Table 2.
Average of sensitivity, specificity, precision and standard deviations for block-level identification over 500 replications
| Method | Graph type | Sensitivity (SD) | Specificity (SD) | Precision (SD) |
|---|---|---|---|---|
| STB | Random | 0.9201 (0.1178) | 0.9996 (0.0049) | 0.9988 (0.0157) |
| STC | 0.9034 (0.1219) | 1 (0) | 1 (0) | |
| ZIBR | 0.9117 (0.1228) | 1 (0) | 1 (0) | |
| ANCOM-BC | 1 (0) | 0 (0) | 0.2 (0) | |
| Hu et al. [14] | 0.1510 (0.1255) | 0.9719 (0.0326) | 0.5806 (0.4815) | |
| STB | Hub | 0.8690 (0.1250) | 1 (0) | 1 (0) |
| STC | 0.9917 (0.0447) | 0.9869 (0.0255) | 0.9581 (0.0814) | |
| ZIBR | 0.8648 (0.1404) | 1 (0) | 1 (0) | |
| ANCOM-BC | 1 (0) | 0 (0) | 0.2 (0) | |
| Hu et al. [14] | 0.0945 (0.1213) | 0.9588 (0.0307) | 0.3634 (0.4739) | |
| STB | Cluster | 0.9467 (0.1025) | 0.9975 (0.0123) | 0.9919 (0.0395) |
| STC | 0.9318 (0.1115) | 1 (0) | 1 (0) | |
| ZIBR | 0.8128 (0.1340) | 1 (0) | 1 (0) | |
| ANCOM-BC | 1 (0) | 0 (0) | 0.2 (0) | |
| Hu et al. [14] | 0.1175 (0.1259) | 0.9655 (0.0323) | 0.4630 (0.4966) |
Different graph types are set to reflect various correlation structures among OTUs. Random graph structure indicates that OTUs are correlated with each other randomly. The hub and cluster graphs capture some aspects of biological networks, such as highly connected nodes and community structure. More details can be found in Osborne et al. [20]