Python script for Windows:
from rdkit import Chem
from rdkit.Chem import Descriptors
from rdkit.Chem import rdMolDescriptors
# List of molecules in SMILES format with names
molecules = [
("Fc1ccc2cc1C(=O)N[C@H]1CN(C[C@@H]1Oc1ccc(CNC(=O)COc3cccc2c3)cc1)C(=O)c1cnncc1", "MolPort-051-704-251"),
("CS(=O)(=O)c1ccc(CN2CCN3C[C@@H]2C(=O)N2CC[C@@H](CC2)N2CCC[C@H]2C(=O)NC2(CCN(CC2)C(=O)c2ccc(F)cc2)CC3=O)cc1", "MolPort-047-146-537"),
("Cc1ccc(cc1NC(=O)c1ccc2C(=O)c3ccccc3S(=O)(=O)c2c1)n1cnnn1", "MolPort-016-317-936"),
("Cc1nn(CC(=O)N2C[C@@H]3NC(=O)c4cc(ccc4F)c4cc(OCC(=O)NCc5ccc(O[C@H]3C2)cc5)ccc4)c(C)n1", "MolPort-051-711-095"),
("CCOC(=O)C(=P(c1ccccc1)(c1ccccc1)c1ccccc1)/N=N/c1nc2c([nH]1)c(=O)n(C)c(=O)n2C", "MolPort-003-875-006"),
("Cc1nnc(NN/C=C/2C(=O)N(C(=O)c3ccccc23)c2cccc(c2)C(F)(F)F)[nH]c1=O", "MolPort-005-845-260"),
("O=C(Nc1ccc2OCCCOc2c1)c1cccc(c1)S(=O)(=O)Nc1cccc(c1)n1cnnn1", "MolPort-005-780-546"),
("FC(F)(F)c1cc2c(OC[C@@H]3CN(CCN3C(=O)[C@@H]3C[C@H](CN3C2=O)OCc2cn(nn2)c2cccnc2)C2CCOCC2)cc1", "MolPort-047-146-805"),
("Cc1cc(no1)C(=O)N1C[C@@H]2NC(=O)CN(CCCCOc3cccc(c3)[C@H]2C1)C(=O)c1cc2c(OCC2)cc1", "MolPort-051-537-866"),
("OC(=O)c1cccc(c1)c1ccc(o1)/C=N/Nc1nc(nc(n1)N1CCOCC1)N1CCOCC1", "MolPort-019-736-907"),
("Fc1ccc(cc1NC(=O)c1ccc2c(=O)n(Cc3ccco3)c(=O)c2c1)n1cnnn1", "MolPort-016-351-790"),
("Cc1cc(no1)C(=O)N1C[C@@H]2NC(=O)CN(CCCCOc3cccc(c3)[C@H]2C1)C(=O)c1cc2c(OCC2)cc1", "MolPort-051-537-867"),
("Cc1ccc(C)c(c1)N1N=C(CCC1=O)C(=O)N1CCN(CC1)S(=O)(=O)c1cc(F)ccc1F", "MolPort-015-311-581"),
("OC(=O)c1cccc(c1)c1ccc(o1)/C=N/Nc1nc(nc(n1)N1CCOCC1)N1CCCOC1", "MolPort-002-324-981"),
("O=c1[nH]c(=O)c(=Cc2ccc(o2)c2ccc3c(=O)c4ccccc4c(=O)c3c2)c(=O)[nH]1", "MolPort-018-497-786"),
("Cc1ccc2N(C(=O)N(c2c1)S(=O)(=O)c1ccc(F)cc1)S(=O)(=O)c1ccc(F)cc1", "MolPort-000-645-425"),
("COc1c2OCCCNC(=O)c3cc(Oc4ccc5[C@@H](N(CCc5c4)S(=O)(=O)c4cn(C)c(=O)n(C)c4=O)c(cc1)c2)ccc3F", "MolPort-051-706-687"),
("O=C(Nc1cccc(c1)n1cnnn1)[C@@H]1CCN(CC1)C1=NS(=O)(=O)c2ccccc12", "MolPort-005-327-526"),
("Cc1ccc(C)c(c1)N1N=C(CCC1=O)C(=O)N1CCN(CC1)S(=O)(=O)c1ccc(F)cc1", "MolPort-009-502-131"),
("O=C(N1C[C@H]2C[C@@H]1C(=O)NCC[C@H]1CN(CC[C@H]1CC(=O)N1CC[C@H](CC1)N1CCC[C@H]1C(=O)N2)C1CCOCC1)c1ccccc1", "MolPort-047-146-646"),
("CNC(=O)c1nccc(c1)C(=O)N[C@@H]1CCc2nc3ncc(cc3cc2C1)c1cncnc1", "MolPort-050-857-090"),
("COC(=O)[C@H]1C[C@H]2CN(CC(=O)N2[C@H]1c1ccccc1)C(=O)c1n[nH]c(c1)n1cnnn1", "MolPort-047-597-539"),
("O=C(Nc1ccc(NS(=O)(=O)c2ccc3OCCOc3c2)cc1)c1cccc(c1)n1cnnn1", "MolPort-005-791-198"),
("Fc1ccc(CN2N=C(CCC2=O)C(=O)Nc2cccc(c2)c2noc(=O)[nH]2)cc1MolPort-027-974-229", "MolPort-027-974-229"),
