Table 2.
Results of different chemotypes diversity analyses on the data sets.
| Database | N | N/M | Nsing | Nsing/N | Nsing/M | AUC | F50 |
|---|---|---|---|---|---|---|---|
| Fungal metabolites | 131 | 0.587 | 87 | 0.664 | 0.390 | 0.664 | 0.244 |
| MEGx | 935 | 0.374 | 642 | 0.687 | 0.257 | 0.781 | 0.072 |
| NATx | 799 | 0.320 | 400 | 0.501 | 0.160 | 0.768 | 0.116 |
| GRAS | 238 | 0.106 | 150 | 0.630 | 0.067 | 0.926 | 0.004 |
| Anticancer drugs | 70 | 0.921 | 65 | 0.929 | 0.855 | 0.537 | 0.457 |
| Non-anticancer drugs | 844 | 0.572 | 686 | 0.813 | 0.465 | 0.699 | 0.157 |
N, number of chemotypes; M, number of molecules; Nsing, number of singletons; AUC, area under the curve; F50, fraction of chemotypes that contains 50% of the data set.