From drug NAME to SMILE string

readme

Invoke like this:

```bash
python GetSmiles.py oli_drugs.txt
```

getSmiles.py

import pubchempy as pcp
import pandas as pd
import numpy as np
from collections import OrderedDict

drugs_df = pd.read_csv('oli_drugs.csv')

def queryPubChem(compounds,batchlist = None,match='name'):
    """
    This function queries the PubChem database to retrieve both the isomeric smile and CID of a compound.

    You may need to be run in batches to not overload pubchem causing query failure. You can input a previous output to continue from.

    Inputs:
    compounds = pandas series containing compound names for query
    batchlist (optional) = output of a previous run

    Output:
    a list containing two dictionaries. First is compound name to SMILE mapping, second is CID mapping.
    """
    if batchlist == None:
        Iso_SMILE = OrderedDict()
        Can_SMILE = OrderedDict()
        ik = OrderedDict()
        CID = OrderedDict()
    else:
        SMILE = batchlist[0]
        CID = batchlist[1]
    multi = 0
    cnt = 0
    print("Retrieving compound information for " +str(compounds['0'].nunique()) + " compounds...")
    for i in compounds['0']:
        cpd = pcp.get_compounds(i,match)
        cnt+=1
        if len(cpd) > 1:
            multi+=1
        if cnt in [100,500,1000,2000,5000,10000]:
            print("processing... "+ str(cnt))
        if len(cpd) != 0:
            Iso_SMILE[i] = cpd[0].isomeric_smiles
            Can_SMILE[i] = cpd[0].canonical_smiles
            ik[i] = cpd[0].inchikey
            CID[i] = cpd[0].cid
        else:
            Iso_SMILE[i] = ""
            Can_SMILE[i] = ""
            ik[i] = ""
            CID[i] = ""
    print("##########")
    print("COMPLETE!")
    print("A total of " + str(multi) + " had multiple IDs matching. First matches were recorded.")
    results = pd.DataFrame([Iso_SMILE, Can_SMILE, CID, ik]).transpose()
    results.to_csv('oli_result.csv', sep="\t")

if __name__ == '__main__':
    queryPubChem(drugs_df)

