annotate asist_dynamic.ipynb @ 9:4f36d48d6090 draft default tip

Uploaded xml

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1309,
   "id": "27cfc66f",
   "metadata": {},
   "outputs": [],
   "source": [
    "#ASIST program for phenotype based on Antibiotics profile\n",
    "# create a profile based on selected antibiotics only\n",
    "# [e-mail], 14-June-2021"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "75a352b7",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import sys\n",
    "import os\n",
    "from collections import Counter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 162,
   "id": "d66ec0d2",
   "metadata": {},
   "outputs": [],
   "source": [
    "#input_file=sys.argv[1]\n",
    "#output_file=sys.argv[2]\n",
    "input_file='test-data/strains_788_input_16k.csv'\n",
    "output_file='/mnt/d/PhD_Work/Tina_Work/ASIST_Galaxy/ASIST/strains_788_output_16k.csv'\n",
    "#input_file='/mnt/d/PhD_Work/Tina_Work/ASIST_Galaxy/ASIST/asist_example15.csv'\n",
    "#output_file='/mnt/d/PhD_Work/Tina_Work/ASIST_Galaxy/ASIST/asist_example15_output.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 163,
   "id": "bf24c946",
   "metadata": {},
   "outputs": [],
   "source": [
    "# strain_profile to phenotype condition\n",
    "def s_phen(sus,res,intm,na,pb_sus):\n",
    "    if (sus>0 and res==0 and na>=0):\n",
    "        #print('Possible Susceptible')\n",
    "        phen='Possible Susceptible'\n",
    "    elif (sus>=0 and 3<=res<7 and na>=0 and pb_sus==0):\n",
    "        #print('Possible MDR')\n",
    "        phen='Possible MDR'\n",
    "    elif (sus>=0 and 7<=res<9 and na>=0 and pb_sus==0):\n",
    "        #print('Possible XDR')\n",
    "        phen='Possible XDR'\n",
    "    #special cases\n",
    "    elif (sus>=1 and res>0 and na>=0 and pb_sus==1):\n",
    "        #print('Possible XDR')\n",
    "        phen='Possible XDR'\n",
    "    #special cases\n",
    "    elif (sus>0 and res==9 and na>=0):\n",
    "        #print('Possible XDR')\n",
    "        phen='Possible XDR'\n",
    "    elif (sus==0 and res==9 and na>=0):\n",
    "        #print('Possible TDR')\n",
    "        phen='Possible TDR'\n",
    "    else:\n",
    "        #print('Strain could not be classified')\n",
    "        phen='Strain could not be classified ('+ str(intm)+' | ' + str(na) +')'\n",
    "    return(phen)\n",
    "\n",
    "#print(s_phen(1,9,0,0))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 164,
   "id": "8bad7d9d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# define Antibiotic groups as per antibiotic of CLSI breakpoints MIC\n",
    "#Aminoglycoside\n",
    "cat1=['Amikacin','Tobramycin','Gentamycin','Netilmicin']\n",
    "#Beta-lactams- Carbapenems\n",
    "cat2=['Imipenem','Meropenam','Doripenem']\n",
    "#Fluoroquinolone\n",
    "cat3=['Ciprofloxacin','Levofloxacin']\n",
    "#Beta-lactam inhibitor\n",
    "cat4=['Piperacillin/tazobactam','Ticarcillin/clavulanicacid']\n",
    "#Cephalosporin\n",
    "cat5=['Cefotaxime','Ceftriaxone','Ceftazidime','Cefepime']\n",
    "#Sulfonamides\n",
    "cat6=['Trimethoprim/sulfamethoxazole']\n",
    "#Penicillins/beta-lactamase\n",
    "cat7=['Ampicillin/sulbactam']\n",
    "#Polymyxins\n",
    "cat8=['Colistin','Polymyxinb']\n",
    "#Tetracycline\n",
    "cat9=['Tetracycline','Doxicycline','Minocycline']\n",
    "\n",
    "def s_profiler(pd_series):\n",
    "    #print(type(pd_series),'\\n', pd_series)\n",
    "    #create a dictionary of dataframe series\n",
    "    cats={'s1':cat1,'s2':cat2,'s3':cat3,'s4':cat4,'s5':cat5,'s6':cat6,'s7':cat7,'s8':cat8,'s9':cat9}\n",
    "    # find the antibiotics name in input series\n",
    "    for cat in cats:\n",
    "        #print(cats[cat])\n",
    "        cats[cat]=pd_series.filter(cats[cat])\n",
    "        #print(cats[cat])\n",
    "    #define res,sus,intm,na,pb_sus\n",
    "    res=0\n",
    "    sus=0\n",
    "    intm=0\n",
    "    na=0\n",
    "    pb_sus=0\n",
    "    # special case of 'Polymyxin b' for its value\n",
    "    if 'Polymyxinb' in pd_series:\n",
    "        ctp=cats['s8']['Polymyxinb'].strip().lower()\n",
    "        if ctp == 'susceptible':\n",
    "            pb_sus=1\n",
    "        #print((ctp,p_sus))\n",
    "    # check all categories\n",
    "    for cat in cats:\n",
    "        #ctp=cats['s8'].iloc[i:i+1].stack().value_counts().to_dict()\n",
