MolMini small, DECIMER HDM
Failure breakdown
Attempted: 1000 | exact: 125 (0.125)
| failure mode |
n |
share of all |
share of failures |
what it points at |
| unparseable output |
66 |
0.066 |
0.075 |
decoder emitted a string RDKit cannot read |
| stereochemistry only |
45 |
0.045 |
0.051 |
skeleton correct; wedge/hash reading wrong |
| right formula, wrong bonds |
3 |
0.003 |
0.003 |
atoms counted correctly, connectivity misread |
| other structural error |
761 |
0.761 |
0.870 |
a genuinely different molecule |
Accuracy by molecule size
| heavy atoms |
n |
exact |
valid |
| <=10 |
431 |
0.109 |
0.905 |
| <=15 |
325 |
0.138 |
0.957 |
| <=20 |
172 |
0.122 |
0.965 |
| <=25 |
70 |
0.171 |
0.929 |
| <=30 |
2 |
0.000 |
1.000 |
Sequence length
- Reference SMILES length, all attempted: median 20 tokens
- Reference SMILES length, correct predictions: median 20 tokens
Longest failures
| reference |
predicted |
CSC(=S)C1=c2sc(s2)=C(C(=S)SC)SCCOCCOCCS1 |
C=C(C)C(=O)C=C(C)P(=O)(F)F |
O=S(=O)(O)OCN(COS(=O)(=O)O)COS(=O)(=O)O |
CC(C)S(=O)(=O)OCN(COS(=O)(=O)O)COS(=O)(=O)O |
C#C[C@@]1(O)CC2CCC3C(CCC4(C)C3CC[C@@H]4O)C2(C)C1 |
C=C[C@]1(O)CC2CCC3C4CC[C@H](O)C4(C)CCC3C2(C)C1 |
O=C(OI(OC(=O)C(F)(F)F)C(F)(F)F)C(F)(F)F |
O=C(OC(OC(=O)C(F)(F)F)C(F)(F)F)C(F)(F)F |
CN[C@H]1CC[C@@]2(C)C(=CC[C@H]3[C@@H]4CC[C@H](N)[C@@]4(C)CC[C@@H]32)C1 |
CN[C@H]1CC[C@@]2(C)C(=CC[C@@H]3[C@@H]2CC[C@]2(C)[C@@H](O)CC[C@@H]32)C1 |