Skip to main content


Fig. 4 | Journal of Cheminformatics

Fig. 4

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

Fig. 4

The results of toxicophore screens on the compound set, using the FAFDrugs4 screen (a, b), and the “reactive, unstable, toxic” endpoint alerts from ToxCast (c, d). The results of the FAFDrugs4 test are unable to usefully screen for acute oral toxicity as encoded by GHS classes: in B, both rejection (red bar) and acceptance (green bar) is more common in nontoxic compounds. However, there is a weak relationship between these classes and the presence/absence of the “reactive, unstable, toxic” ToxAlerts toxicophores, as illustrated by the higher red bar for the toxic compounds in D

Back to article page