Skip to content

MolMini base, novel scaffolds

Failure breakdown

Attempted: 2895 | exact: 2588 (0.894)

failure mode n share of all share of failures what it points at
unparseable output 11 0.004 0.036 decoder emitted a string RDKit cannot read
stereochemistry only 121 0.042 0.394 skeleton correct; wedge/hash reading wrong
right formula, wrong bonds 13 0.004 0.042 atoms counted correctly, connectivity misread
other structural error 162 0.056 0.528 a genuinely different molecule

Accuracy by molecule size

heavy atoms n exact valid
<=15 30 1.000 1.000
<=20 246 0.854 0.984
<=25 750 0.900 0.995
<=30 741 0.927 0.997
<=35 540 0.889 1.000
<=40 357 0.899 1.000
>40 231 0.801 0.996

Accuracy by rendering style

style n exact valid
clean 965 0.938 0.998
degraded 965 0.808 0.995
varied 965 0.936 0.996

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)(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)(C2=
Cc1c(C)c2c(c(C)c1OC(=O)CCC(=O)NC1CC(C)(C)N([O])C1(C)C)CCC(C)(C(=O)NC1C Cc1c(C)c2c(c(C)c1OC(=O)CCC(=O)NC1CC(C)(C)N([O])C1(C)C)CCC(C)(C(=O)N[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)C2(C[C@@H](/C=C/C(C)C)C(C)(C)[C@@]3(CC=C(C)C)C(=
Cn1nc(N)c2cccc(-c3cccnc3[C@H](Cc3cc(F)cc(F)c3)NC(=O)Cn3nc(C(F)(F)F)c4c Cn1nc(N)c2cccc(-c3cccnc3[C@H](Cc3cc(F)cc(F)c3)NC(=O)Cn3nc(C(F)(F)F)c4c