MolMini small, novel scaffolds
Failure breakdown
Attempted: 2895 | exact: 2507 (0.866)
| failure mode |
n |
share of all |
share of failures |
what it points at |
| unparseable output |
19 |
0.007 |
0.049 |
decoder emitted a string RDKit cannot read |
| stereochemistry only |
178 |
0.061 |
0.459 |
skeleton correct; wedge/hash reading wrong |
| right formula, wrong bonds |
8 |
0.003 |
0.021 |
atoms counted correctly, connectivity misread |
| other structural error |
183 |
0.063 |
0.472 |
a genuinely different molecule |
Accuracy by molecule size
| heavy atoms |
n |
exact |
valid |
| <=15 |
30 |
1.000 |
1.000 |
| <=20 |
246 |
0.817 |
1.000 |
| <=25 |
750 |
0.875 |
0.996 |
| <=30 |
741 |
0.906 |
0.993 |
| <=35 |
540 |
0.876 |
0.994 |
| <=40 |
357 |
0.877 |
0.994 |
| >40 |
231 |
0.706 |
0.974 |
Accuracy by rendering style
| style |
n |
exact |
valid |
| clean |
965 |
0.917 |
0.998 |
| degraded |
965 |
0.777 |
0.989 |
| varied |
965 |
0.904 |
0.994 |
Sequence length
- Reference SMILES length, all attempted: median 46 tokens
- Reference SMILES length, correct predictions: median 46 tokens
Longest failures
| reference |
predicted |
C=C(C)[C@H]1C[C@@H](C[C@@]23C[C@@H](/C=C/C(C)C)C(C)(C)[C@@](CC=C(C)C)( |
C=C(C)[C@H]1C[C@@H](C[C@]23C[C@H](/C=C/C(C)C)C(C)(C)[C@](CC=C(C)C)(C2= |
C=C(C)[C@H]1C[C@@H](C[C@@]23C[C@@H](/C=C/C(C)C)C(C)(C)[C@@](CC=C(C)C)( |
C=C(C)[C@H]1C[C@@H](C[C@]23C[C@@H](/C=C/C(C)C)C(C)(C)[C@@](CC=C(C)C)(C |
C=C(C)[C@H]1C[C@@H](C[C@@]23C[C@@H](/C=C/C(C)C)C(C)(C)[C@@](CC=C(C)C)( |
C=C(C)[C@H]1C[C@@H](C[C@]23C[C@@]4(C(=O)c5cc(OC)c(O)cc5O[C@]45C(C)(C)C |
CC(C)[C@]12O[C@H]1[C@@H]1O[C@]13[C@]1(O[C@H]1C[C@H]1C4=C(CC[C@@]13C)C( |
CC(C)[C@]12C[C@@H](OC(=O)CCCCOc3no[n+]([O-])c3S(=O)(=O)c3ccccc3)[C@@]3 |
NC(=O)C(CC(=O)O)NC(=O)[C@@H]1CCOc2c(I)cc([N+](=O)[O-])cc2C(=O)N[C@@H]( |
NC(=O)C(CC(=O)O)NC(=O)[C@@H]1CCOc2c(I)cc([N+](=O)[O-])cc2C(=O)N[C@@H]( |