Python kegg.Kegg类代码示例

def GetFullOxidationReaction(cid):
    kegg = Kegg.getInstance()

    basic_cids = [1, 7, 9, 11, 14]  # H2O, O2, Pi, CO2, NH3
    basic_elements = ["C", "O", "P", "N", "e-"]
    element_mat = np.matrix(np.zeros((len(basic_elements), len(basic_cids))))
    for j in xrange(len(basic_cids)):
        atom_bag = kegg.cid2atom_bag(basic_cids[j])
        atom_bag["e-"] = kegg.cid2num_electrons(basic_cids[j])
        for i in xrange(len(basic_elements)):
            element_mat[i, j] = atom_bag.get(basic_elements[i], 0)

    cs_element_vec = np.zeros((len(basic_elements), 1))
    atom_bag = kegg.cid2atom_bag(cid)
    atom_bag["e-"] = kegg.cid2num_electrons(cid)
    for i in xrange(len(basic_elements)):
        cs_element_vec[i, 0] = atom_bag.get(basic_elements[i], 0)

    x = np.linalg.inv(element_mat) * cs_element_vec

    sparse = dict([(basic_cids[i], np.round(x[i, 0], 3)) for i in xrange(len(basic_cids))])
    sparse[cid] = -1

    r = Reaction("complete oxidation of %s" % kegg.cid2name(cid), sparse)

    return r

def ExportJSONFiles():
    estimators = LoadAllEstimators()
    options, _ = MakeOpts(estimators).parse_args(sys.argv)
    
    thermo_list = []
    thermo_list.append(estimators[options.thermodynamics_source])
    thermo_list.append(PsuedoisomerTableThermodynamics.FromCsvFile(options.thermodynamics_csv))

    # Make sure we have all the data.
    kegg = Kegg.getInstance()
    for i, thermo in enumerate(thermo_list):
        print "Priority %d - formation energies of: %s" % (i+1, thermo.name)
        kegg.AddThermodynamicData(thermo, priority=(i+1))
    
    db = SqliteDatabase('../res/gibbs.sqlite')

    print 'Exporting Group Contribution Nullspace matrix as JSON.'
    nullspace_vectors = []
    for row in db.DictReader('ugc_conservations'):
        d = {'msg': row['msg']}
        sparse = json.loads(row['json'])
        d['reaction'] = []
        for cid, coeff in sparse.iteritems():
            d['reaction'].append([coeff, "C%05d" % int(cid)])
        nullspace_vectors.append(d)
    WriteJSONFile(nullspace_vectors, options.nullspace_out_filename)
        
    print 'Exporting KEGG compounds as JSON.'
    WriteJSONFile(kegg.AllCompounds(), options.compounds_out_filename)

    print 'Exporting KEGG reactions as JSON.'
    WriteJSONFile(kegg.AllReactions(), options.reactions_out_filename)
    
    print 'Exporting KEGG enzymes as JSON.'
    WriteJSONFile(kegg.AllEnzymes(), options.enzymes_out_filename)

def main():
    html_fname = '../res/reversibility.html'
    logging.info('Writing HTML output to %s', html_fname)
    html_writer = HtmlWriter(html_fname)
    
    # plot the profile graph
    pylab.rcParams['text.usetex'] = False
    pylab.rcParams['legend.fontsize'] = 10
    pylab.rcParams['font.family'] = 'sans-serif'
    pylab.rcParams['font.size'] = 14
    pylab.rcParams['lines.linewidth'] = 2
    pylab.rcParams['lines.markersize'] = 6
    pylab.rcParams['figure.figsize'] = [6.0, 6.0]
    pylab.rcParams['figure.dpi'] = 90
    
    estimators = LoadAllEstimators()
    #analyse_reversibility(estimators['hatzi_gc'], 'HatziGC')
    #analyse_reversibility(estimators['PGC'], 'MiloGC_zoom')
    
    reaction_list = Kegg.getInstance().AllReactions()
    #reaction_list = Feist.FromFiles().reactions
    thermo = estimators['PGC']
    
    thermo.c_mid = DEFAULT_CMID
    thermo.T = DEFAULT_T
    thermo.pH = DEFAULT_PH
    thermo.I = DEFAULT_I
    thermo.pMg = DEFAULT_PMG

    compare_reversibility_to_dG0(reaction_list, thermo=thermo,
                                 html_writer=html_writer)

def main():
    opt_parser = flags.MakeOpts()
    options, _ = opt_parser.parse_args(sys.argv)
    estimators = LoadAllEstimators()
    
    print ('Parameters: T=%f K, pH=%.2g, pMg=%.2g, '
           'I=%.2gmM, Median concentration=%.2gM' % 
           (default_T, options.ph, options.pmg, options.i_s, options.c_mid))

