Analyse_ST_codonUse-Statsphospho.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "All HA and NA data analysed uses files filtered to only contain strains with the full motif. The dataframes with S/T data\n",
    "therefore can contain 100 entries for some sites and 4000 for some sites, howevere when plotting relative circles it is only relative to usage at each site so those circles may appear similar in size when from different sites. Either be very clear about this or change it in future."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "#import relevant libraries\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "import CommonMotifProb as MP\n",
    "import matplotlib\n",
    "from scipy.stats import chi2_contingency\n",
    "matplotlib.rcParams['pdf.fonttype'] = 42\n",
    "matplotlib.rcParams['ps.fonttype'] = 42\n",
    "import random"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "#define files\n",
    "path='Residue_Dataframes/'\n",
    "#inputfiles=['H3_fixed_residue_Dataframe_non-motif-positions_allResidues.csv']\n",
    "#inputfiles=['NP_fixed_residue_Dataframe_motif-positions_allResidues.csv']\n",
    "#inputfiles=['NP_fixed_residue_Dataframe_non-motif-positions_allResidues.csv']\n",
    "#inputfiles=['NS2_residues_Dataframe_motif-positions_allResidues.csv','M2_residues_Dataframe_motif-positions_allResidues.csv','PA_fixed_residue_Dataframe_motif-positions_allResidues.csv']#['NP_fixed_residue_Dataframe_motif-positions_allResidues.csv']\n",
    "inputfiles=['NP_fixed_residue_Dataframe_motif-positions_allResidues.csv', 'M12_fixed_residue_Dataframe_motif-positions_allResidues.csv','NS12_residue_Dataframe_motif-positions_allResidues.csv','NS2_residues_Dataframe_motif-positions_allResidues.csv','M2_residues_Dataframe_motif-positions_allResidues.csv','PA_fixed_residue_Dataframe_motif-positions_allResidues.csv']\n",
    "#inputfiles=['NP_fixed_residue_Dataframe_motif-positions_allResidues.csv', 'M12_fixed_residue_Dataframe_motif-positions_allResidues.csv','NS12_residue_Dataframe_motif-positions_allResidues.csv']#'A','B','C']\n",
    "nonmotiffiles=['NP_fixed_residue_Dataframe_non-motif-positions_S_T.csv','M12_fixed_residue_Dataframe_non-motif-positions_S_T.csv','NS12_residue_Dataframe_non-motif-positions_S_T.csv']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "#read in selected motifs file\n",
    "#also read in motifs to compare with from full motifs file?\n",
    "path='Residue_Dataframes/'\n",
    "keyresiduedata=[pd.read_csv(path+i,index_col=0) for i in inputfiles]\n",
    "keyresiduedataconcat=pd.concat(keyresiduedata)\n",
    "\n",
    "nonmotifdata=[pd.read_csv(path+i,index_col=0) for i in nonmotiffiles]\n",
    "nonmotifdata=pd.concat(nonmotifdata)\n",
    "\n",
    "AAs=['S','T']\n",
    "\n",
    "\n",
    "relevantcodons=[j.replace('U','T') for i in AAs for j in MP.AAtoCodonDICT[MP.SingleLetterDICT[i]]]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "keyresiduedata=keyresiduedataconcat[keyresiduedataconcat['AminoAcid'].isin(AAs)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "columns = ['Site','Codon','Phospho']\n",
    "nondatas=[]\n",
    "sites=nonmotifdata.ResidueNo.unique()\n",
    "for i in sites:\n",
    "    temp=nonmotifdata[nonmotifdata['ResidueNo']==i]\n",
    "    sitecodons=temp.Codon.value_counts()\n",
    "    for j in sitecodons.keys():\n",
    "        if sitecodons[j]>500:\n",
    "            \n",
    "            nondatas.append([i,j,0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "columns = ['Site','Codon','Phospho']\n",
    "datas=[]\n",
    "sites=keyresiduedata.ResidueNo.unique()\n",
    "for i in sites:\n",
    "    temp=keyresiduedata[keyresiduedata['ResidueNo']==i]\n",
    "    sitecodons=temp.Codon.value_counts()\n",
    "    for j in sitecodons.keys():\n",
    "        if sitecodons[j]>500:\n",
    "            datas.append([i,j,1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "#determining table assuming full or partial dependence\n",
    "columns = ['Site','Codon','Phospho']\n",
    "nondatas=[]\n",
    "sites=nonmotifdata.ResidueNo.unique()\n",
    "for i in sites:\n",
    "    temp=nonmotifdata[nonmotifdata['ResidueNo']==i]\n",
    "    sitecodons=temp.Codon.value_counts()\n",
    "    for j in sitecodons.keys():\n",
    "        if sitecodons[j]>1000:\n",
    "            loopcount=sitecodons[j]/1000\n",
    "            for l in range(int(loopcount)):\n",
    "                nondatas.append([i,j,0])\n",
    "            \n",
    "            \n",
    "columns = ['Site','Codon','Phospho']\n",
    "datas=[]\n",
    "sites=keyresiduedata.ResidueNo.unique()\n",
    "for i in sites:\n",
    "    temp=keyresiduedata[keyresiduedata['ResidueNo']==i]\n",
    "    sitecodons=temp.Codon.value_counts()\n",
    "    for j in sitecodons.keys():\n",
    "        if sitecodons[j]>1000:\n",
    "            loopcount=sitecodons[j]/1000\n",
    "            for l in range(int(loopcount)):\n",
