Skip to main content
. 2018 Oct 17;13(10):e0204587. doi: 10.1371/journal.pone.0204587

Table 3. Fraction of domains correctly classified at different SCOP hierarchy levels using a Nearest-Neighbor classifier built with similarity scores produced by different PSC and MCPSC methods.

In the SCOP hierarchy: Level 1 = Class, Level 2 = Fold, Level 3 = Superfamily and Level 4 = Family.

Original dataset Common subset Imputed dataset
SCOP Level 1 2 3 4 1 2 3 4 1 2 3 4
TM-align 1.00 1.00 0.99 0.99 0.74 0.57 0.57 0.57 1.00 1.00 0.99 0.99
CE 0.78 0.61 0.61 0.60 0.63 0.47 0.47 0.47 0.76 0.60 0.60 0.58
GRALIGN 1.00 1.00 1.00 1.00 0.74 0.57 0.57 0.57 0.89 0.89 0.89 0.88
FAST 0.20 0.08 0.08 0.08 0.19 0.07 0.07 0.07 0.20 0.08 0.08 0.08
USM 0.84 0.72 0.67 0.65 0.65 0.51 0.49 0.49 0.84 0.72 0.67 0.65
M1 0.99 0.98 0.98 0.98 0.73 0.57 0.56 0.56 0.99 0.99 0.98 0.98
M2 0.99 0.98 0.98 0.98 0.75 0.57 0.56 0.56 0.99 0.98 0.97 0.97
M3 1.00 1.00 1.00 1.00 0.74 0.57 0.57 0.57 1.00 1.00 1.00 1.00
M4 0.99 0.99 0.99 0.99 0.72 0.57 0.57 0.57 0.99 0.99 0.99 0.99
M5 1.00 1.00 1.00 1.00 0.74 0.57 0.57 0.57 1.00 1.00 1.00 1.00
Median MCPSC 0.99 0.99 0.99 0.99 0.74 0.57 0.57 0.57 0.99 0.99 0.99 0.99