oli_drugs.csv

oli_result.csv

	0	1	2
Cisplatin	N.N.Cl[Pt]Cl	N.N.Cl[Pt]Cl	5702198
camptothecin	CC[C@@]1(C2=C(COC1=O)C(=O)N3CC4=CC5=CC=CC=C5N=C4C3=C2)O	CCC1(C2=C(COC1=O)C(=O)N3CC4=CC5=CC=CC=C5N=C4C3=C2)O	24360
Etoposide	C[C@@H]1OC[C@@H]2[C@@H](O1)[C@@H]([C@H]([C@@H](O2)O[C@H]3[C@H]4COC(=O)[C@@H]4[C@@H](C5=CC6=C(C=C35)OCO6)C7=CC(=C(C(=C7)OC)O)OC)O)O	CC1OCC2C(O1)C(C(C(O2)OC3C4COC(=O)C4C(C5=CC6=C(C=C35)OCO6)C7=CC(=C(C(=C7)OC)O)OC)O)O	36462
HU	C(=O)(N)NO	C(=O)(N)NO	3657
IR	[Ir]	[Ir]	23924
Doxorubicin	C[C@H]1[C@H]([C@H](C[C@@H](O1)O[C@H]2C[C@@](CC3=C2C(=C4C(=C3O)C(=O)C5=C(C4=O)C(=CC=C5)OC)O)(C(=O)CO)O)N)O	CC1C(C(CC(O1)OC2CC(CC3=C2C(=C4C(=C3O)C(=O)C5=C(C4=O)C(=CC=C5)OC)O)(C(=O)CO)O)N)O	31703
H2O2	OO	OO	784
MMS	COS(=O)(=O)C	COS(=O)(=O)C	4156
Pyridostatin	C1=CC=C2C(=C1)C(=CC(=N2)NC(=O)C3=CC(=CC(=N3)C(=O)NC4=NC5=CC=CC=C5C(=C4)OCCN)OCCN)OCCN	C1=CC=C2C(=C1)C(=CC(=N2)NC(=O)C3=CC(=CC(=N3)C(=O)NC4=NC5=CC=CC=C5C(=C4)OCCN)OCCN)OCCN	25227847
UV	CC[C@@H](C=O)NC(=O)[C@H](CC)NC(=O)[C@H](CC)NC(=O)[C@H](CC)NC(=O)[C@H](CC)NC(=O)[C@H](CC)NC(=O)[C@H](CC)NC(=O)[C@H](CC)N	CCC(C=O)NC(=O)C(CC)NC(=O)C(CC)NC(=O)C(CC)NC(=O)C(CC)NC(=O)C(CC)NC(=O)C(CC)NC(=O)C(CC)N	155487962
Bleomycin	CC1=C(N=C(N=C1N)[C@H](CC(=O)N)NC[C@@H](C(=O)N)N)C(=O)N[C@@H]([C@H](C2=CN=CN2)OC3C(C(C(C(O3)CO)O)O)OC4C(C(C(C(O4)CO)O)OC(=O)N)O)C(=O)N[C@H](C)[C@H]([C@H](C)C(=O)N[C@@H]([C@@H](C)O)C(=O)NCCC5=NC(=CS5)C6=NC(=CS6)C(=O)NCCC[S+](C)C)O	CC1=C(N=C(N=C1N)C(CC(=O)N)NCC(C(=O)N)N)C(=O)NC(C(C2=CN=CN2)OC3C(C(C(C(O3)CO)O)O)OC4C(C(C(C(O4)CO)O)OC(=O)N)O)C(=O)NC(C)C(C(C)C(=O)NC(C(C)O)C(=O)NCCC5=NC(=CS5)C6=NC(=CS6)C(=O)NCCC[S+](C)C)O	5360373
Olaparib	C1CC1C(=O)N2CCN(CC2)C(=O)C3=C(C=CC(=C3)CC4=NNC(=O)C5=CC=CC=C54)F	C1CC1C(=O)N2CCN(CC2)C(=O)C3=C(C=CC(=C3)CC4=NNC(=O)C5=CC=CC=C54)F	23725625
AZD6738	C[C@@H]1COCCN1C2=NC(=NC(=C2)C3(CC3)[S@](=N)(=O)C)C4=C5C=CNC5=NC=C4	CC1COCCN1C2=NC(=NC(=C2)C3(CC3)S(=N)(=O)C)C4=C5C=CNC5=NC=C4	54761306
ICRF			
Formaldehyde	C=O	C=O	712
PhenDC3	C[N+]1=CC(=CC2=CC=CC=C21)NC(=O)C3=NC4=C(C=CC5=C4N=C(C=C5)C(=O)NC6=CC7=CC=CC=C7[N+](=C6)C)C=C3.C(F)(F)(F)S(=O)(=O)[O-].C(F)(F)(F)S(=O)(=O)[O-]	C[N+]1=CC(=CC2=CC=CC=C21)NC(=O)C3=NC4=C(C=CC5=C4N=C(C=C5)C(=O)NC6=CC7=CC=CC=C7[N+](=C6)C)C=C3.C(F)(F)(F)S(=O)(=O)[O-].C(F)(F)(F)S(=O)(=O)[O-]	131704505
Duocarmycin			
Trabectedin	CC1=CC2=C([C@@H]3[C@@H]4[C@H]5C6=C(C(=C7C(=C6[C@@H](N4[C@H]([C@H](C2)N3C)O)COC(=O)[C@@]8(CS5)C9=CC(=C(C=C9CCN8)O)OC)OCO7)C)OC(=O)C)C(=C1OC)O	CC1=CC2=C(C3C4C5C6=C(C(=C7C(=C6C(N4C(C(C2)N3C)O)COC(=O)C8(CS5)C9=CC(=C(C=C9CCN8)O)OC)OCO7)C)OC(=O)C)C(=C1OC)O	108150
Calicheamicin	CCN[C@H]1CO[C@H](C[C@@H]1OC)O[C@@H]2[C@H]([C@@H]([C@H](O[C@H]2O[C@H]3C#C/C=C\C#C[C@@]\4(CC(=O)C(=C3/C4=C/CSSSC)NC(=O)OC)O)C)NO[C@H]5C[C@@H]([C@@H]([C@H](O5)C)SC(=O)C6=C(C(=C(C(=C6OC)OC)O[C@H]7[C@@H]([C@@H]([C@H]([C@@H](O7)C)O)OC)O)I)C)O)O	CCNC1COC(CC1OC)OC2C(C(C(OC2OC3C#CC=CC#CC4(CC(=O)C(=C3C4=CCSSSC)NC(=O)OC)O)C)NOC5CC(C(C(O5)C)SC(=O)C6=C(C(=C(C(=C6OC)OC)OC7C(C(C(C(O7)C)O)OC)O)I)C)O)O	101617325
Gemcitabine	C1=CN(C(=O)N=C1N)[C@H]2C([C@@H]([C@H](O2)CO)O)(F)F	C1=CN(C(=O)N=C1N)C2C(C(C(O2)CO)O)(F)F	60750
illudinS			
MLN4924	C1CC2=CC=CC=C2[C@H]1NC3=C4C=CN(C4=NC=N3)[C@@H]5C[C@H]([C@H](C5)O)COS(=O)(=O)N	C1CC2=CC=CC=C2C1NC3=C4C=CN(C4=NC=N3)C5CC(C(C5)O)COS(=O)(=O)N	16720766
MNNG	CN(C(=N)N[N+](=O)[O-])N=O	CN(C(=N)N[N+](=O)[O-])N=O	135436526
KBrO3			
CD437	C1C2CC3CC1CC(C2)(C3)C4=C(C=CC(=C4)C5=CC6=C(C=C5)C=C(C=C6)C(=O)O)O	C1C2CC3CC1CC(C2)(C3)C4=C(C=CC(=C4)C5=CC6=C(C=C5)C=C(C=C6)C(=O)O)O	135411
BPDE	C1=CC2=C3C(=C1)C=CC4=C3C(=CC5=C4C6C(O6)C(C5O)O)C=C2	C1=CC2=C3C(=C1)C=CC4=C3C(=CC5=C4C6C(O6)C(C5O)O)C=C2	41322
HU2	CCC[C@@H](C(C(=O)NCC(=O)N[C@@H](C1=CC=CC=C1)C(=O)O)(O)O)NC(=O)[C@H](CC(C)C)NC(=O)[C@@H](CCCCC(C)C)C(C)C	CCCC(C(C(=O)NCC(=O)NC(C1=CC=CC=C1)C(=O)O)(O)O)NC(=O)C(CC(C)C)NC(=O)C(CCCCC(C)C)C(C)C	16741223
PladB