    for thermo in estimators.values():
        thermo.c_mid = options.c_mid
        thermo.pH = options.ph
        thermo.pMg = options.pmg
        thermo.I = options.i_s
        thermo.T = default_T
    
    kegg = Kegg.getInstance()
    while True:
        cid = GetReactionIdInput()        
        compound = kegg.cid2compound(cid)
        print 'Compound Name: %s' % compound.name
        print '\tKegg ID: C%05d' % cid
        print '\tFormula: %s' % compound.formula
        print '\tInChI: %s' % compound.inchi
        for key, thermo in estimators.iteritems():
            print "\t<< %s >>" % key
            try:
                print thermo.cid2PseudoisomerMap(cid),
                print '--> dG0\'f = %.1f kJ/mol' % compound.PredictFormationEnergy(thermo)
            except Exception as e: 
                print '\t\tError: %s' % (str(e))

    def Train(self, FromDatabase=True, prior_thermodynamics=None):
        if FromDatabase and self.db.DoesTableExist('prc_S'):
            S = self.db.LoadSparseNumpyMatrix('prc_S')
            dG0 = self.db.LoadNumpyMatrix('prc_b').T
            cids = []
            cid2nH_nMg = {}
            for rowdict in self.db.DictReader('prc_compounds'):
                cid, nH, nMg = int(rowdict['cid']), int(rowdict['nH']), int(rowdict['nMg'])
                cids.append(int(rowdict['cid']))
                cid2nH_nMg[cid] = (nH, nMg)
        else:
            cid2nH_nMg = self.GetDissociation().GetCid2nH_nMg(
                                            self.pH, self.I, self.pMg, self.T)
            S, dG0, cids = self.ReverseTransform(cid2nH_nMg=cid2nH_nMg)
            self.db.SaveSparseNumpyMatrix('prc_S', S)
            self.db.SaveNumpyMatrix('prc_b', dG0.T)
            self.db.CreateTable('prc_compounds',
                                'cid INT, name TEXT, nH INT, nMg INT')
            kegg = Kegg.getInstance()
            for cid in cids:
                nH, nMg = cid2nH_nMg[cid]
                self.db.Insert('prc_compounds',
                               [cid, kegg.cid2name(cid), nH, nMg])
            self.db.Commit()

        # Train the formation energies using linear regression
        self.LinearRegression(S, dG0, cids, cid2nH_nMg, prior_thermodynamics)
        self.ToDatabase(self.db, 'prc_pseudoisomers')

 def Populate(self, filename):
     """Populates the database from files."""
     self._InitTables()
     
     f = open(filename)
     r = csv.DictReader(f)
     
     for row in r:
         insert_row = []
         for table_header in self.ORG_TABLE_HEADERS:
             if table_header not in self.CSV_HEADER_MAPPING:
                 insert_row.append(None)
                 continue
             
             csv_header = self.CSV_HEADER_MAPPING[table_header]
             val = row.get(csv_header, None)
             if val and val.strip():
                 insert_row.append(val)
             else: 
                 insert_row.append(None)
             
         oxy_req = row.get(self.OXY_REQ, None)
         broad_req = self.GetBroadyOxyReq(oxy_req)
         insert_row[-1] = broad_req
         
         self.db.Insert('organisms', insert_row)     
     f.close()
     
     k = Kegg.getInstance(loadFromAPI=False)
     enzyme_map = k.ec2enzyme_map
     for ec, enzyme in enzyme_map.iteritems():
         for org in enzyme.genes.keys():                
             self.db.Insert('organism_enzymes', [org.lower(), ec])

 def __init__(self, db, html_writer, thermodynamics,
              kegg=None):
     self.db = db
     self.html_writer = html_writer
     self.thermo = thermodynamics
     self.kegg = kegg or Kegg.getInstance()
     self.pathways = {}

def main():
    pH, I, pMg, T = 7.0, 0.25, 14.0, 298.15

    dissociation = DissociationConstants.FromPublicDB()
    kegg = Kegg.getInstance()
    obs_fname = "../data/thermodynamics/formation_energies.csv"
    res_fname = "../res/formation_energies_transformed.csv"

    train_species = PsuedoisomerTableThermodynamics.FromCsvFile(obs_fname, label="testing")
    csv_out = csv.writer(open(res_fname, "w"))
    csv_out.writerow(["cid", "name", "dG'0", "pH", "I", "pMg", "T", "anchor", "compound_ref", "remark"])
    for cid in train_species.get_all_cids():
        pmap = train_species.cid2PseudoisomerMap(cid)
        source = train_species.cid2source_string[cid]
        pmatrix = pmap.ToMatrix()  # ToMatrix returns tuples of (nH, z, nMg, dG0)
        if len(pmatrix) != 1:
            raise Exception("multiple training species for C%05d" % cid)
        nH, charge, nMg, dG0 = pmatrix[0]
        name = "%s (%d)" % (kegg.cid2name(cid), nH)
        logging.info("Adding the formation energy of %s", name)
        diss_table = dissociation.GetDissociationTable(cid, create_if_missing=True)
        if diss_table is None:
            raise Exception("%s [C%05d, nH=%d, nMg=%d] does not have a " "dissociation table" % (name, cid, nH, nMg))