("Cc1c2OCC(=O)NCc3ccc(O[C@H]4CCN(C[C@@H]4NC(=O)c(cc1)c2)c1nccc(c1)C#N)cc3", "MolPort-051-504-308"),
("Cn1c2c(c(c([nH]2)c2cc3c(OCCO3)cc2)c2c(n3cccc3)n(C)c(=O)n(C)c2=O)c(=O)n(C)c1=O", "MolPort-010-755-462"),
("Cc1c2OCC(=O)NCc3ccc(O[C@H]4CCN(C[C@@H]4NC(=O)c(cc1)c2)c1ncc(cc1)C#N)cc3", "MolPort-051-505-109"),
("CNC(=O)c1cccc(NC(=O)c2ccc(OC)c(c2)S(=O)(=O)N2CCCCCC2)c1", "MolPort-019-471-102"),
("Cc1ccc(cc1NC(=O)c1cccc(c1)S(=O)(=O)N1CCNC(=O)C1)n1cnnn1", "MolPort-016-318-066"),
("O=C([C@H](C#N)c1nc2ccccc2c(=O)[nH]1)c1ccc2C(=O)c3ccccc3S(=O)(=O)c2c1", "MolPort-047-768-807"),
("O=C([C@H]1C[C@]21C(=O)Nc1c2cccc1)N1CC2(CCCC2)c2c1ccc(c2)C(=O)N1CC[C@@]2(C1)NC(=O)NC2=O", "MolPort-051-592-471"),
("OC(=O)/C=C/c1ccc(cc1)S(=O)(=O)Nn1c(=O)/c(=C/c2ccco2)/nc1c1ccccc1", "MolPort-003-873-516"),
("Nc1n[nH]c2ccc(cc12)c1cccc(c1)C(=O)N1C[C@H]2COC[C@@H](C1)C(=O)N2", "MolPort-051-750-878"),
("Cn1c2c(c(c([nH]2)c2cc3c(OCO3)cc2)c2c(n3cccc3)n(C)c(=O)n(C)c2=O)c(=O)n(C)c1=O", "MolPort-007-698-991"),
("COC(=O)c1ccc(CNC(=O)c2cccc(NS(=O)(=O)c3ccc4OCCOc4c3)c2)cc1", "MolPort-004-482-921"),
("Cc1ccc(cc1NC(=O)c1ccc(C)c(c1)S(=O)(=O)N1CCCCC1)n1cnnn1", "MolPort-010-354-128"),
("O=C(Nc1cccc(c1)n1cnnn1)c1ccc2c(=O)n(Cc3ccco3)c(=O)c2c1", "MolPort-005-767-802"),
("O=C(Nc1cccc(c1)n1cnnn1)c1cccc(c1)S(=O)(=O)N1CCN(CC1)c1ccccc1", "MolPort-019-471-867"),
("COc1ccc(Cn2c(=O)c3ccccc3c2=O)cc1C(=O)Nc1cc(ccc1F)n1cnnn1", "MolPort-016-351-793"),
("Cc1ccc(cc1NC(=O)c1cccc(CN2C(=O)CNC2=O)c1)n1cnnn1", "MolPort-016-318-061"),
("Cc1ccc(cc1NC(=O)C1CCN(CC1)S(=O)(=O)c1ccc(cc1)C#N)n1cnnn1", "MolPort-016-317-952"),
("Oc1ccc(cn1)C(=O)NNC(=O)c1cccc(c1)S(=O)(=O)Nc1cccc(c1)C(F)(F)F", "MolPort-019-485-069"),
("COc1ccc(cc1S(=O)(=O)N1CCOCC1)C(=O)Nc1cc(NC(=O)C2CC2)ccc1C", "MolPort-007-540-817"),
("CCOC(=O)c1nn(cc1)c1cccc(NC(=O)C2=NN(C(=O)CN2)c2ccc(C)cc2)c1", "MolPort-016-529-703"),
("O=C(Nc1cccc(c1)c1nnn[nH]1)c1ccc2c(=O)n3CCCCCc3nc2c1", "MolPort-005-754-412"),
("CNC(=O)c1cccc(NC(=O)c2ccc(F)c(c2)S(=O)(=O)N2CCCCC2)c1", "MolPort-010-285-351"),
("CC(=O)Nc1ccc(C)c(NC(=O)C2CCN(CC2)S(=O)(=O)c2ccccc2)c1", "MolPort-007-499-937"),
("CNC(=O)c1cccc(NC(=O)c2nn(C)c(NC(=O)CCc3ccccc3)c2)c1", "MolPort-008-196-016"),
("Fc1ccc(cc1NC(=O)c1ccc(NS(=O)(=O)c2cccs2)cc1)n1cnnn1", "MolPort-016-355-012"),
("Fc1ccc(Cn2c(=O)c(Cc3ccccc3)cc3c2CCN(C3)C(=O)c2n[nH]c(=O)[nH]2)cc1", "MolPort-004-983-373"),
("Cc1ccc(cc1NC(=O)c1cccc(CN2C(=O)CSC2=O)c1)n1cnnn1", "MolPort-016-318-051"),
("CNC(=O)c1cccc(NC(=O)c2cccc(c2)S(=O)(=O)N2CCN(CC2)c2ccccc2)c1", "MolPort-019-471-016"),
