From: STOUT: SMILES to IUPAC names using neural machine translation
No. | IUPAC names | BLEU Score | IUPAC names translated into SMILES using OPSIN | Tanimoto similarity Index | ||
---|---|---|---|---|---|---|
Original | Predicted | Original | Predicted | |||
1 | 4-[(4-amino-2,3,6-trimethylphenyl)methyl]-2,3,5-trimethylaniline | 4-[(4-amino-2,3,5-trimethylphenyl)methyl]-2,3,6-trimethylaniline | 1.0 | NC=1C=C(C(=C(C1C)C)CC=2C(=CC(N)=C(C2C)C)C)C | NC1=C(C=C(C(=C1C)C)CC2=CC(=C(N)C(=C2C)C)C)C | 0.97 |
2 | 3-[(3-amino-2,6-diethylphenyl)methyl]-2,4-diethylaniline | 3-[(3-amino-2,4-diethylphenyl)methyl]-2,6-diethylaniline | 1.0 | NC1=CC=C(C(=C1CC)CC=2C(=CC=C(N)C2CC)CC)CC | NC=1C(=CC=C(C1CC)CC2=CC=C(C(N)=C2CC)CC)CC | 0.92 |
3 | 2-{4-[(dimethylamino)methyl]-6-[(2,6-dimethylphenoxy)methyl]-6-hydroxycyclohexa-2,4-dien-1-yl}acetonitrile | 2-{4-[(2,6-dimethylphenoxy)methyl]-6-[(dimethylamino)methyl]-6-hydroxycyclohexa-2,4-dien-1-yl}acetonitrile | 1.0 | N#CCC1C=CC(=CC1(O)COC=2C(=CC=CC2C)C)CN(C)C | N#CCC1C=CC(=CC1(O)CN(C)C)COC=2C(=CC=CC2C)C | 0.93 |
4 | 4-[4-(3-hydroxycyclohepta-1,3,6-trien-1-yl)phenyl]-N-(7-methylcyclohepta-1,4,6-trien-1-yl)butanamide | 4-[4-(3-hydroxycyclohepta-1,4,6-trien-1-yl)phenyl]-N-(7-methylcyclohepta-1,3,6-trien-1-yl)butanamide | 1.0 | O=C(NC1=CCC=CC=C1C)CCCC=2C=CC(=CC2)C=3C=CCC=C(O)C3 | O=C(NC1=CC=CCC=C1C)CCCC=2C=CC(=CC2)C=3C=CC=CC(O)C3 | 0.95 |
5 | (but-1-en-2-yl)(prop-1-en-1-yl)amine | (but-1-en-1-yl)(prop-1-en-2-yl)amine | 1.0 | C=C(NC=CC)CC | C=C(NC=CCC)C | 0.97 |