    "        #print(ctp)\n",
    "        # Pandas series\n",
    "        ct=cats[cat].value_counts().to_dict()\n",
    "        #print(ct)\n",
    "        # remove whitespace and convert to lowercase words\n",
    "        ct =  {k.strip().lower(): v for k, v in ct.items()}\n",
    "        #print(ct)\n",
    "        k=Counter(ct)\n",
    "        #j=Counter(ct)+Counter(j)\n",
    "        #print(j)\n",
    "        # category wise marking\n",
    "        if k['resistant']>=1:\n",
    "            res=res+1\n",
    "        if k['susceptible']>=1:\n",
    "            sus=sus+1\n",
    "        if k['intermediate']>=1:\n",
    "            intm=intm+1\n",
    "        if k['na']>=1:\n",
    "            na=na+1\n",
    "    #print(sus,res,intm,na,pb_sus)\n",
    "    #print(s_phen(sus,res,intm,na,pb_sus))\n",
    "    return(s_phen(sus,res,intm,na,pb_sus))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 165,
   "id": "7629fc10",
   "metadata": {},
   "outputs": [],
   "source": [
    "#input_file='input2.csv_table.csv'\n",
    "#output_file=input_file+'_output.txt'\n",
    "strain_profile=pd.read_csv(input_file, sep=',',na_filter=False,skipinitialspace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 166,
   "id": "bed1abba",
   "metadata": {},
   "outputs": [],
   "source": [
    "old_strain_name=strain_profile.columns[0]\n",
    "new_strain_name=old_strain_name.capitalize().strip().replace(' ', '')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 167,
   "id": "a64b5022",
   "metadata": {},
   "outputs": [],
   "source": [
    "# make header capitalization, remove leading,lagging, and multiple whitespace for comparision\n",
    "strain_profile.columns=strain_profile.columns.str.capitalize().str.strip().str.replace('\\s+', '', regex=True)\n",
    "#print(strain_profile.columns)\n",
    "#strain_profile.head()\n",
    "#strain_profile.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 168,
   "id": "caac57d7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# add new column in dataframe on second position\n",
    "strain_profile.insert(1, 'Strain phenotype','')\n",
    "#strain_profile.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 169,
   "id": "eb4b0c4d",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "strain_profile['Strain phenotype'] = strain_profile.apply(lambda x: (s_profiler(x)), axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 170,
   "id": "86441c0f",
   "metadata": {},
   "outputs": [],
   "source": [
    "#strain_profile.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 171,
   "id": "75698be5",
   "metadata": {},
   "outputs": [],
   "source": [
    "#rename headers for old name\n",
    "strain_profile=strain_profile.rename(columns = {new_strain_name:old_strain_name, 'Ticarcillin/clavulanicacid':'Ticarcillin/ clavulanic acid','Piperacillin/tazobactam':'Piperacillin/ tazobactam','Trimethoprim/sulfamethoxazole': 'Trimethoprim/ sulfamethoxazole','Ampicillin/sulbactam':'Ampicillin/ sulbactam', 'Polymyxinb': 'Polymyxin B'} )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 172,
   "id": "c14a13eb",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "#strain_profile.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 173,
   "id": "1b113050",
   "metadata": {},
   "outputs": [],
   "source": [
    "#strain_profile"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 174,
   "id": "5ab72211",
   "metadata": {},
   "outputs": [],
   "source": [
    "strain_profile.to_csv(output_file,na_rep='NA',index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 175,
   "id": "c17c84c4",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Open a file with access mode 'a'\n",
    "with open(output_file, \"a\") as file_object:\n",
    "    # Append 'hello' at the end of file\n",
    "    file_object.write(\"Note: \\n1. 'MDR': Multidrug-resistant, 'XDR': Extensively drug-resistant, 'TDR':totally drug resistant, NA': Data Not Available.\\n2. 'Strain could not be classified' numbers follow the format as ('Number of antibiotics categories count as Intermediate' | 'Number of antibiotics categories count as NA')\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7e8e1fa8",
   "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": "3.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}