("O=C(Cn1c(=O)c2c(sc3c2CCC3)nc1N1CCN(CC(=O)N2CC2)CC1)Nc1cccc2ccccc12", "MolPort-006-683-342"),
("NC(=O)c1cc(NC(=O)c2ccc3C(=O)c4ccccc4S(=O)(=O)c3c2)ccc1F", "MolPort-009-185-968"),
("Cc1ccc(cc1C)S(=O)(=O)N1CCC(CC1)C(=O)Nc1cc(ccc1F)n1cnnn1", "MolPort-016-351-789"),
("CC(=O)c1ccc(cc1)S(=O)(=O)N1CCC(CC1)C(=O)Nc1cccc(c1)n1cnnn1", "MolPort-019-471-949"),
("CN(C)S(=O)(=O)c1cc(cc(C)c1C)C(=O)Nc1cc(ccc1F)n1cnnn1", "MolPort-016-351-916"),
("Cc1ccc(cc1S(=O)(=O)N1CCCCC1)C(=O)Nc1cccc(c1)n1cnnn1", "MolPort-018-270-599"),
("OC(=O)Cc1csc(NC(=O)c2cccc(c2)S(=O)(=O)N2CCc3ccccc3C2)n1", "MolPort-005-406-336"),
("Cc1ccc(cc1NC(=O)c1ccc(F)c(c1)S(=O)(=O)N1CCCCC1)n1cnnn1", "MolPort-016-317-991"),
("O=C(N1CCN(CC1)C(=O)c1cc(Nc2nc3ccccc3n3nnnc23)ccc1)c1ccco1", "MolPort-007-757-935"),
("OC(=O)c1cc(NS(=O)(=O)c2ccc3c(=O)c4ccccc4c(=O)c3c2)ccc1O", "MolPort-002-363-292"),
("NC(=O)CNC(=O)c1cccc(NC(=O)c2ccc3c(=O)n(Cc4ccccc4)c(=O)c3c2)c1", "MolPort-007-474-755"),
("CS(=O)(=O)c1nc(C(=O)Nc2cc(ccc2F)n2cnnn2)c2ccccn12", "MolPort-015-759-447"),
("COC(=O)c1cccc(c1)C#Cc1cccc(NS(=O)(=O)c2ccc(cc2)S(=O)(=O)N(C)C)c1", "MolPort-005-728-204"),
("[H]N1C([H])=C(C2=C1C([H])=C([H])C([H])=C2[H])C([H])([H])[C@@]1([H])N([H])[C@]2(C(=O)N([H])C3=C2C([H])=C(Cl)C([H])=C3[H])[C@@]2([H])C(=O)N(C(=O)[C@@]12[H])C1=C([H])C([H])=C2OC([H])([H])C([H])([H])OC2=C1[H]", "PHAR-ISO1"),
("[H]N1C([H])=C(C2=C1C([H])=C([H])C([H])=C2[H])C([H])([H])[C@]1([H])N([H])[C@@]2(C(=O)N([H])C3=C2C([H])=C(Cl)C([H])=C3[H])[C@]2([H])C(=O)N(C(=O)[C@]12[H])C1=C([H])C([H])=C2OC([H])([H])C([H])([H])OC2=C1[H]", "PHAR-ISO2"),
("COc1cc(N[C@H]2C[C@H](C2)c2cc(=O)[nH]c(n2)N2CCCC2)nc(N)n1MolPort-038-389-925", "MolPort-038-389-925"),
("O=C(Nc1cccc(c1)c1nnco1)c1cccc(c1)S(=O)(=O)N1CCCC1MolPort-035-515-658", "MolPort-035-515-658"),
("O=C(CNC(=O)c1ccco1)Nc1cccc(c1)S(=O)(=O)/N=C1/CCCCCN1MolPort-039-260-233", "MolPort-039-260-233"),
("C[C@H]1NC(=O)c2c(OCCCn3cc(CN(CCCNC1=O)C(=O)Cc1ccc4OCOc4c1)nn3)cc(C)cc2", "MolPort-046-570-315"),
("O=C(NCc1nnn[nH]1)c1cccc(c1)c1ccc(o1)C(=O)N1CCCCC1", "MolPort-042-625-092"),
]
# Create a list to store molecular properties
molecule_data = []
for smiles, name in molecules:
mol = Chem.MolFromSmiles(smiles) # Convert SMILES to RDKit Mol object
if mol:
# Calculate molecular descriptors
logp = Descriptors.MolLogP(mol) # LogP: hydrophobicity (lower = more polar)
tpsa = Descriptors.TPSA(mol) # Polar Surface Area (PSA)
mw = Descriptors.MolWt(mol) # Molecular Weight (MW)
rot_bonds = Descriptors.NumRotatableBonds(mol) # Number of rotatable bonds
arom_rings = rdMolDescriptors.CalcNumAromaticRings(mol) # Number of aromatic rings
