README-Stoltzman-PNAS-2008-S1.md

Stoltzman et al. PNAS 2008 Figure S1

This Github gist contains a CSV file of manually transcribed gene names from Figure S1 of Stoltzman et al. 2008 PNAS paper.

Another file containing the ENSEMBL gene identifiers matched to these ids has been produced via mygene.info API (Xin,2016)

References

• Stoltzman, C., Peterson, C., Breen, K., Muoio, D., Billin, A., Ayer, D. (2008). Glucose sensing by MondoA:Mlx complexes: A role for hexokinases and direct regulation of thioredoxin-interacting protein expression Proceedings of the National Academy of Sciences 105(19), 6912-6917. https://dx.doi.org/10.1073/pnas.0712199105
• Xin, J., Mark, A., Afrasiabi, C., Tsueng, G., Juchler, M., Gopal, N., Stupp, G., Putman, T., Ainscough, B., Griffith, O., Torkamani, A., Whetzel, P., Mungall, C., Mooney, S., Su, A., Wu, C. (2016). High-performance web services for querying gene and variant annotation Genome Biology 17(1), 91. https://dx.doi.org/10.1186/s13059-016-0953-9

Stoltzman-PNAS-2008-figure-s1-id-conversion.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import mygene"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.read_csv('figure-s1.tsv', sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "symbols = data.stack().unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['ADAMTS15', 'ABL2', 'ANGPTL4', 'ADRA1B', 'ANKRD1', 'BBC3', 'ALS2',\n",
       "       'C1orf79', 'BMP8A', 'ANGPT1', 'C3orf52', 'C10orf137', 'AQP10',\n",
       "       'CCL3', 'CNOT2', 'ARC', 'CRYAB', 'CXCL14', 'ARHGAP6', 'CSF2',\n",
       "       'CYR61', 'ARHGEF3', 'DST', 'DEFB103B', 'ARID3B', 'DUSP6', 'DGCR8',\n",
       "       'ARID5B', 'EBI2', 'DRD4', 'ARRDC4', 'EDN1', 'DUSP1', 'AVPI1',\n",
       "       'EPC1', 'DUX4', 'AXUD1', 'EYA3', 'ETS2', 'BACH1', 'FAM46C',\n",
       "       'FLJ10404', 'BAMBI', 'FBN2', 'FTMT', 'BCL2A1', 'FGFR3', 'GLI4',\n",
       "       'BCL6', 'GEM', 'GSX2', 'BHLHB2', 'GNPTAB', 'HCN2', 'BIRC3',\n",
       "       'GRASP', 'HNRPDL', 'C11orf17', 'ID1', 'HS2ST1', 'C12orf42', 'IER3',\n",
       "       'INSIG1', 'C13orf15', 'IL11', 'KCNQ10T1', 'C1orf63', 'IL1RL1',\n",
       "       'KRTAP2-4', 'C1orf71', 'KBTBD8', 'KRTAP4-12', 'C21orf135',\n",
       "       'KIAA0999', 'MMP10', 'C3orf50', 'LFNG', 'MMP12', 'CCL26', 'LUZP1',\n",
       "       'MMP3', 'CCL3L3', 'MMP1', 'MOGAT1', 'CCRN4L', 'NFKBIA', 'MYC',\n",
       "       'CD274', 'NFKBIE', 'PARP10', 'CD69', 'NPPC', 'PFKFB3', 'CD83',\n",
       "       'PHLDB2', 'PLK3', 'CDKN1A', 'PTGER4', 'POLD3', 'CECR1', 'PTGS2',\n",
       "       'PTPRC', 'CIB3', 'RRAD', 'SPINK1', 'CLCF1', 'SAT1', 'TMPRSS9',\n",
       "       'CLK4', 'SEC24A', 'UBE1L2', 'CNNM4', 'SERPINA3', 'CREBBP',\n",
       "       'SLC2A3', 'CTGF', 'SPRY2', 'CYP2E1', 'SYNE1', 'DENND2C', 'TBX3',\n",
       "       'DEPDC2', 'TMCC3', 'DIRAS3', 'TNFAIP3', 'DMXL1', 'TRIB1', 'DUSP10',\n",
       "       'YOD1', 'DUSP2', 'DUSP8', 'EGR1', 'ERN1', 'ERRFI1', 'FA2H', 'FGD4',\n",
       "       'FOSL1', 'FOSL2', 'GADD45A', 'GATA6', 'GNB5', 'GNRH1', 'GNRHR',\n",
       "       'GREM2', 'HBEGF', 'HDAC4', 'ID2', 'ID3', 'ID4', 'IL12A', 'IL3RA',\n",
       "       'IL6', 'IL8', 'IRF8', 'JAG2', 'JARID2', 'JUNB', 'KCNJ14',\n",
       "       'KIAA1754', 'KITLG', 'KLF10', 'KLF11', 'KLF5', 'LGI2', 'LIPG',\n",
       "       'LOC341346', 'LRCH1', 'MEX3B', 'MGEA5', 'MIDN', 'MLLT1', 'MYLIP',\n",
       "       'N4BP3', 'NFIL3', 'NFYA', 'NLRP3', 'NR4A1', 'NR4A2', 'NR4A3',\n",
       "       'OBSCN', 'OR11H12', 'OSR1', 'PCNXL2', 'PDE4D', 'PDE4DIP', 'PDXDC2',\n",
       "       'PER1', 'PIM1', 'PLA2G3', 'PPP1R14C', 'PPP1R3B', 'PRDM1', 'PTGIS',\n",
       "       'PTPRE', 'RASL11B', 'RBM15', 'RBM25', 'RICTOR', 'RIPK4', 'RNF152',\n",
       "       'RP13-36C9.6', 'RREB1', 'RSRC2', 'SERPINB9', 'SERTAD1', 'SETX',\n",
       "       'SGK269', 'SLC19A2', 'SLC22A16', 'SLC25A25', 'SLC2A14', 'SNF1LK',\n",
       "       'SOD2', 'SOX9', 'SPSB1', 'STK17B', 'TAGLN3', 'TANC2', 'TCL6',\n",
