{
  "cells": [
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "# SBML to Boltzmann"
    },
    {
      "metadata": {
        "collapsed": true,
        "trusted": true
      },
      "cell_type": "code",
      "source": "import re\nclass sbml2boltzmann:\n    def __init__( self, sbml, deltag ):\n        self.sbml = sbml\n        self.deltag = deltag\n        self.ordRE = re.compile('__([0-9]+)__')\n    def repl( self, matchobj ):\n        return chr(int(matchobj.group(1)))\n   \n    def unmunge( self, sbmlid, prefix='M_' ):\n        return self.ordRE.sub( self.repl, sbmlid[len(prefix):])\n   \n    def get_met_comp( self, speciesId ):\n        s = self.sbml.getSpecies(speciesId)\n        if s.getCompartment() == 'CCO__45__CYTOSOL':\n            return self.unmunge( s.getId() + ':' + s.getCompartment() )\n        else:\n            return self.unmunge( s.getId()).replace('[',':').rstrip(']')\n       \n    def write_compartment( self, filename ):\n        with open(filename, 'w') as out:\n            i = 1\n            for comp in self.sbml.getListOfCompartments():\n                out.write('{}\\t{}\\tliters\\t0\\tV\\n'.format(self.unmunge(comp.getId()), float(i)))\n                i +=1\n    def write_concentrations( self, filename, volume=1.0e-15, conc_units=1.0e-9, default_conc=1.1111111e-01):\n        with open(filename, 'w') as out:\n            out.write('VOLUME\\t{}\\n'.format(volume))\n            out.write('CONC_UNITS\\t{}\\n'.format(conc_units))\n            for species in self.sbml.getListOfSpecies():\n                if species.getBoundaryCondition():\n                    boundary = 'F'\n                else:\n                    boundary = 'V'\n                out.write('{}\\t{}\\t{}\\n'.format(self.get_met_comp(species.getId()), default_conc, boundary))\n   \n    def getDeltaG( self, rxnName ):\n        if rxnName in self.deltag:\n            return self.deltag[rxnName]\n        else:\n            return 0.0\n    def write_reactions( self, filename):\n        with open(filename, 'w') as out:\n            for rxn in self.sbml.getListOfReactions():\n                out.write('REACTION\\t{}\\n'.format(rxn.getName()))\n                out.write('LEFT\\t{}\\n'.format(' + '.join([self.get_met_comp(sr.getSpecies()) \n                                                         for sr in rxn.getListOfReactants()])))\n                out.write('RIGHT\\t{}\\n'.format(' + '.join([self.get_met_comp(sr.getSpecies()) \n                                                         for sr in rxn.getListOfProducts()])))\n                out.write('DGZERO\\t{}\\n'.format(self.getDeltaG(rxn.getName())))\n                out.write('DGZERO_UNITS\\t{}\\n'.format('KCAL/MOL'))\n                out.write('//\\n')\n                         \ns2b = sbml2boltzmann(m, deltag['DeltaG(pH7.3)'].to_dict())\ns2b.get_met_comp('M_CPD__45__548')\ns2b.write_compartment('nc12.cmpts')\ns2b.write_concentrations('nc12.concs.in')\ns2b.write_reactions('nc12.rxns.dat')",
      "execution_count": null,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "# Boltzmann to COBRA"
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2018-01-03T20:39:33.081966Z",
          "start_time": "2018-01-03T20:39:32.857510Z"
        },
        "trusted": true,
        "collapsed": true
      },
      "cell_type": "code",
      "source": "import cobra, os,re\nfrom fractions import Fraction\ndef char2ord( matchobj ):\n    return '__{}__'.format( ord(matchobj.group(0)) )\nclass boltzmann2cobra:\n    def __init__( self ):\n        self.model = cobra.Model()\n        self.metabolites = set()\n    \n    \n    def munge( self, Id, prefix='M_', regexp=r'[^A-Za-z0-9_]' ):\n        return prefix + re.sub(regexp, char2ord, Id )\n           \n    def dat2model( self, datfile ):\n        attributes = ['REACTION','LEFT','RIGHT','LEFT_COMPARTMENT','RIGHT_COMPARTMENT','ENZYME_LEVEL','NREGULATION','COMMENT', 'COMMENTS','PATHWAY']\n        with open(datfile) as dat:\n            modelname = os.path.splitext(os.path.basename(datfile))[0]\n            self.model.id = self.munge(modelname)\n            self.model.name = modelname\n            rxns = []\n            rxn = {}\n            for line in dat:\n                if line.strip() != '//' and line[0] != '#':\n                    cols = line.strip().split('\\t')\n                    if len(cols) >= 2:\n                        attribute, value = cols[0].strip(), cols[1].strip()\n                        if attribute in attributes:\n                            if attribute in rxn:\n                                rxn[attribute] += value\n                            else:\n                                rxn[attribute] = value\n                    elif cols[0] == 'COMMENT':\n                        pass\n                    else:\n                        print(line)\n                        print(rxn)\n                elif line.strip() == '//':\n                    if 'REACTION' not in rxn:\n                        print(rxn)\n                    reaction = self.create_reaction( rxn )\n                    rxns.append(reaction)\n                    rxn = {}\n        return self.model\n    def parse_mixture( self, rxn ):\n        pattern = re.compile(r'([0-9./]+\\s+)?