h_acceptors = Descriptors.NumHAcceptors(mol) # Number of hydrogen bond acceptors
h_donors = Descriptors.NumHDonors(mol) # Number of hydrogen bond donors
# Append the calculated properties to the list
molecule_data.append((name, smiles, logp, tpsa, mw, rot_bonds, arom_rings, h_acceptors, h_donors))
# Sort the list by LogP (relative polarity)
# sorted_by_logp = sorted(molecule_data, key=lambda x: x[2])
sorted_by_tpsa = sorted(molecule_data, key=lambda x: x[3])
# Display results
print(f"{'Name':<20} {'LogP':<8} {'PSA':<8} {'MW':<8} {'RotB':<6} {'AromR':<6} {'H-Accept':<10} {'H-Donors':<10} SMILES")
print("=" * 80)
for name, smiles, logp, tpsa, mw, rot_bonds, arom_rings, h_acceptors, h_donors in sorted_by_tpsa:
print(f"{name:<20} {logp:<8.2f} {tpsa:<8.2f} {mw:<8.2f} {rot_bonds:<6} {arom_rings:<6} {h_acceptors:<10} {h_donors:<10} {smiles}")
See the results:
Name LogP TPSA MW RotB AromR H-Accept H-Donors SMILES
================================================================================
MolPort-015-311-581 2.60 90.36 490.53 4 2 5 0 Cc1ccc(C)c(c1)N1N=C(CCC1=O)C(=O)N1CCN(CC1)S(=O)(=O)c1cc(F)ccc1F
MolPort-009-502-131 2.46 90.36 472.54 4 2 5 0 Cc1ccc(C)c(c1)N1N=C(CCC1=O)C(=O)N1CCN(CC1)S(=O)(=O)c1ccc(F)cc1
MolPort-006-683-342 2.70 90.55 542.67 6 4 8 1 O=C(Cn1c(=O)c2c(sc3c2CCC3)nc1N1CCN(CC(=O)N2CC2)CC1)Nc1cccc2ccccc12
MolPort-000-645-425 2.86 95.21 464.47 4 4 7 0 Cc1ccc2N(C(=O)N(c2c1)S(=O)(=O)c1ccc(F)cc1)S(=O)(=O)c1ccc(F)cc1
MolPort-010-285-351 2.61 95.58 419.48 5 2 4 2 CNC(=O)c1cccc(NC(=O)c2ccc(F)c(c2)S(=O)(=O)N2CCCCC2)c1
MolPort-007-499-937 2.99 95.58 415.52 5 2 4 2 CC(=O)Nc1ccc(C)c(NC(=O)C2CCN(CC2)S(=O)(=O)c2ccccc2)c1
MolPort-019-471-016 2.81 98.82 478.57 6 3 5 2 CNC(=O)c1cccc(NC(=O)c2cccc(c2)S(=O)(=O)N2CCN(CC2)c2ccccc2)c1
MolPort-004-983-373 2.24 103.85 459.48 5 4 5 2 Fc1ccc(Cn2c(=O)c(Cc3ccccc3)cc3c2CCN(C3)C(=O)c2n[nH]c(=O)[nH]2)cc1
MolPort-019-471-102 2.87 104.81 445.54 6 2 5 2 CNC(=O)c1cccc(NC(=O)c2ccc(OC)c(c2)S(=O)(=O)N2CCCCCC2)c1
MolPort-008-196-016 2.60 105.12 405.46 7 3 5 3 CNC(=O)c1cccc(NC(=O)c2nn(C)c(NC(=O)CCc3ccccc3)c2)c1
MolPort-005-728-204 2.92 109.85 498.58 6 3 6 1 COC(=O)c1cccc(c1)C#Cc1cccc(NS(=O)(=O)c2ccc(cc2)S(=O)(=O)N(C)C)c1
MolPort-010-354-128 2.71 110.08 440.53 5 3 7 1 Cc1ccc(cc1NC(=O)c1ccc(C)c(c1)S(=O)(=O)N1CCCCC1)n1cnnn1
MolPort-016-318-051 2.42 110.08 408.44 5 3 8 1 Cc1ccc(cc1NC(=O)c1cccc(CN2C(=O)CSC2=O)c1)n1cnnn1
MolPort-016-351-789 2.46 110.08 458.52 5 3 7 1 Cc1ccc(cc1C)S(=O)(=O)N1CCC(CC1)C(=O)Nc1cc(ccc1F)n1cnnn1
MolPort-016-351-916 1.92 110.08 418.45 5 3 7 1 CN(C)S(=O)(=O)c1cc(cc(C)c1C)C(=O)Nc1cc(ccc1F)n1cnnn1
