Skip to main content

Table 1 Optimal hyperparameters for the standard QSAR models

From: Diversity oriented Deep Reinforcement Learning for targeted molecule generation

SVR

RF

K-NN

Kernel

C

Gamma

\(\hbox {NumEstimators}^{[1]}\)

\(\hbox {MaxFeatures}^{[2]}\)

K

Metric

’poly’

0.125

8

500

’sqrt’

11

Euclidean

  1. \({}^{[1]}\)Number of decision trees in the forest.
  2. \({}^{[2]}\)Maximum number of features considered for splitting a node. In this case, MaxFeatures = sqrt(n_features)
Back to article page

Journal of Cheminformatics

ISSN: 1758-2946

Contact us