Skip to main content

Table 6 Benchmark results of the general model G for all four objectives

From: Conditional reduction of the loss value versus reinforcement learning for biassing a de-novo drug design generator

objective

Validity

Novelty

Uniqueness

intDiv

Desirability

1

77.53

92.63

79.23

0.80

41.90 = 2385

2

78.62

92.16

81.02

0.80

17.04 = 996

3

81.17

91.73

81.30

0.80

9.81 = 594

4

77.01

92.28

78.44

0.81

1.25 = 69

Back to article page

Journal of Cheminformatics

ISSN: 1758-2946

Contact us