MolPort-018-270-599 2.40 110.08 426.50 5 3 7 1 Cc1ccc(cc1S(=O)(=O)N1CCCCC1)C(=O)Nc1cccc(c1)n1cnnn1
MolPort-016-317-991 2.54 110.08 444.49 5 3 7 1 Cc1ccc(cc1NC(=O)c1ccc(F)c(c1)S(=O)(=O)N1CCCCC1)n1cnnn1
PHAR-ISO1 3.76 112.76 554.99 3 4 6 3 [H]N1C([H])=C(C2=C1C([H])=C([H])C([H])=C2[H])C([H])([H])[C@@]1([H])N([H])[C@]2(C(=O)N([H])C3=C2C([H])=C(Cl)C([H])=C3[H])[C@@]2([H])C(=O)N(C(=O)[C@@]12[H])C1=C([H])C([H])=C2OC([H])([H])C([H])([H])OC2=C1[H]
PHAR-ISO2 3.76 112.76 554.99 3 4 6 3 [H]N1C([H])=C(C2=C1C([H])=C([H])C([H])=C2[H])C([H])([H])[C@]1([H])N([H])[C@@]2(C(=O)N([H])C3=C2C([H])=C(Cl)C([H])=C3[H])[C@]2([H])C(=O)N(C(=O)[C@]12[H])C1=C([H])C([H])=C2OC([H])([H])C([H])([H])OC2=C1[H]
MolPort-019-471-867 2.43 113.32 489.56 6 4 8 1 O=C(Nc1cccc(c1)n1cnnn1)c1cccc(c1)S(=O)(=O)N1CCN(CC1)c1ccccc1
MolPort-051-750-878 1.40 113.34 391.43 2 3 5 3 Nc1n[nH]c2ccc(cc12)c1cccc(c1)C(=O)N1C[C@H]2COC[C@@H](C1)C(=O)N2
MolPort-007-540-817 2.63 114.04 473.55 7 2 6 2 COc1ccc(cc1S(=O)(=O)N1CCOCC1)C(=O)Nc1cc(NC(=O)C2CC2)ccc1C
MolPort-051-537-866 2.96 114.21 544.61 2 3 7 1 Cc1cc(no1)C(=O)N1C[C@@H]2NC(=O)CN(CCCCOc3cccc(c3)[C@H]2C1)C(=O)c1cc2c(OCC2)cc1
MolPort-051-537-867 2.96 114.21 544.61 2 3 7 1 Cc1cc(no1)C(=O)N1C[C@@H]2NC(=O)CN(CCCCOc3cccc(c3)[C@H]2C1)C(=O)c1cc2c(OCC2)cc1
MolPort-047-146-646 1.87 114.53 648.85 2 1 7 2 O=C(N1C[C@H]2C[C@@H]1C(=O)NCC[C@H]1CN(CC[C@H]1CC(=O)N1CC[C@H](CC1)N1CCC[C@H]1C(=O)N2)C1CCOCC1)c1ccccc1
MolPort-047-146-805 2.57 115.15 641.65 5 3 10 0 FC(F)(F)c1cc2c(OC[C@@H]3CN(CCN3C(=O)[C@@H]3C[C@H](CN3C2=O)OCc2cn(nn2)c2cccnc2)C2CCOCC2)cc1
MolPort-051-504-308 2.73 116.58 497.56 1 3 7 2 Cc1c2OCC(=O)NCc3ccc(O[C@H]4CCN(C[C@@H]4NC(=O)c(cc1)c2)c1nccc(c1)C#N)cc3
MolPort-051-505-109 2.73 116.58 497.56 1 3 7 2 Cc1c2OCC(=O)NCc3ccc(O[C@H]4CCN(C[C@@H]4NC(=O)c(cc1)c2)c1ncc(cc1)C#N)cc3
MolPort-005-406-336 2.77 116.67 457.53 6 3 6 2 OC(=O)Cc1csc(NC(=O)c2cccc(c2)S(=O)(=O)N2CCc3ccccc3C2)n1
MolPort-042-625-092 2.02 117.01 380.41 5 3 6 2 O=C(NCc1nnn[nH]1)c1cccc(c1)c1ccc(o1)C(=O)N1CCCCC1
MolPort-016-529-703 2.25 117.92 446.47 6 3 8 2 CCOC(=O)c1nn(cc1)c1cccc(NC(=O)C2=NN(C(=O)CN2)c2ccc(C)cc2)c1
MolPort-005-754-412 2.56 118.45 401.43 3 4 7 2 O=C(Nc1cccc(c1)c1nnn[nH]1)c1ccc2c(=O)n3CCCCCc3nc2c1
MolPort-016-355-012 2.92 118.87 444.47 6 4 8 2 Fc1ccc(cc1NC(=O)c1ccc(NS(=O)(=O)c2cccs2)cc1)n1cnnn1
MolPort-016-351-793 2.86 119.31 472.44 6 4 8 1 COc1ccc(Cn2c(=O)c3ccccc3c2=O)cc1C(=O)Nc1cc(ccc1F)n1cnnn1
MolPort-004-482-921 2.98 120.03 482.51 7 3 7 2 COC(=O)c1ccc(CNC(=O)c2cccc(NS(=O)(=O)c3ccc4OCCOc4c3)c2)cc1
MolPort-005-845-260 2.64 120.08 456.38 4 3 7 3 Cc1nnc(NN/C=C/2C(=O)N(C(=O)c3ccccc23)c2cccc(c2)C(F)(F)F)[nH]c1=O
