Table 5.
Top ranking substructures and their corresponding description and the number of occurrence in carcinogens and non-carcinogens.
| Fingerprint Key | Description | SMARTS Pattern | Present in Carcinogens | Present in Non-Carcinogens |
|---|---|---|---|---|
| AP2D-14 | N-O at topological distance 1 | [#7]~[#8] | 175 | 67 |
| AP2D-13 | N-N at topological distance 1 | [#7]~[#7] | 160 | 54 |
| Estate-28 | dsN | [ND2H0]( = *)-* | 155 | 69 |
| KR-4117 | N = O | N = O | 162 | 59 |
| KR-4301 | NN | NN | 137 | 40 |
| MACCS-52 | NN | [#7]~[#7] | 160 | 54 |
| MACCS-63 | N = O | [#7] = [#8] | 162 | 59 |
| Pubchem-423 | N = O | [#7] = ,:[#8] | 163 | 60 |
| Pubchem-515 | N-N-C-C | N-N-C-C | 131 | 43 |
| FP4-88 | Carboxylic acid derivative | [$([#6X3 H0][#6]),$([#6X3H])]( = [!#6])[!#6] | 136 | 234 |