Skip to main content

Advertisement

Table 5 Benchmarking analysis

From: Cytochrome P450 site of metabolism prediction from 2D topological fingerprints using GPU accelerated probabilistic classifiers

Data Method q   Runtime seconds   x-fold to Ref
set     Ref GT640 C2075   GT640 C2075
  RASCAL 40   42 11 2.2   4 19
  NB 40   8.8 1.4 0.3   6 29
2C9 PRW 40   436 114 32   4 14
  NB 175   8.2 1.3 0.3   6 27
  PRW 175   7.0 31 3.6   0.2 2
  RASCAL 40   57 15 3.0   4 19
  NB 40   12 1.9 0.4   6 30
2D6 PRW 40   727 157 44   5 17
  NB 175   11 1.8 0.4   6 28
  PRW 175   9.7 43 5.0   0.2 2
  RASCAL 40   298 66 13   5 23
  NB 40   55 8.3 1.8   7 31
3A4 PRW 40   3,654 714 201   5 18
  NB 175   53 8.1 1.8   7 29
  PRW 175   45 197 23   0.2 2
  1. Table shows the time taken in seconds and relative performance o the reference (Ref) to run all three classifiers over the three data sets using a scenario with bond depth of 6 (175 features) and j = 201 and q = 40. The reference is a single Intel Xeon E5506 at 2.13GHz. The number of vectors in data sets CYP 2C9, 2D6 and 3A4 are 2905, 3399 and 7294, respectively.