MolPort-007-757-935 2.61 121.76 468.48 4 5 9 1 O=C(N1CCN(CC1)C(=O)c1cc(Nc2nc3ccccc3n3nnnc23)ccc1)c1ccco1
MolPort-016-318-061 1.27 122.11 391.39 5 3 7 2 Cc1ccc(cc1NC(=O)c1cccc(CN2C(=O)CNC2=O)c1)n1cnnn1
MolPort-005-327-526 1.46 122.44 437.49 3 3 8 1 O=C(Nc1cccc(c1)n1cnnn1)[C@@H]1CCN(CC1)C1=NS(=O)(=O)c2ccccc12
MolPort-018-497-786 2.47 122.55 412.36 2 3 6 2 O=c1[nH]c(=O)c(=Cc2ccc(o2)c2ccc3c(=O)c4ccccc4c(=O)c3c2)c(=O)[nH]1
MolPort-050-857-090 2.13 122.65 439.48 4 4 7 2 CNC(=O)c1nccc(c1)C(=O)N[C@@H]1CCc2nc3ncc(cc3cc2C1)c1cncnc1
MolPort-051-704-251 2.99 122.75 567.58 1 4 7 2 Fc1ccc2cc1C(=O)N[C@H]1CN(C[C@@H]1Oc1ccc(CNC(=O)COc3cccc2c3)cc1)C(=O)c1cnncc1
MolPort-005-767-802 2.30 123.22 414.38 5 4 8 1 O=C(Nc1cccc(c1)n1cnnn1)c1ccc2c(=O)n(Cc3ccco3)c(=O)c2c1
MolPort-016-351-790 2.44 123.22 432.37 5 4 8 1 Fc1ccc(cc1NC(=O)c1ccc2c(=O)n(Cc3ccco3)c(=O)c2c1)n1cnnn1
MolPort-009-185-968 2.55 123.40 424.41 3 3 5 2 NC(=O)c1cc(NC(=O)c2ccc3C(=O)c4ccccc4S(=O)(=O)c3c2)ccc1F
MolPort-003-875-006 2.73 123.70 554.55 7 5 8 1 CCOC(=O)C(=P(c1ccccc1)(c1ccccc1)c1ccccc1)/N=N/c1nc2c([nH]1)c(=O)n(C)c(=O)n2C
MolPort-016-317-936 2.60 123.91 445.46 3 4 8 1 Cc1ccc(cc1NC(=O)c1ccc2C(=O)c3ccccc3S(=O)(=O)c2c1)n1cnnn1
MolPort-015-759-447 1.10 124.14 401.38 4 4 9 1 CS(=O)(=O)c1nc(C(=O)Nc2cc(ccc2F)n2cnnn2)c2ccccn12
MolPort-019-471-949 1.90 127.15 454.51 6 3 8 1 CC(=O)c1ccc(cc1)S(=O)(=O)N1CCC(CC1)C(=O)Nc1cccc(c1)n1cnnn1
MolPort-010-755-462 0.86 127.18 516.51 3 5 11 1 Cn1c2c(c(c([nH]2)c2cc3c(OCCO3)cc2)c2c(n3cccc3)n(C)c(=O)n(C)c2=O)c(=O)n(C)c1=O
MolPort-007-698-991 0.82 127.18 502.49 3 5 11 1 Cn1c2c(c(c([nH]2)c2cc3c(OCO3)cc2)c2c(n3cccc3)n(C)c(=O)n(C)c2=O)c(=O)n(C)c1=O
MolPort-051-711-095 2.80 127.68 598.64 2 4 8 2 Cc1nn(CC(=O)N2C[C@@H]3NC(=O)c4cc(ccc4F)c4cc(OCC(=O)NCc5ccc(O[C@H]3C2)cc5)ccc4)c(C)n1
MolPort-051-592-471 2.18 127.92 539.59 2 2 5 3 O=C([C@H]1C[C@]21C(=O)Nc1c2cccc1)N1CC2(CCCC2)c2c1ccc(c2)C(=O)N1CC[C@@]2(C1)NC(=O)NC2=O
MolPort-003-873-516 2.90 129.28 463.47 7 3 6 2 OC(=O)/C=C/c1ccc(cc1)S(=O)(=O)Nn1c(=O)/c(=C/c2ccco2)/nc1c1ccccc1
MolPort-047-146-537 1.89 130.65 722.88 4 2 8 1 CS(=O)(=O)c1ccc(CN2CCN3C[C@@H]2C(=O)N2CC[C@@H](CC2)N2CCC[C@H]2C(=O)NC2(CCN(CC2)C(=O)c2ccc(F)cc2)CC3=O)cc1
MolPort-016-317-952 1.88 133.87 451.51 5 3 8 1 Cc1ccc(cc1NC(=O)C1CCN(CC1)S(=O)(=O)c1ccc(cc1)C#N)n1cnnn1
MolPort-046-570-315 1.99 136.91 562.63 2 3 9 2 C[C@H]1NC(=O)c2c(OCCCn3cc(CN(CCCNC1=O)C(=O)Cc1ccc4OCOc4c1)nn3)cc(C)cc2
MolPort-005-780-546 2.88 137.33 492.52 6 4 9 2 O=C(Nc1ccc2OCCCOc2c1)c1cccc(c1)S(=O)(=O)Nc1cccc(c1)n1cnnn1
