Table 2. Vector class prediction efficiency.
RFM model predictions* | ||||
---|---|---|---|---|
Vectors | Material | Strong | Weak | |
LV_1 | DC | 100 | 0 | |
LV_2 | DC | 100 | 0 | |
A | AP205_3 | DC | 3 | 97 |
MLV_2 | DC | 5 | 95 | |
AP205_1 | Spleen | 99 | 1 | |
MVA_1 | Spleen | 100 | 0 | |
B | rAd_1 | Spleen | 98 | 2 |
MLV_1 | Spleen | 9 | 91 | |
MPT_1 | Spleen | 0 | 100 | |
AP205_1 | PBMC | 73 | 27 | |
MVA_1 | PBMC | 90 | 10 | |
Qb_1 | PBMC | 99 | 1 | |
Qb_2 | PBMC | 95 | 5 | |
C | Qb_3 | PBMC | 100 | 0 |
Qb_4 | PBMC | 100 | 0 | |
Qb_5 | PBMC | 98 | 2 | |
MLV_1 | PBMC | 0 | 100 | |
MPT_1 | PBMC | 0 | 100 | |
rAd_1_6 | Spleen | 98 | 2 | |
D | rAd_1_48 | Spleen | 0 | 100 |
rAd_1_72 | Spleen | 2 | 98 |
*Number of the 100 bootstrapped datasets predicted as “Strong” or “Weak”.