Skip to main content


Fig. 3 | Journal of Cheminformatics

Fig. 3

From: Leveraging heterogeneous data from GHS toxicity annotations, molecular and protein target descriptors and Tox21 assay readouts to predict and rationalise acute toxicity

Fig. 3

Lipinski’s rule failure rate (a) and DataWarrior fragment-based druglikeness score (b) for the structures in our compound set. Compounds with an available GHS-derived acute oral toxicity classification (including implied nontoxicity) more frequently pass the Lipinski filter, which may indicate higher bioavailability among those compounds. The distributions (median and inter-quartile range) of druglikeness among the classifications are very similar, though the tail length varies. Hence, we determined that the annotated compounds did not substantially differ with regard to their druglikeness

Back to article page