MolPort-005-791-198 2.49 137.33 478.49 6 4 9 2 O=C(Nc1ccc(NS(=O)(=O)c2ccc3OCCOc3c2)cc1)c1cccc(c1)n1cnnn1
MolPort-019-485-069 2.68 137.49 480.42 5 3 6 4 Oc1ccc(cn1)C(=O)NNC(=O)c1cccc(c1)S(=O)(=O)Nc1cccc(c1)C(F)(F)F
MolPort-047-768-807 2.79 137.82 455.45 3 4 7 1 O=C([C@H](C#N)c1nc2ccccc2c(=O)[nH]1)c1ccc2C(=O)c3ccccc3S(=O)(=O)c2c1
MolPort-002-363-292 2.67 137.84 423.40 4 3 6 3 OC(=O)c1cc(NS(=O)(=O)c2ccc3c(=O)c4ccccc4c(=O)c3c2)ccc1O
MolPort-051-706-687 2.87 138.17 650.69 3 4 10 1 COc1c2OCCCNC(=O)c3cc(Oc4ccc5[C@@H](N(CCc5c4)S(=O)(=O)c4cn(C)c(=O)n(C)c4=O)c(cc1)c2)ccc3F
MolPort-019-736-907 1.95 138.44 479.50 7 3 11 2 OC(=O)c1cccc(c1)c1ccc(o1)/C=N/Nc1nc(nc(n1)N1CCOCC1)N1CCOCC1
MolPort-002-324-981 2.30 138.44 479.50 7 3 11 2 OC(=O)c1cccc(c1)c1ccc(o1)/C=N/Nc1nc(nc(n1)N1CCOCC1)N1CCCOC1
MolPort-007-474-755 1.95 138.67 456.46 7 3 5 3 NC(=O)CNC(=O)c1cccc(NC(=O)c2ccc3c(=O)n(Cc4ccccc4)c(=O)c3c2)c1
MolPort-016-318-066 0.34 139.18 441.47 5 3 8 2 Cc1ccc(cc1NC(=O)c1cccc(c1)S(=O)(=O)N1CCNC(=O)C1)n1cnnn1
MolPort-047-597-539 -0.03 139.20 436.43 4 3 9 1 COC(=O)[C@H]1C[C@H]2CN(CC(=O)N2[C@H]1c1ccccc1)C(=O)c1n[nH]c(c1)n1cnnn1
A second version with a list.txt for Name and SMILES of the molecules.
import csv
from rdkit import Chem
from rdkit.Chem import Descriptors
from rdkit.Chem import rdMolDescriptors
# Path to the input file
input_file = r"D:\encinar\tempjant\24_bTRCP\104-10millones-contra-1P22\_ordena-TPSA.txt"
# Read molecules from the file
molecules = []
with open(input_file, "r") as file:
reader = csv.DictReader(file, delimiter="\t") # Use tab as the delimiter
for row in reader:
name = row["Name"] # Molecule name
smiles = row["SMILES"] # SMILES representation
molecules.append((name, smiles))
# Create a list to store molecular properties
molecule_data = []
for name, smiles in molecules:
mol = Chem.MolFromSmiles(smiles) # Convert SMILES to RDKit Mol object
if mol:
# Calculate molecular descriptors
logp = Descriptors.MolLogP(mol) # LogP: Hydrophobicity (lower = more polar)
tpsa = Descriptors.TPSA(mol) # Topological Polar Surface Area (TPSA)
mw = Descriptors.MolWt(mol) # Molecular Weight (MW)
rot_bonds = Descriptors.NumRotatableBonds(mol) # Number of rotatable bonds
arom_rings = rdMolDescriptors.CalcNumAromaticRings(mol) # Number of aromatic rings
h_acceptors = Descriptors.NumHAcceptors(mol) # Number of hydrogen bond acceptors
h_donors = Descriptors.NumHDonors(mol) # Number of hydrogen bond donors
# Append calculated properties to the list
molecule_data.append((name, smiles, logp, tpsa, mw, rot_bonds, arom_rings, h_acceptors, h_donors))
