#!/usr/local2/bin/python
import os, string
from openeye.oechem import *

aa = open('d_amino_acids.smi', 'r')
dnum = []
for line in aa.readlines():
    dnum.append(int(string.split(line)[0]))
aa.close()

ifs = oemolistream()
ifs.open('amino_acids.smi')
ifs2 = oemolistream()
ifs2.open('/raid1/people/joha/DB/1_KEGG2SDF/a_kegg_filter_5.sdf')
ofs_3 = oemolostream()
ofs_3.open('a_aa_outofkegg.sdf')
aa_dict = {}

for aa in ifs.GetOEMols():
    aa_dict[OECreateCanSmiString(aa)] = [aa.GetTitle(),0]
count = 0

for mol in ifs2.GetOEMols():
    key = OECreateCanSmiString(mol)
    if aa_dict.has_key(key):
        print dnum, int(mol.GetTitle()[1:])
        count+=1
        title = aa_dict[key][0]
        #ofs_3.open('a_'+title+'_'+mol.GetTitle()+'.mol2')
        # The first one is always S-configurated
        if aa_dict[key][1] == 0 and int(mol.GetTitle()[1:]) not in dnum and aa_dict[key][0] != 'Glycine':
            mol.SetTitle('L-'+title)
            OEWriteMolecule(ofs_3, mol)
            aa_dict[key][1] = 1
        elif aa_dict[key][1] == 1 and int(mol.GetTitle()[1:]) in dnum: 
            mol.SetTitle('D-'+title)
            OEWriteMolecule(ofs_3, mol)
            aa_dict[key][1] = 2
        elif aa_dict[key][1] == 0 and aa_dict[key][0] == 'Glycine': 
            mol.SetTitle(title)
            OEWriteMolecule(ofs_3, mol)
            aa_dict[key][1] = 1
print count