        diss_table.SetFormationEnergyByNumHydrogens(dG0, nH, nMg)
        diss_table.SetCharge(nH, charge, nMg)
        dG0_prime = diss_table.Transform(pH, I, pMg, T)
        csv_out.writerow([cid, kegg.cid2name(cid), "%.1f" % dG0_prime, pH, I, pMg, T, True, source, None])

def GetMolInput(dissociation):
    mols = [] # a list of pairs of Molecule objects and stoichiometric coefficients 
    while mols == []:
        print 'KEGG ID or SMILES (or Enter to quit):',
        s_input = raw_input()
        if not s_input:
            return []
        elif re.findall('C\d\d\d\d\d', s_input) != []:
            try:
                cid = int(s_input[1:])
                mols = [(GetMostAbundantMol(cid, dissociation), 1)]
                print "Compound:", mols[0][0].ToInChI()
            except ValueError:
                print 'syntax error: KEGG compound ID is bad (%s), please try again' % s_input
        elif re.findall('R\d\d\d\d\d', s_input) != []:
            try:
                rid = int(s_input[1:])
                reaction = Kegg.getInstance().rid2reaction(rid)
                print "Reaction:", str(reaction)
                for cid, coeff in reaction.iteritems():
                    mols += [(GetMostAbundantMol(cid, dissociation), coeff)]
            except ValueError:
                print 'syntax error: KEGG reaction ID is bad (%s), please try again' % s_input
        else:
            try:
                mols = [(Molecule.FromSmiles(s_input), 1)]
                print "Compound:", mols[0][0].ToInChI()
            except Exception:
                print 'unable to parse SMILES string, please try again'
        
    return mols

    def run(self):
        from toolbox.molecule import Molecule
        
        self.semaphore.acquire()
        
        start_time = time.time()

        logging.debug("SMILES: " + self.smiles)
        diss_table = Molecule._GetDissociationTable(self.smiles, fmt='smiles',
            mid_pH=default_pH, min_pKa=0, max_pKa=14, T=default_T)
        logging.debug("Min charge: %d" % diss_table.min_charge)
        logging.debug("Min nH: %d" % diss_table.min_nH)
        
        elapsed_time = time.time() - start_time
        self.db_lock.acquire()
        db = SqliteDatabase(self.options.db_file)
        kegg = Kegg.getInstance()
        name = kegg.cid2name(self.cid)
        
        if diss_table is not None:
            for row in diss_table.ToDatabaseRow():
                db.Insert(self.options.table_name, [self.cid, name] + row)
        else:
            db.Insert(self.options.table_name, [self.cid, name] + [None] * 10)
        del db
        self.db_lock.release()

        logging.info("Completed C%05d, elapsed time = %.1f sec" %
                     (self.cid, elapsed_time))

        self.semaphore.release()

    def FromChemAxon(cid2mol=None, html_writer=None):
        kegg = Kegg.getInstance()
        diss = DissociationConstants()
        if cid2mol is None:
            cid2mol = dict([(cid, None) for cid in kegg.get_all_cids()])
        
        for cid, mol in sorted(cid2mol.iteritems()):
            logging.info("Using ChemAxon to find the pKa values for %s - C%05d" %
                         (kegg.cid2name(cid), cid))
            if html_writer:
                html_writer.write('<h2>%s - C%05d</h2>\n' %
                                  (kegg.cid2name(cid), cid))
            # if this CID is not assigned to a Molecule, use the KEGG database
            # to create a Molecule for it.
            if mol is None:
                try:
                    mol = kegg.cid2mol(cid)
                except KeggParseException:
                    continue

            diss_table = mol.GetDissociationTable()
            diss.cid2DissociationTable[cid] = diss_table
            if diss_table and html_writer:
                diss_table.WriteToHTML(html_writer)
                html_writer.write('</br>\n')
        return diss

 def __init__(self, db, html_writer=None, dissociation=None, anchor_all=False):
     PsuedoisomerTableThermodynamics.__init__(self, name="Unified Group Contribution")
     self.db = db
     self.html_writer = html_writer or NullHtmlWriter()
     self.dissociation = dissociation
     self.transformed = False
     self.CollapseReactions = False
     self.epsilon = 1e-10
     self.kegg = Kegg.getInstance()
     