    "                datas.append([i,j,1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "\n",
    "data=pd.DataFrame(datas,columns=columns)\n",
    "nondata=pd.DataFrame(nondatas,columns=columns)\n",
    "\n",
    "newdata=pd.concat([data,nondata])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "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>Site</th>\n",
       "      <th>Codon</th>\n",
       "      <th>Phospho</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>ACC</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6</td>\n",
       "      <td>ACC</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6</td>\n",
       "      <td>ACC</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6</td>\n",
       "      <td>ACC</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6</td>\n",
       "      <td>ACC</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>887</th>\n",
       "      <td>127</td>\n",
       "      <td>ACC</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>888</th>\n",
       "      <td>213</td>\n",
       "      <td>TCA</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>889</th>\n",
       "      <td>213</td>\n",
       "      <td>TCA</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>74</td>\n",
       "      <td>AGC</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>891</th>\n",
       "      <td>86</td>\n",
       "      <td>ACT</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1134 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Site Codon  Phospho\n",
       "0       6   ACC        1\n",
       "1       6   ACC        1\n",
       "2       6   ACC        1\n",
       "3       6   ACC        1\n",
       "4       6   ACC        1\n",
       "..    ...   ...      ...\n",
       "887   127   ACC        0\n",
       "888   213   TCA        0\n",
       "889   213   TCA        0\n",
       "890    74   AGC        0\n",
       "891    86   ACT        0\n",
       "\n",
       "[1134 rows x 3 columns]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "newdata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/dt/9s3cdx090n1_ppdzkzk88tx40000gp/T/ipykernel_10290/3640571219.py:2: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  NPPhospho['Phospho']=1\n"
     ]
    }
   ],
   "source": [
    "NPPhospho=keyresiduedata\n",
    "NPPhospho['Phospho']=1\n",
    "NPNonPho=nonmotifdata\n",
    "NPNonPho['Phospho']=0\n",
    "\n",
    "PhosphoConcat=pd.concat([NPPhospho,NPNonPho])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "data=PhosphoConcat"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Phospho    0   1\n",
      "Codon           \n",
      "ACA      124  28\n",
      "ACC       71  48\n",
      "ACG       21  29\n",
      "ACT      153  25\n",
      "AGC       88   7\n",
      "AGT      143   0\n",
      "TCA      109  16\n",
      "TCC       66  37\n",
      "TCG       15  11\n",
      "TCT      102  41\n"
     ]
    }
   ],
   "source": [
    "data_crosstab = pd.crosstab(newdata['Codon'], \n",
    "                            newdata['Phospho'],  \n",
    "                               margins = False) \n",
    "print(data_crosstab) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Phospho       0      1\n",
      "Codon                 \n",
      "ACA      148091  33601\n",
      "ACC       90999  54095\n",
      "ACG       31672  32429\n",
      "ACT      173891  28829\n",
      "AGC      107065   7218\n",
      "AGT      161325    330\n",
      "TCA      125139  18987\n",
      "TCC       77635  41692\n",
      "TCG       19723  12769\n",
      "TCT      118200  47113\n"
     ]
    }
   ],
   "source": [
    "data_crosstab = pd.crosstab(data['Codon'], \n",
    "                            data['Phospho'],  \n",
    "                               margins = False) \n",
    "print(data_crosstab) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Chi2ContingencyResult(statistic=152717.06651074922, pvalue=0.0, dof=9, expected_freq=array([[143865.11608405,  37826.88391595],\n",
      "       [114886.53960053,  30207.46039947],\n",
      "       [ 50755.66236325,  13345.33763675],\n",
      "       [160515.24741077,  42204.75258923],\n",
      "       [ 90490.15400476,  23792.84599524],\n",
      "       [127999.66614142,  33655.33385858],\n",
      "       [114120.06979245,  30005.93020755],\n",
      "       [ 94484.03180636,  24842.96819364],\n",
      "       [ 25727.41426041,   6764.58573959],\n",
      "       [130896.098536  ,  34416.901464  ]]))\n"
     ]
    }
   ],
   "source": [
    "a=chi2_contingency(data_crosstab)\n",
    "print (a)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "nonmotifdata[0]\n",
    "#dp=nonmotifdata[0]\n",
    "#dp[dp['ResidueNo']==60]"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.6 64-bit",
   "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": "3.9.6"
  },
  "vscode": {
   "interpreter": {
    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}