc3",
   "metadata": {},
   "outputs": [],
   "source": [
    "clsi_bp=pd.read_csv(input_clsi,sep=',')\n",

    "#clsi_bp[clsi_bp[['Antibiotics', 'Susceptible']].duplicated()].shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 148,
   "id": "a818676d",
   "metadata": {},
   "outputs": [],
   "source": [
    "#clsi_bp\n",
    "#strain_mic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 149,
   "id": "c2aae757",
   "metadata": {},
   "outputs": [],
   "source": [
    "input_dups=strain_mic[strain_mic[['Strain name','Antibiotics']].duplicated()]\n",
    "if (input_dups.shape[0] == 0):\n",
    "    #print( \"No duplicates\")\n",
    "    pass\n",
    "else:\n",
    "    input_dups.to_csv(output_table,na_rep='NA')\n",
    "    with open(output_table, \"a\") as file_object:\n",
    "    # Append 'hello' at the end of file\n",
    "        file_object.write('Input File Error: Please remove duplicate/mutiple MIC values for same combination of Strain name and Antibiotics from input file')\n",
    "    exit()\n",
    "#input_dups.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "id": "c6b4c59b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# convert MIC to numbers sMIC, rMIC\n",

    "clsi_bp['i_mic'] = clsi_bp[['Intermediate']].applymap(lambda x: (re.sub(r'[^0-9.\\/-]', '', x)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "id": "d0171f94",
   "metadata": {},
   "outputs": [],
   "source": [
    "#clsi_bp['i_mic'] = clsi_bp[['Intermediate']].applymap(lambda x: (re.sub(r'[^0-9.\\/-]', '', x)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "id": "fe45b2dd",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Read only numbers in MIC values\n",

    "#    print('Waring: Error in MIC value')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "id": "ddbbe4d9",
   "metadata": {},
   "outputs": [],
   "source": [
    "#strain_mic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "id": "640508f1",
   "metadata": {},
   "outputs": [],
   "source": [
    "# capitalize each Antibiotic Name for comparision with removing whitespace\n",

    "clsi_bp['Antibiotics']=clsi_bp['Antibiotics'].str.capitalize().str.replace(\" \",\"\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "id": "b87426f4",
   "metadata": {},
   "outputs": [],
   "source": [
    "#find duplicate values in input files\n",

    "        print('Waring: Error in input Values')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "id": "91bfc94d",
   "metadata": {},
   "outputs": [],
   "source": [
    "#result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,

5:3c27e5c2a8e9

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "9aa0a6f7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ASIST module2 | map AST result to the CLSI breakporints with combination antibiotics\n",

    "import sys"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "9af8387e",
   "metadata": {},
   "outputs": [],
   "source": [
    "#print(pd.__version__, re.__version__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "73d0783c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# compare two MIC value strings\n",

    "#check_mic('65','32-64','i')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "4d2ab1b1",
   "metadata": {},
   "outputs": [],
   "source": [
    "# compare MIC value in pandas list\n",

    "#sus_res_int(mic)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "0e22ef0d",
   "metadata": {},
   "outputs": [
    {
     "ename": "IndexError",
     "evalue": "list index out of range",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mIndexError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-11-26f141926f14>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0minput_user\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msys\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margv\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0minput_clsi\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msys\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margv\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0moutput_table\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msys\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margv\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m3\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;31mIndexError\u001b[0m: list index out of range"
     ]
    }
   ],
   "source": [
    "# for input argument\n",
    "input_user = sys.argv[1]\n",

    "output_table = sys.argv[3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "21d5fe63",
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\"input_user='~/Jupyterlab_notebook/ASIST_module/strain_profiles_16k.csv.csv'\n",
    "#input_user='test-data/input2.csv'\n",
    "input_clsi='test-data/clsi.csv'\n",
    "output_profile='test-data/input2_profile.csv'\n",
    "#output_table='test-data/input2_table.csv'\n",
    "output_table='/home/rakesh/Jupyterlab_notebook/ASIST_module/strain_profiles_16k_table.csv'\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "1e64b025",
   "metadata": {},
   "outputs": [],
   "source": [
    "# read user AST data with selected 3 columns\n",

    "#strain_mic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "0d30ddc3",
   "metadata": {},
   "outputs": [],
   "source": [
    "clsi_bp=pd.read_csv(input_clsi,sep=',')\n",

    "#clsi_bp[clsi_bp[['Antibiotics', 'Susceptible']].duplicated()].shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "a818676d",
   "metadata": {},
   "outputs": [],
   "source": [
    "#clsi_bp\n",
    "#strain_mic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "c2aae757",
   "metadata": {},
   "outputs": [],
   "source": [
    "# warn user for duplicate files\n",
    "input_dups=strain_mic[strain_mic[['Strain name','Antibiotics']].duplicated()]\n",
    "if (input_dups.shape[0] == 0):\n",
    "    #print( \"No duplicates\")\n",
    "    pass\n",
    "else:\n",
    "    with open(output_table, \"w\") as file_object:\n",
    "    # Append 'hello' at the end of file\n",
    "        file_object.write('S.No.,Strain name,Antibiotics,MIC\\nInput File Error: Please remove duplicate/mutiple MIC values for same combination of Strain name and Antibiotics from input file\\n')\n",
    "    input_dups.to_csv(output_table,na_rep='NA', mode='a')\n",
    "    exit()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "c6b4c59b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# convert MIC to numbers sMIC, rMIC\n",

    "clsi_bp['i_mic'] = clsi_bp[['Intermediate']].applymap(lambda x: (re.sub(r'[^0-9.\\/-]', '', x)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "d0171f94",
   "metadata": {},
   "outputs": [],
   "source": [
    "#clsi_bp['i_mic'] = clsi_bp[['Intermediate']].applymap(lambda x: (re.sub(r'[^0-9.\\/-]', '', x)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "fe45b2dd",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Read only numbers in MIC values\n",

    "#    print('Waring: Error in MIC value')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "ddbbe4d9",
   "metadata": {},
   "outputs": [],
   "source": [
    "#strain_mic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "640508f1",
   "metadata": {},
   "outputs": [],
   "source": [
    "# capitalize each Antibiotic Name for comparision with removing whitespace\n",

    "clsi_bp['Antibiotics']=clsi_bp['Antibiotics'].str.capitalize().str.replace(\" \",\"\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "b87426f4",
   "metadata": {},
   "outputs": [],
   "source": [
    "#find duplicate values in input files\n",

    "        print('Waring: Error in input Values')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "91bfc94d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Strain name</th>\n",
       "      <th>Antibiotics</th>\n",
       "      <th>MIC</th>\n",
       "      <th>o_mic</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [Strain name, Antibiotics, MIC, o_mic]\n",
       "Index: []"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dups.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,