Table 6.
Results obtained from detection of similar data items for different templates
| Keyword | Number of data after running predefined query | Number of similar data | Human Judgment |
|---|---|---|---|
| Template label: 1 | |||
| MJFJKKXQDNNUJF-UHFFFAOYSA-N | 10 | 8 | Yes |
| MSTNYGQPCMXVAQ-KIYNQFGBSA-N | 30 | 12 | Yes |
| PMATZTZNYRCHOR-IMVLJIQENA-N | 5 | 3 | Yes |
| GUGOEEXESWIERI-UHFFFAOYSA-N | 347 | 99 | No |
| SEKGMJVHSBBHRD-WZHZPDAFSA-M | 6 | 2 | Yes |
| HSMNQINEKMPTIC-UHFFFAOYSA-N | 341 | 106 | No |
| Template label: 2 | |||
| C1 = CC(=CC(=C1)F)CSC2 = NC3 = C(N2)C = NC = C3 | 4 | 3 | Yes |
| CCOC(=O)C1(CCN(C)CC1)c2ccccc2 | 104 | 65 | No |
| C1CCC(CC1)N2C(=O)C3 = CC = CC = C3N = C2SCC#N | 3 | 2 | Yes |
| CC1CCCCC1NC(=S)NC2 = CC = C(C = C2)SC(F)F | 2 | 0 | Yes |
| CC1(CC1(Cl)Cl)C(=O)NNC(=O)C2CCCCC2 | 7 | 3 | Yes |
| Nc1nc(O)c2NC(CNc3ccc(cc3)C(=O)N[C@@H](CCC(=O)O)C(=O)O)CNc2n1 | 23 | 18 | Yes |
| Template label: 3 | |||
| AAAAKTROWFNLEP-UHFFFAOYSA-N | 2 | 0 | Yes |
| MIQPIUSUKVNLNT-UHFFFAOYSA-N | 107 | 41 | No |
| STQGQHZAVUOBTE-VGBVRHCVSA-N | 149 | 50 | Yes |
| UWWDHYUMIORJTA-HSQYWUDLSA-N | 2 | 0 | Yes |
| XCGSFFUVFURLIX-VFGNJEKYSA-N | 20 | 2 | Yes |
| ZPEIMTDSQAKGNT-UHFFFAOYSA-N | 117 | 44 | Yes |
| Total matching: 92% (over all 50 test cases) | |||