# Sort molecules by TPSA (absolute polarity)
sorted_by_tpsa = sorted(molecule_data, key=lambda x: x[3])
# Display results in a formatted table
print(f"{'Name':<20} {'LogP':<8} {'TPSA':<8} {'MW':<8} {'RotB':<6} {'AromR':<6} {'H-Accept':<10} {'H-Donors':<10} SMILES")
print("=" * 100)
for name, smiles, logp, tpsa, mw, rot_bonds, arom_rings, h_acceptors, h_donors in sorted_by_tpsa:
print(f"{name:<20} {logp:<8.2f} {tpsa:<8.2f} {mw:<8.2f} {rot_bonds:<6} {arom_rings:<6} {h_acceptors:<10} {h_donors:<10} {smiles}")
See the input _ordena-TPSA.txt:
Name SMILES
MolPort-045-630-269 O=C(Nc1ccc(NS(=O)(=O)c2ccc3OCCCOc3c2)cc1)c1cccc(c1)n1cnnn1
MolPort-044-301-427 Cc1nnc(NN/C=C/2C(=O)N(C(=O)c3ccccc23)c2cccc(c2)C(F)(F)F)[nH]c1=O
MolPort-045-628-701 Cc1ccc(cc1NC(=O)c1cccc(c1)S(=O)(=O)NCC#C)c1n[nH]c(=O)[nH]1
MolPort-046-075-198 Cc1ccc(cc1S(=O)(=O)C)C(=O)Nc1cccc(c1)c1nnc[nH]1
MolPort-050-951-899 Cc1cc(no1)C(=O)Nc1nc(co1)C(=O)N1CCc2nc3ncc(C)cc3cc2C1
MolPort-051-015-674 CN(CC(=O)N1CCC(CC1)Nc1ncnc(c1)C(F)(F)F)C(=O)c1ccc(cc1)S(=O)(=O)N1CCOCC1
MolPort-050-559-530 CC(=O)Nc1cc(C)c(cc1)S(=O)(=O)N1CCc2nc3ncc(C)cc3cc2C1
MolPort-050-566-524 Cn1c(=O)[nH]c(cc1=O)N1CCN(CC1)C(=O)c1c(c2cc(Cl)ccc2[nH]1)c1ccccc1
MolPort-049-226-531 OS(=O)(=O)c1ccc(o1)/C=N/n1cnc2c([nH]c3c2cc(Br)cc3)c1=O
MolPort-049-171-342 CN(C)S(=O)(=O)c1cc(ccc1C)C(=O)N1CCOc2c1cc(NC(=O)c1ccncc1)cc2and see the output:
Name LogP TPSA MW RotB AromR H-Accept H-Donors SMILES
====================================================================================================
MolPort-050-559-530 2.95 92.26 410.50 3 3 5 1 CC(=O)Nc1cc(C)c(cc1)S(=O)(=O)N1CCc2nc3ncc(C)cc3cc2C1
MolPort-050-566-524 2.84 94.20 463.93 3 4 5 2 Cn1c(=O)[nH]c(cc1=O)N1CCN(CC1)C(=O)c1c(c2cc(Cl)ccc2[nH]1)c1ccccc1
MolPort-046-075-198 2.44 104.81 356.41 4 3 5 2 Cc1ccc(cc1S(=O)(=O)C)C(=O)Nc1cccc(c1)c1nnc[nH]1
MolPort-049-171-342 2.93 108.91 480.55 5 3 6 1 CN(C)S(=O)(=O)c1cc(ccc1C)C(=O)N1CCOc2c1cc(NC(=O)c1ccncc1)cc2
MolPort-044-301-427 2.64 120.08 456.38 4 3 7 3 Cc1nnc(NN/C=C/2C(=O)N(C(=O)c3ccccc23)c2cccc(c2)C(F)(F)F)[nH]c1=O
MolPort-051-015-674 1.69 125.04 570.59 7 2 8 1 CN(CC(=O)N1CCC(CC1)Nc1ncnc(c1)C(F)(F)F)C(=O)c1ccc(cc1)S(=O)(=O)N1CCOCC1
MolPort-050-951-899 2.67 127.25 418.41 3 4 8 1 Cc1cc(no1)C(=O)Nc1nc(co1)C(=O)N1CCc2nc3ncc(C)cc3cc2C1
MolPort-049-226-531 2.36 130.55 437.23 3 4 7 2 OS(=O)(=O)c1ccc(o1)/C=N/n1cnc2c([nH]c3c2cc(Br)cc3)c1=O
MolPort-045-628-701 1.24 136.81 411.44 6 3 5 4 Cc1ccc(cc1NC(=O)c1cccc(c1)S(=O)(=O)NCC#C)c1n[nH]c(=O)[nH]1
MolPort-045-630-269 2.88 137.33 492.52 6 4 9 2 O=C(Nc1ccc(NS(=O)(=O)c2ccc3OCCCOc3c2)cc1)c1cccc(c1)n1cnnn1