     self.STOICHIOMETRIC_TABLE_NAME = 'ugc_S'
     self.GROUP_TABLE_NAME = 'ugc_G'
     self.GIBBS_ENERGY_TABLE_NAME = 'ugc_b'
     self.ANCHORED_TABLE_NAME = 'ugc_anchored'
     self.COMPOUND_TABLE_NAME = 'ugc_compounds'
     self.OBSERVATION_TABLE_NAME = 'ugc_observations'
     self.GROUPVEC_TABLE_NAME = 'ugc_groupvectors'
     self.UNIQUE_OBSERVATION_TABLE_NAME = 'ugc_unique_observations'
     self.THERMODYNAMICS_TABLE_NAME = 'ugc_pseudoisomers'
     self.ERRORS_TABLE_NAME = 'ugc_errors'
     self.CONSERVATIONS_TABLE_NAME = 'ugc_conservations'
     
     if anchor_all:
         self.FORMATION_ENERGY_FILENAME = '../data/thermodynamics/formation_energies_anchor_all.csv'
     else:
         self.FORMATION_ENERGY_FILENAME = '../data/thermodynamics/formation_energies.csv'

    def GetForamtionEnergies(self, thermo):
        self.db.CreateTable(self.GIBBS_ENERGY_TABLE_NAME, "equation TEXT, dG0 REAL, dGc REAL", drop_if_exists=True)
        self.db.CreateIndex('gibbs_equation_idx', self.GIBBS_ENERGY_TABLE_NAME, 'equation', unique=True, drop_if_exists=True)

        all_equations = set()
        for row in self.db.Execute("SELECT distinct(equation) FROM %s" % 
                                   (self.EQUATION_TABLE_NAME)):
            all_equations.add(str(row[0]))
        
        from pygibbs.kegg import Kegg
        kegg = Kegg.getInstance()
        all_kegg_cids = set(kegg.get_all_cids())
        for equation in all_equations:
            try:
                rxn = Reaction.FromFormula(equation)
                if not rxn.get_cids().issubset(all_kegg_cids):
                    raise KeggNonCompoundException
                rxn.Balance(balance_water=True, exception_if_unknown=True)
                dG0 = thermo.GetTransfromedKeggReactionEnergies([rxn], conc=1)[0, 0]
                dGc = thermo.GetTransfromedKeggReactionEnergies([rxn], conc=1e-3)[0, 0]
                self.db.Insert(self.GIBBS_ENERGY_TABLE_NAME, [equation, dG0, dGc])
                
            except (KeggParseException, KeggNonCompoundException, KeggReactionNotBalancedException):
                self.db.Insert(self.GIBBS_ENERGY_TABLE_NAME, [equation, None, None])
    
        self.db.Commit()

    def GetJSONDictionary(self):
        """Returns a JSON formatted thermodynamic data."""
        kegg = Kegg.getInstance()
        formations = []
        for cid in self.get_all_cids():
            h = {}
            h['cid'] = cid
            try:
                h['name'] = kegg.cid2name(h['cid'])
            except KeyError:
                h['name'] = None
            try:
                h['inchi'] = kegg.cid2inchi(h['cid'])
            except KeyError:
                h['inchi'] = None
            try:
                h['num_electrons'] = kegg.cid2num_electrons(h['cid'])
            except KeggParseException:
                h['num_electrons'] = None

            h['source'] = self.cid2source_string.get(cid, None)
            h['species'] = []
            for nH, z, nMg, dG0 in self.cid2PseudoisomerMap(cid).ToMatrix():
                h['species'].append({"nH":nH, "z":z, "nMg":nMg, "dG0_f":dG0})
            formations.append(h)
        
        return formations

 def __init__(self, S, reaction_ids, compound_ids,
              fluxes=None, name=None):
     """Initialize the stoichiometric model.
     
     Args:
         S: the stoichiometrix matrix.
            Reactions are on the rows, compounds on the columns.
         reaction_ids: the ids/names of the reactions (rows).
         compound_ids: the ids/names of the compounds (columns).
         fluxes: the list of relative fluxes through all reactions.
                 if not supplied, assumed to be 1.0 for all reactions.
         name: a string name for this model.
     """
     self.kegg = Kegg.getInstance()
     self.S = S
     self.reaction_ids = reaction_ids
     self.compound_ids = compound_ids
     self.Nr = len(self.reaction_ids)
     self.Nc = len(self.compound_ids)
     self.name = name
     self.slug_name = util.slugify(self.name)
     
     self.fluxes = np.array(fluxes)
     if fluxes is None:
         self.fluxes = np.ones((1, self.Nr))
     
     expected_Nc, expected_Nr = self.S.shape
     if self.Nr != expected_Nr:
         raise ValueError('Number of columns does not match number of reactions')
     if self.Nc != expected_Nc:
         raise ValueError('Number of rows does not match number of compounds')
     
     if self.fluxes is None:
         self.fluxes = np.ones((self.Nr, 1))