(.*)')\n        parts = {}\n        for side in ['LEFT','RIGHT']:\n            compartment = rxn['{}_COMPARTMENT'.format( side )]\n            for part in rxn[side].split(' + '):\n                m = pattern.search(part.strip())\n                if m:\n                    if not m.group(1) or m.group(1) == '':\n                        stoichiometry = 1\n                    elif '.' in m.group(1):\n                        stoichiometry = float(m.group(1).strip())\n                    else:\n                        stoichiometry = int(m.group(1).strip())\n                    if side=='LEFT':\n                        stoichiometry = -stoichiometry\n                    species =  m.group(2).strip()\n                    met = cobra.Metabolite(\"{}:{}\".format(species, compartment),name=species, compartment=compartment)\n                    if met not in self.model.metabolites:\n                        self.model.add_metabolites( [met] )\n                    parts[met] =  stoichiometry\n        return parts\n\n    def create_reaction( self, rxn, prefix='', regexp='~'):\n        reaction  = cobra.Reaction()\n        reaction.id = self.munge(rxn['REACTION'], 'R_')\n        reaction.name = rxn['REACTION']    \n        self.model.add_reactions([reaction])\n        reaction.add_metabolites( self.parse_mixture( rxn ))\n        return reaction\n",
      "execution_count": 100,
      "outputs": []
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2018-01-03T21:07:26.572784Z",
          "start_time": "2018-01-03T21:07:26.506942Z"
        },
        "scrolled": false,
        "trusted": true,
        "collapsed": true
      },
      "cell_type": "code",
      "source": "b2c = boltzmann2cobra()\nmodel = b2c.dat2model('neurospora_pentose_phos.glycolysis.tca.2.dat')\ncobra.io.save_json_model(model, 'neurospora_pentose_phos.glycolysis.tca.2.json',sort=True,pretty=True)",
      "execution_count": 102,
      "outputs": []
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2018-01-03T01:02:46.237996Z",
          "start_time": "2018-01-03T01:02:46.078149Z"
        },
        "trusted": true
      },
      "cell_type": "code",
      "source": "!head neurospora_pentose_phos.glycolysis.tca.2.dat",
      "execution_count": 9,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "REACTION ME1m\r\nLEFT\t(S)-MALATE + NAD+ \r\nRIGHT\tpyruvate + NADH + CO2\r\nLEFT_COMPARTMENT MITOCHONDRIA\r\nRIGHT_COMPARTMENT MITOCHONDRIA\r\nENZYME_LEVEL\t0.0\r\n//\r\nREACTION ME2m\r\nLEFT    (S)-MALATE + NADP+\r\nRIGHT   PYRUVATE + NADPH + CO2\r\n"
        }
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3",
      "language": "python"
    },
    "language_info": {
      "name": "python",
      "version": "3.6.1",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "toc": {
      "threshold": 4,
      "number_sections": true,
      "toc_cell": false,
      "toc_window_display": false,
      "toc_section_display": "block",
      "sideBar": true,
      "navigate_menu": true,
      "moveMenuLeft": true,
      "widenNotebook": false,
      "colors": {
        "hover_highlight": "#DAA520",
        "selected_highlight": "#FFD700",
        "running_highlight": "#FF0000",
        "wrapper_background": "#FFFFFF",
        "sidebar_border": "#EEEEEE",
        "navigate_text": "#333333",
        "navigate_num": "#000000"
      },
      "nav_menu": {
        "height": "30px",
        "width": "252px"
      }
    },
    "varInspector": {
      "window_display": false,
      "cols": {
        "lenName": 16,
        "lenType": 16,
        "lenVar": 40
      },
      "kernels_config": {
        "python": {
          "library": "var_list.py",
          "delete_cmd_prefix": "del ",
          "delete_cmd_postfix": "",
          "varRefreshCmd": "print(var_dic_list())"
        },
        "r": {
          "library": "var_list.r",
          "delete_cmd_prefix": "rm(",
          "delete_cmd_postfix": ") ",
          "varRefreshCmd": "cat(var_dic_list()) "
        }
      },
      "types_to_exclude": [
        "module",
        "function",
        "builtin_function_or_method",
        "instance",
        "_Feature"
      ]
    },
    "gist": {
      "id": "",
      "data": {
        "description": "Neurospora/neurospora_no_regulation/MENTOS_comparison_with_boltzmann_on_neurospora.ipynb",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}