MolMini base, chembl_test_linux
Failure breakdown
Attempted: 3000 | exact: 2692 (0.897)
| failure mode |
n |
share of all |
share of failures |
what it points at |
| unparseable output |
9 |
0.003 |
0.029 |
decoder emitted a string RDKit cannot read |
| stereochemistry only |
120 |
0.040 |
0.390 |
skeleton correct; wedge/hash reading wrong |
| right formula, wrong bonds |
11 |
0.004 |
0.036 |
atoms counted correctly, connectivity misread |
| other structural error |
168 |
0.056 |
0.545 |
a genuinely different molecule |
Accuracy by molecule size
| heavy atoms |
n |
exact |
valid |
| <=10 |
9 |
1.000 |
1.000 |
| <=15 |
84 |
0.821 |
0.976 |
| <=20 |
324 |
0.948 |
1.000 |
| <=25 |
741 |
0.923 |
0.997 |
| <=30 |
741 |
0.924 |
0.999 |
| <=35 |
576 |
0.887 |
1.000 |
| <=40 |
327 |
0.838 |
0.997 |
| >40 |
198 |
0.773 |
0.985 |
Accuracy by rendering style
| style |
n |
exact |
valid |
| clean |
1000 |
0.952 |
0.998 |
| degraded |
1000 |
0.806 |
0.997 |
| varied |
1000 |
0.934 |
0.996 |
Sequence length
- Reference SMILES length, all attempted: median 47 tokens
- Reference SMILES length, correct predictions: median 46 tokens
Longest failures
| reference |
predicted |
CC(=O)OC[C@H]1O[C@@H](O[C@H]2[C@H](OC(C)=O)[C@@H](OC(C)=O)[C@H](S(N)(= |
CC(=O)OC[C@H]1O[C@@H](S(N)(=O)=O)[C@H](OC(C)=O)[C@@H](OC(C)=O)[C@@H]1O |
CC(=O)OC[C@H]1O[C@@H](O[C@H]2[C@H](OC(C)=O)[C@@H](OC(C)=O)[C@H](S(N)(= |
CC(=O)OC[C@H]1O[C@@H](S(N)(=O)=O)[C@H](OC(C)=O)[C@@H](OC(C)=O)[C@@H]1O |
CC(=O)OC[C@H]1O[C@@H](O[C@H]2[C@H](OC(C)=O)[C@@H](OC(C)=O)[C@H](S(N)(= |
CC(=O)O[C@H]1CC[C@@]2(C)C(=CC[C@H]3[C@@H]4CC[C@H]([C@H](C)CCCC(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@@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@@H](/C=C/C(C)C)C(C)(C)[C@](CC=C(C)C)(C |