Skip to main content
Fig. 18 | Journal of Cheminformatics

Fig. 18

From: Learning chemistry: exploring the suitability of machine learning for the task of structure-based chemical ontology classification

Fig. 18

a Number of parent classes in different approaches. b Path length to asserted parent class in different approaches. c Minimum and maximum path lengths to asserted parent classes. d D-glucopyranose 3-phosphate, an example molecule for which ClassyFire performs poorly on this metric. Training refers to the selection of members for classes in the learning task

Back to article page