Table 3 Classification accuracy using mixed-genome array data with non-hierarchical clustering for four sample (bacterial species) clusters. PA is the prediction accuracy.
From: A Java-based tool for the design of classification microarrays
| Â | Number of clusters of probes, Îş | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Â | 2 | 5 | 10 | 20 | 30 | 40 | ||||||
Number of top-ranked probes | PA (%) | No. of probes | PA (%) | No. of probes | PA (%) | No. of probes | PA (%) | No. of probes | PA (%) | No. of probes | PA (%) | No. of probes |
50 | 100 | 2 | 100 | 5 | 100 | 7 | 100 | 7 | 100 | 1 | 75 | 1 |
100 | 100 | 2 | 100 | 5 | 100 | 7 | 100 | 7 | 100 | 7 | 100 | 1 |