Skip to main content

Table 3 Descriptive statistics and P-values are presented for the performance of generative models that implemented RL

From: A systematic review of deep learning chemical language models in recent era

 

Unbiased model

Target Model

Samples

P-values

Validity

91.1

96.5

9

0.1289

Uniqueness

99.9

89.7

7

0.0935

Novelty

91.5

93.5

4

0.2500

  1. Median values are reported for both the Unbiased and target models, and P-values were calculated through the Mann–Whitney U test for paired samples. The number of articles meeting the required metric reporting criteria for analysis is indicated by the sample’s column
Back to article page

Journal of Cheminformatics

ISSN: 1758-2946

Contact us