       "       'TLE3', 'TNF', 'TNFSF9', 'TRAF1', 'TRIM36', 'TRIM49', 'TXNIP',\n",
       "       'UBE3A', 'USP36', 'VASN', 'VNN3', 'ZC3H12A', 'ZCCHC6', 'ZFP36L2',\n",
       "       'ZNF462', 'ZSCAN4'], dtype=object)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "symbols"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "import mygene\n",
    "mg = mygene.MyGeneInfo()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "querying 1-235...done.\n",
      "Finished.\n",
      "15 input query terms found dup hits:\n",
      "\t[('ARC', 2), ('DUSP1', 2), ('DUX4', 7), ('BACH1', 2), ('GEM', 2), ('KRTAP2-4', 2), ('SAT1', 3), ('JU\n",
      "4 input query terms found no hit:\n",
      "\t['FLJ10404', 'KIAA0999', 'LOC341346', 'RP13-36C9.6']\n",
      "Pass \"returnall=True\" to return complete lists of duplicate or missing query terms.\n"
     ]
    }
   ],
   "source": [
    "mappings = mg.querymany(symbols, \n",
    "                        fields='symbol,ensembl.gene',\n",
    "                        scopes='symbol,alias', \n",
    "                        species='human',\n",
    "                        as_dataframe=True)\n",
    "\n",
    "mappings['notfound'] = mappings['notfound'].fillna(False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# deduplicate by taking the best scoring result\n",
    "mappings = mappings.groupby(mappings.index).apply(lambda x: x.sort_values(by='_score', ascending=False).iloc[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "mappings_processed = []\n",
    "\n",
    "for ix, row in mappings.iterrows():\n",
    "    ensembl = row['ensembl']\n",
    "    ensembl_gene = row['ensembl.gene']\n",
    "\n",
    "    if not isinstance(ensembl, list) and pd.isnull(ensembl):\n",
    "        mappings_processed.append(row)\n",
    "    else:\n",
    "        \n",
    "        new_row = row.copy()\n",
    "        if not pd.isnull(ensembl_gene):\n",
    "            raise Exception(f'Both non null for {ix}')\n",
    "        \n",
    "        gene_ids = set()\n",
    "        for annot in ensembl:\n",
    "            gene_ids.add(annot['gene'])\n",
    "        \n",
    "        new_row['ensembl.gene'] = '/'.join(sorted(gene_ids))\n",
    "        new_row['ensembl'] = None\n",
    "        \n",
    "        mappings_processed.append(new_row)\n",
    "\n",
    "mappings_processed = pd.DataFrame(mappings_processed, index=mappings.index)\n",
    "\n",
    "del mappings_processed['ensembl']\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Mygene.info gets most but this is some extra\n",
    "MANUAL_MAPPINGS = {\n",
    "    'C1orf79': 'ENSG00000197989',\n",
    "    'C21orf135': 'ENSG00000261706',\n",
    "    'C3orf50': 'ENSG00000206120',\n",
    "    'FLJ10404': 'ENSG00000146067',\n",
    "    'KCNQ10T1': 'ENSG00000269821',\n",
    "    'KIAA0999': 'ENSG00000160584',\n",
    "    'LOC341346': 'ENSG00000165935',\n",
    "    'PDXDC2': 'ENSG00000255185',\n",
    "    'RP13-36C9.6': 'ENSG00000228836',\n",
    "}\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "for ix, ensembl_gene in MANUAL_MAPPINGS.items():\n",
    "    \n",
    "    current_gene = mappings_processed.loc[ix, 'ensembl.gene']\n",
    "    \n",
    "    if not pd.isnull(current_gene) and current_gene != ensembl_gene:\n",
    "        raise Exception(f'Trying to assing {ensembl_gene} to {ix} but it already has {current_gene} assigned')\n",
    "    \n",
    "    mappings_processed.loc[ix, 'ensembl.gene'] = ensembl_gene"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>_id</th>\n",
       "      <th>_score</th>\n",
       "      <th>symbol</th>\n",
       "      <th>ensembl.gene</th>\n",
       "      <th>notfound</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>query</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [_id, _score, symbol, ensembl.gene, notfound]\n",
       "Index: []"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mappings_processed[mappings_processed['ensembl.gene'].isnull()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>_id</th>\n",
