#functions to help visualise output

from rdkit import Chem
from rdkit.Chem.Draw import IPythonConsole
from rdkit.Chem import Draw
from rdkit.Chem import AllChem

def depict(input):
    if(">>" in input):
        rxn = AllChem.ReactionFromSmarts(input)       
        return Draw.ReactionToImage(rxn)
    else:
        temp = Chem.MolFromSmiles(input)
        return temp
    
def showFile(in_file):
    fo = open(in_file, "r")
    
    mols=[]
    ids=[]
    n=0
    for line in fo:
        if(n < 10):
            smi,id = line.rstrip().split()
            mols.append( Chem.MolFromSmiles(smi) )
            ids.append(id)
        n=n+1
    
    return Draw.MolsToGridImage(mols,molsPerRow=5,legends=ids)

def showMMPs(in_file):
    fo = open(in_file, "r")
    
    mols=[]
    trans=[]
    n=0
    for line in fo:
        if(n < 9):
            m1,m2,id1,id2,t,c = line.rstrip().split(",")
            smi = "%s.%s" % (m1,m2)
            mols.append( Chem.MolFromSmiles(smi) )
            trans.append(t)
        n=n+1
    
    return Draw.MolsToGridImage(mols,molsPerRow=3,subImgSize= ( 300 , 300 ) ,legends=trans)

def showLine(in_string):
    f = in_string.split(",")
    
    rxn =f[-2].split(">>")      
        
    mols=[]
    ids=[]
    
    mols.append( Chem.MolFromSmiles(f[-6]) )
    mols.append( Chem.MolFromSmiles(f[-5]) )
    mols.append( Chem.MolFromSmiles(rxn[0]) )
    mols.append( Chem.MolFromSmiles(rxn[1]) )
    mols.append( Chem.MolFromSmiles(f[-1]) )
    ids.append(f[-3])
    ids.append(f[-4])
    ids.append("LHS")  
    ids.append("RHS")  
    ids.append("CONTEXT")  
    
    return Draw.MolsToGridImage(mols,molsPerRow=6,legends=ids)

cd t1_files/

ls

!wc -l sample.smi

!head sample.smi

showFile('sample.smi')

!python $RDBASE/Contrib/mmpa/rfrag.py <sample.smi >out_fragmented.txt

!head out_fragmented.txt

!python $RDBASE/Contrib/mmpa/indexing.py <out_fragmented.txt >out_mmps_default.csv

!head out_mmps_default.csv

showLine("Cc1cccn2cc(-c3cccc(S(=O)(=O)N4CCCCC4)c3)nc12,Cc1cccn2cc(-c3ccc(S(=O)(=O)N4CCCCC4)cc3)nc12,2963575,1156028,[*:1]c1cccc([*:2])c1>>[*:1]c1ccc([*:2])cc1,[*:1]c1cn2cccc(C)c2n1.[*:2]S(=O)(=O)N1CCCCC1")

showMMPs("out_mmps_default.csv")

!python $RDBASE/Contrib/mmpa/indexing.py -m 3 <out_fragmented.txt

showLine("Nc1ccc(-c2cc3ccccc3oc2=O)cc1,O=c1oc2ccccc2cc1-c1ccc(O)cc1,310860,4055843,[*:1]N>>[*:1]O,[*:1]c1ccc(-c2cc3ccccc3oc2=O)cc1")

!python $RDBASE/Contrib/mmpa/indexing.py -r 0.1 <out_fragmented.txt

showLine("Nc1ccc(-c2cc3ccccc3oc2=O)cc1,O=c1oc2ccccc2cc1-c1ccc(O)cc1,310860,4055843,[*:1]N>>[*:1]O,[*:1]c1ccc(-c2cc3ccccc3oc2=O)cc1")

!python $RDBASE/Contrib/mmpa/indexing.py -r 0.1 -s <out_fragmented.txt >out_mmps_sym.csv

!head out_mmps_sym.csv
showMMPs("out_mmps_sym.csv")

depict("[*:2]c1ccc([*:1])o1>>[*:1]c1ccc([*:2])cc1")

depict("[*:1]c1ccc([*:2])o1>>[*:2]c1ccc([*:1])cc1")

!head sample_smirks.txt

!python $RDBASE/Contrib/mmpa/cansmirk.py <sample_smirks.txt

!head sample_smirks_mol_trans.txt

depict("[*:1]C(=O)O>>[*:1]C(N)=O")

!head sample_smiles_mol_trans.smi

depict("O=C(O)c1ccc(NC(=O)C2COc3ccccc3O2)cc1")

!python $RDBASE/Contrib/mmpa/mol_transform.py -f sample_smirks_mol_trans.txt <sample_smiles_mol_trans.smi

depict("NC(=O)c1ccc(NC(=O)C2COc3ccccc3O2)cc1")