       "      <th>_score</th>\n",
       "      <th>symbol</th>\n",
       "      <th>ensembl.gene</th>\n",
       "      <th>notfound</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>query</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>ABL2</th>\n",
       "      <td>27</td>\n",
       "      <td>85.996160</td>\n",
       "      <td>ABL2</td>\n",
       "      <td>ENSG00000143322</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ADAMTS15</th>\n",
       "      <td>170689</td>\n",
       "      <td>88.832230</td>\n",
       "      <td>ADAMTS15</td>\n",
       "      <td>ENSG00000166106</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ADRA1B</th>\n",
       "      <td>147</td>\n",
       "      <td>88.841980</td>\n",
       "      <td>ADRA1B</td>\n",
       "      <td>ENSG00000170214</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ALS2</th>\n",
       "      <td>57679</td>\n",
       "      <td>87.331290</td>\n",
       "      <td>ALS2</td>\n",
       "      <td>ENSG00000003393</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ANGPT1</th>\n",
       "      <td>284</td>\n",
       "      <td>87.895485</td>\n",
       "      <td>ANGPT1</td>\n",
       "      <td>ENSG00000154188</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             _id     _score    symbol     ensembl.gene  notfound\n",
       "query                                                           \n",
       "ABL2          27  85.996160      ABL2  ENSG00000143322     False\n",
       "ADAMTS15  170689  88.832230  ADAMTS15  ENSG00000166106     False\n",
       "ADRA1B       147  88.841980    ADRA1B  ENSG00000170214     False\n",
       "ALS2       57679  87.331290      ALS2  ENSG00000003393     False\n",
       "ANGPT1       284  87.895485    ANGPT1  ENSG00000154188     False"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mappings_processed.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "mappings_processed = mappings_processed[['symbol', 'ensembl.gene']]\n",
    "mappings_processed = mappings_processed.rename(columns={\n",
    "    'symbol': 'updated_symbol',\n",
    "    'ensembl.gene': 'ensembl_gene_id'\n",
    "})\n",
    "\n",
    "mappings_processed.index.name = 'stoltzman_symbol'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "long_data = data.stack().reset_index()\n",
    "del long_data['level_0']\n",
    "\n",
    "long_data.columns = ['stoltzman_classification', 'stoltzman_symbol']\n",
    "long_data = long_data.join(mappings_processed, on='stoltzman_symbol')\n",
    "long_data = long_data.sort_values(by=['stoltzman_classification', 'stoltzman_symbol'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "long_data.to_csv('figure-s1-processed.tsv',\n",
    "                 index=False,\n",
    "                 sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "stoltzman_classification\tstoltzman_symbol\tupdated_symbol\tensembl_gene_id\r\n",
      "Compensation\tANGPTL4\tANGPTL4\tENSG00000167772\r\n",
      "Compensation\tBBC3\tBBC3\tENSG00000105327\r\n",
      "Compensation\tBMP8A\tBMP8A\tENSG00000183682\r\n",
      "Compensation\tC10orf137\tEDRF1\tENSG00000107938\r\n",
      "Compensation\tCNOT2\tCNOT2\tENSG00000111596\r\n",
      "Compensation\tCXCL14\tCXCL14\tENSG00000145824\r\n",
      "Compensation\tCYR61\tCCN1\tENSG00000142871\r\n",
      "Compensation\tDEFB103B\tDEFB103B\tENSG00000177243/ENSG00000273641\r\n",
      "Compensation\tDGCR8\tDGCR8\tENSG00000128191\r\n"
     ]
    }
   ],
   "source": [
    "!head figure-s1-processed.tsv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3.1.0\n"
     ]
    }
   ],
   "source": [
    "print(mygene.__version__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "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": "3.7.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}

stoltzman-pnas-2008-figure-s1-processed.tsv

stoltzman-pnas-2008-figure-s1.tsv